• November 3-7, Chicago

    AMIA 2012 Annual Symposium

    Informatics: Transforming Health and Healthcare

AMIA 2012 Tutorials & Working Group PreSymposia

CME/CE eligibility

  • Half-Day sessions = 3 CME/CE
  • Full Day sessions = 6 CME/CE
  • Full Day and One-Half Day sessions = 9 CME/CE
Tutorials are CME/CE eligible and incur an additional fee beyond the registration fee. Tutorials and Working Group PreSymposia fees are not included in the registration fee.

* If you have already registered for AMIA 2012, but at a later date would like to add tutorials, the Networking Meet-up or Up Comedy Club ticket, please click to read these steps.

  1. Login to your AMIA account
  2. Go to My Profile.
  3. Click the Invoices & Transactions tab of the page
  4. Scroll to Events
  5. Find AMIA 2012 and click on “Add Tracks/Sessions”
  6. Select the appropriate sessions, click “Save/Add to cart” and proceed with check-out.

Tutorial & Working Group PreSymposia Length

CME/CE eligible creditsFull &
Member Advantage
Half-Day sessions3$95$150$95
Full Day sessions6$190$300$190
Full Day and One-Half Day9$190$300$190
CMIO/CNIO Tutorial (includes box lunch and reception)9$385$485$385

*Note: WISH 2012 is not a CME/CE eligible session.

Saturday, November 3, 8:30 a.m. – 12:00 p.m.

T-01: Clinical Research Informatics: Theory, Methods, and Best Practices

Content Level: 20% basic, 50% intermediate, 30% advanced
Fee: $95 member/student $150 non-member

Intended Audience: Scientists; researchers; physicians, nurses, and other healthcare professionals; and computer scientists, system developers, and programmers. You should attend … if you would like to increase your understanding of clinical research informatics and its relationship with other biomedical informatics subdisciplines as well as the clinical/translational sciences. You want to plan and implement complex information management architectures in order to support a full spectrum of clinical research activities. CME/CE=3

Philip Payne, Peter Embi, The Ohio State University

Clinical research is critical to the advancement of medical science and public health. Conducting such research is a complex, resource intensive endeavor comprised of a multitude of actors, workflows, processes, and information resources. Recent national-level research and policy efforts have explicitly focused on increasing the clinical research capacity of the biomedical sector, largely through fostering improvements in both workflow and information management infrastructure. These efforts have served to increase attention on clinical research throughout the governmental, academic, and private sectors. In the specific context of the intersection between biomedical informatics and clinical research, the emergence of both a notable body of literature and a set oft-targeted funding mechanisms such as the National Cancer Institute’s (NCI) Cancer Biomedical Informatics Grid (caBIG) and National Center for Advancing Translational Science (NCATS) Clinical and Translational Science Award (CTSA) programs have served as significant catalysts for the emergence of a robust sub-discipline of informatics focusing on clinical research applications, known as Clinical Research Informatics (CRI).

In this tutorial, we will provide researchers, technical leaders, and technical staff with an overview of the core definitions and informatics theory that collectively contribute to the successful practice of CRI. We will use a set of research vignettes to illustrate common challenges and opportunities in the CRI space and best-practice approaches to such scenarios, include: 1) the design and implementation of integrative clinical research information management systems; 2) the query of disparate enterprise and research information systems to support clinical research activities and information dissemination/reporting; and 3) the identification and recruitment of clinical research participants via multiple retrospective and prospective modalities.

By the end of the tutorial, participants will be able to:

  • Define clinical research informatics and understand its relationship with other biomedical informatics subdisciplines as well as the clinical/translational sciences
  • Synthesize the role of current healthcare and informatics policy and standards setting developments relative to the practice of CRI.
  • Identify and apply core informatics theories, methods, and best practices in order to analyze and plan solutions to common clinical research information management challenges
  • Plan for and implement complex information management architectures in order to support a full spectrum of clinical research activities

Outline of Topics:

  • Clinical Research Informatics (CRI) definition and relationship(s) to other biomedical informatics subdisciplines and the clinical/translational sciences
  • Current CRI-relevant funding, policy, and standards-setting efforts or initiatives
  • Enterprise architectures for integrative clinical research information management
  • Semantic interoperability and knowledge engineering in the clinical research domain
  • The relationship of human factors and/or workflow optimization to the effective deployment and utilization of clinical research information management systems
  • Common CRI challenges and their solutions

T-02: Analysis of Human Interaction Behavior for Supporting Health IT Design

Content level: 20% basic, 40% intermediate, 40% advanced
Fee: $95 member/student $150 non-member

Intended Audience: Informatics researchers; healthcare professionals; health IT professionals with an interest in informatics, hospital administrators and physicians interested in understanding and improving their clinical work processes. You should attend … if you want to learn new approaches for capturing and analyzing behavioral data including underlying patterns of sequential behavior, network-theoretic and time-series characteristics, and how to apply these techniques to solve new problems in clinical contexts. CME/CE=3

Thomas Kannampallil, The New York Academy of Medicine; Kai Zheng, University of Michigan; Vimla Patel, The New York Academy of Medicine

Most clinical environments resemble a paradigmatic complex system with its dynamic and interactive collaborative work, non-linear and interdependent activities and uncertainty. Addition of new organizational and systemic interventions, such as health information technologies (health IT), can cause considerable cascading effects in the clinical processes, workflow and consequently on throughput and efficiency. The recent IOM report [1] called for the need for a socio-technical approach for designing and incorporating health IT in clinical contexts. One of the critical aspects of a socio-technical approach is to understand the progression and evolution of human interactions within a socio-technical context. In other words, a better understanding of human interactions in a clinical setting with technology, peers and other artifacts is necessary for a successful and effective socio-technical approach.

This tutorial will discuss a set of convergent methodologies for analyzing human interaction behavior both with technology and with other humans or artifacts. These methodologies will assist in capturing underlying patterns of human interaction behavior, and provide a mechanism to develop integrative, longitudinal metrics for clinical activities for sustained interactive episodes that evolve over time (for e.g., metrics related to performance, or errors). In this tutorial, we will (a) identify challenges to capturing and analyzing human interaction from complex clinical contexts; (b) discuss new approaches for capturing and analyzing sequences of human interaction in clinical settings using sequential analysis and network-theoretic, time-series based and probabilistic methods; (c) utilize one or more of these techniques to demonstrate their effectiveness as a viable mechanism for developing insights on clinical work activities through hands-on sessions; and (d) provide participants hands-on experience in using data collection and data analysis tools.

By the end of the tutorial, participants will be able to:

  • Identify the challenges related to capturing and analyzing human interaction in biomedical contexts
  • Identify new approaches for capturing and analyzing behavioral data including underlying patterns of sequential behavior, network-theoretic and time-series characteristics
  • Develop preliminary understanding of using off-the-shelf applications to perform these analyses
  • Applying these techniques to solve new problems in clinical contexts
  • Structure their data into formats that are amenable to these analyses: for researchers, healthcare professionals, and hospital administrators (Hands on)

Outline of Topics:

  • Overview of concepts of human interaction in biomedical contexts (with health IT, people, and other artifacts)
  • Basic understanding of challenges to capturing and analyzing human interaction data
  • Human interaction data: sources, types and nature
  • New sources and modes of data: methods of collecting data
  • Human interaction as sequences: how to identify patterns of cognitive behavior from sequences of interactions
  • Methods: sequential analysis techniques, social network analysis (including temporal analysis), time-series based evaluation, and probabilistic approaches
  • Tools for analyzing sequences and networks
  • Developing customized applications for analyzing sequences and networks of human behavior (Advanced)

T-03: Knowledge-Based Decision-Support Systems for Implementing Clinical Practice Guidelines

Content Level: 50% basic, 30% intermediate, 20% advanced
Fee: $95 member/student $150 non-member

Intended Audience: Clinicians who are interested in understanding how guidelines can be delivered as part of a computerized clinical decision-support system. Developers and informaticians who are interested in understanding issues related to computerized guideline implementation. You should attend … if you are a clinician, developer, or informatician who would like to increase his/her understanding of issues related to computerized guideline implementation. CME/CE=3

Samson Tu, Stanford University; Mor Peleg, Haifa University; Susana Martins, VA Palo Alto Health Care Systems; Mary Goldstein, Stanford University School of Medicine

In recent years, professional societies, health maintenance organizations, medical publishers, and government agencies have produced a flood of clinical practice guidelines (CPGs) for the purpose of disseminating evidence-based best practices to healthcare providers. The expectation is that, with the adoption of these CPGs, or more generally, clinical recommendations, unwarranted practice variations will be reduced, quality of care will increase, and cost can be contained through decrease in unnecessary tests and procedures. Computer-based decision-support tools can enhance the implementation of these guidelines by bringing focused recommendations to care providers at the point of decision-making. This tutorial will first give an introduction to the concept of clinical decision-support systems, the role CPGs play in the practice of medicine, and then look at the process of operationalizing narrative CPGs recommendations into format ready for formal encoding in some computer-interpretable model. We will discuss alternative representation formats for delivering clinical recommendations.

In particular, we will introduce Arden Syntax-based Medical Logic Modules and model-based formats such as EON and PROforma. We will demonstrate how encoded CPG knowledge bases can be applied to simulated patient data to generate patient-specific recommendations. Using some real clinical recommendations as examples, the tutorial will cover the life cycle of system development, including requirement analysis, distillation and disambiguation of guideline knowledge, modeling of patient data, encoding of the clinical recommendation in a formal model, testing, and deployment. We will look at issues of integrating decision support into clinical information systems and socio-technical issues in system development and deployment. Presentations will be interspersed with hands-on collaborative work sessions and live demonstrations.

By the end of this tutorial, participants will be able to understand:

  • the concept of knowledge-based clinical decision support systems (CDSS) for guideline-based care
  • the steps and issues involved in encoding guideline knowledge
  • alternative methods for representing computable clinical practice guidelines (CPGs)
  • the issues involved in deploying and integrating CDSS for guideline-based care
  • existing and emerging standards in CDS

Outline of Topics:

  • ntroduction to clinical decision-support (CDS) systems
  • Output of CDS systems
  • Process of operationalizing clinical recommendations for use in CDS

T-04: Innovations in Standards & Standards Development: The Use & Re-use of Healthcare Data

Content Level: 40% basic, 40% intermediate, 20% advanced
Fee: $95 member/student $150 non-member

Intended Audience: Healthcare informatics professionals; CMIOs; CIOs; and care givers (physicians and nurses) who must improve the healthcare quality and reduce healthcare costs. You should attend … to gain an understanding of the varied approaches to standards adoption in the USA and internationally of sharing healthcare data. To gain an appreciation for the innovative approaches to standards development and integrations. CME/CE=3

Charles Jaffe, Health Level 7 International; Doug Fridsma, Office of the National Coordinator for Health Information Technology; Rebecca Kush, CDISC; Stanley Huff, Intermountain Healthcare and University of Utah Medical Center; Christopher Chute, Mayo Clinic; Robert Dolin, Lantana Group

The simple unambiguous sharing of healthcare data is insufficient to meet the needs of our delivery systems if we are to improve quality and reduce costs. Exchange must support the reuse of data for a broad range of purposes, including quality evaluation, decision support, clinical research, primary medical science application, public health, and comparative effectiveness. The standards needed to support these goals must rapidly evolve despite an environment constrained by the limited availability of resources, by government regulation and by a rapidly evolving knowledge base. Standards development and the organizations that provide those standards are applying innovative approaches to achieving those demands.

This tutorial will provide the attendees with the background, the rapidly evolving processes, the technical elements, and the innovating approaches to solving the complex problems of interoperable data exchange. In the United States, there are significant objectives for data exchange that are defined by the regulatory requirements of Meaningful Use. For international standards development organizations (SDO), the challenges approach a much larger scale. Regional regulatory differences, parochial research objectives, and shrinking healthcare budgets contribute to the complexity of these international requirements.

Within the scope of this tutorial, we will explain the innovative approaches to these demands and establish the framework for their solution, both near term and in more strategic terms. The requirements in the US will be highlighted as one of the approaches taken by standards developer to recognize the goal of improved quality and safety, while supporting the fiscal requirements of constrained budgets.

By the end of this tutorial, participants will be able to:

  • Recognize the challenges facing standards development on a global scale.
  • Understand the varied approaches to standards adoption in the US and internationally
  • Appreciate the innovative approaches to standards development and integration
  • Appreciate the complexities of the technical requirements

Outline of Topics:

  • Defining the challenges
  • Applying new approaches to standards development
  • Developing innovative solutions to information modeling
  • Accelerating innovation solutions through collaboration
  • Advancing the imperative of vocabulary standards

T-05: User Centered Design for Public Health & Consumer Health Information Systems

Content level: 50% basic, 50% intermediate
Fee: $95 member/student $150 non-member

Intended Audience: This tutorial is aimed at informatics professionals, project sponsors, project managers, and business analysts working within public health or consumer health settings. You should attend … if you want to learn more about User-centered design (UCD). This is a system development approach that puts the user, rather than the technologist at the center of the design effort. CME/CE=3

Barbara Massoudi, RTI International; Rupa S. Valdez, University of Wisconsin-Madison

User centered design (UCD) is a system development approach that puts the user, rather than the technologist at the center of the design effort. Traditional systems development is often technologist driven, prioritizing the expertise and assumptions of the designer. Consequently, it often fails to adequately consider users’ needs and preferences. User acceptance of these systems is often challenging and redesign and development efforts can be prohibitively costly and time consuming.

Although UCD has demonstrated success in involving users and better meeting their needs, it is infrequently used in public health/consumer health information systems (PH/CHIS) development efforts. Using both didactic and hands-on small group case studies, we will introduce the concept of UCD; present the benefits and implications of UCD in PH/CHIS development efforts; and, introduce specific UCD methods/techniques. Additionally, we will discuss how UCD fits within the context of iterative and prototyping system development life cycles, business process reengineering, and usability testing, as these methods are often used in PH/CHIS development efforts. The techniques/methods presented will be relevant to multiple levels of design including the user interface, functionality, content, and integration with other elements of the larger system with which the PH/CHIS is to be integrated.

Outline of Topics:

  • Introduction, expectation and experience statements
  • Rationale for user centered design
  • User centered design methods and techniques
  • Case study presentation
  • Developing user centered design work plans: Small group activity
  • Group presentations of plan
  • User centered design caveats

WG-01: Recommendations for Developing, Evaluating, and Implementing Drug-Drug Interactions CANCELED

Content Level: basic 25%, intermediate 50%, advanced 25%
Fee: $95 member/student $150 non-member

Intended audience: Individuals responsible for developing DDIs systems, application vendors, clinicians and others responsible for maintaining clinical decision support systems, and end-users of clinical decision support systems. CME/CE=3

Presented by the AMIA Pharmacoinformatics Working Group
Terry Seaton, St. Louis College of Pharmacy; John Poikonen, UMass Memorial Health Care; Daniel Malone, Lisa Hines, University of Arizona College of Pharmacy; Shoba Phansalkar, Partners Health Car; Joan Kapusni-Uner, FDB Health; M. Susan Ridgely, Rand Corp.

The evidence suggests that hundreds of millions of interacting drugs are co-prescribed each year, ultimately exposing hundreds of millions of patients to these known hazards. Although the exact magnitude of harm associated with drug-drug interactions (DDIs) is not known, clinically significant interactions occur, resulting in potentially life-threatening consequences. Electronic prescribing and pharmacy information systems include DDI alerts as a form of clinical decision support (CDS) to warn prescribers and pharmacists of potentially harmful medication combinations, and provide them with necessary information to avoid or mitigate the risk of patient harm. Meaningful Use Stage 1 and 2 includes the need for drug-drug interaction (DDI) checking. Despite the availability of this technology to improve patient safety, it has fallen short of fulfilling the promise to reduce and/or eliminate DDIs. In particular, research has shown that “the current DDI alert system is broken.” This pre-symposium will outline the issues and best practices to optimize drug interaction checking.

Outline of topics:

  • Anatomy of a drug-drug interaction (DDI)
  • The Evidence Conundrum: How Evidence is Generated and used to Identify DDIs
  • Alternate DDI checking methods: It is not always alerts
  • Selecting DDIs for alerts: vendor-based, de novo, or mixed approaches
  • Too Many Alerts, Too Much Liability: Sorting Through the Malpractice Implications of Clinical Decision Support and DDI Lists
  • The Top Drug Interactions: The Envelope Please

Saturday, November 3, 8:30 a.m. – 4:30 p.m.

T-06: Clinical Classifications and Biomedical Ontologies: Terminology Evolution, Principles, and Practicalities

Content level: 75% basic, 25% intermediate
Fee: $190 member/student $300 non-member

Intended Audience: Scientists; researchers; physicians, nurses, and other healthcare professionals; computer scientists, system developers, and programmers. Clinicians, scholars, biomedical researchers with an interest in or need for terminologies. You should attend … if you want to understand the origins and evolution of terminologies and ontologies as well as practical access methods. CME/CE=6

Christopher Chute, Mayo Clinic; James Cimino, NIH Clinical Center; Mark Musen, Stanford University

Standardized terminologies and classification systems are an essential component of the information infrastructure that supports healthcare delivery and evaluation. Despite significant advances and increased motivation for the use of terminology systems, widespread integration of standardized terminologies into computer-based systems has not yet occurred. In this tutorial, we provide an overview of the state of the science related to terminologies and classification systems and demonstrate application of selected terminologies to a patient case study to highlight the strengths and weaknesses of various terminologies. Standardized terminologies alone are insufficient to achieve semantic interoperability. Consequently, the tutorial will include content designed to elucidate the relationships among standards for terminologies, information models, messages, and document and record structures. In addition, we will demonstrate the use of advanced terminology tools that facilitate the use of standardized terms in computer-based systems and provide an overview of significant international and national initiatives related to terminology systems.

By the end of the tutorial, participants will be able to:

  • Understand the origins and evolution of terminologies and ontologies
  • Appreciate the present state of the art in health terminology development and deployment
  • Articulate the dependencies within Meaningful Use standards on ontologies and vocabularies
  • Demonstrate practical access methods to many terminologies and ontologies

Outline of Topics:

  • Historical appreciation of the evolution and development of terminology and ontologies
  • An overview of current terminologies and ontologies used in clinical practice
  • The relationship of terminologies and ontologies to Meaningful Use Standards
  • Speculations about the future trends and current developments in health related terminologies and ontologies
  • A laboratory practicum on accessing and using clinical terminologies
  • Desiderata for practical and effective terminologies and ontologies
  • Practical examples and demonstrations about current terminologies and ontologies

T-07: End to End Quality Reporting from Electronic Health Records

Content Level: 25 % basic, 50% intermediate, 25% advanced
Fee: $190 member/student $300 non-member

Intended Audience: Chief Medical Information Officers; Chief Nursing Information Officers; Quality Managers; Clinician Informaticists; Healthcare Policy Advisors You should attend … if you are a medical informatician who is not familiar with HL7& or the National Quality Forum Quality Data Model. This tutorial will introduce the audience to the logistic, technical and semantic aspects of expressing, processing and reporting from Electronic Health Records (EHRs). CME/CE=6

Robert Dolin, Lantana Consulting Group; Floyd Eisenberg, National Quality Forum; Gaye Dolin, Lantana Consulting Group

We begin with an overview of the "end-to-end" quality measurement process and define the infrastructure requirements. The tutorial will clearly explain how efforts by the National Quality Forum (NQF), and Health Level Seven (HL7) are converging to collaboratively meet the needs of the Office of the National Coordinator's (ONC) EHR certification regulations and the Centers for Medicaid and Medicare Services (CMS) "Meaningful Use" (MU) requirements.

NQF has been instrumental here, in part through their rigorous clinical quality measure endorsement process, and in part through their development of the Quality Data Model (QDM), which is a domain analysis model of the types of criteria recurrently found in quality measures (such as "active diagnosis", "discharge medication"). The QDM forms a foundational basis for the semantic interoperability of quality measures.

HL7's role in the collaboration is to turn quality requirements and the QDM into formal computer processable specifications, that work together seamlessly to support the quality reporting process. As part of that process, HL7 has developed the Health Quality Measure Format (HQMF) standard (also referred to as the eMeasure standard) for formalizing the logic in clinical quality measures; and the Quality Reporting Document Architecture (QRDA) standard for communicating patient-level quality data.

HQMF and QRDA work with other MU standards, such that a MU-certified EHR can (in theory) automatically process an eMeasure – import it, turn it in to dynamic queries to extract relevant patient data, package up the data, and transmit it securely to CMS or some other quality reporting agency in QRDA format.

As we will describe, the process for EHR-based quality reporting is being studied for its applicability to distributed decision support and distributed population-based public health reporting.

By the end of this tutorial, participants will be able to:

  • Understand how ONC and CMS are building an EHR-based quality reporting framework in the United States via federal "Meaningful Use" regulations
  • Understand the role of the National Quality Forum (NQF) and the NQF's Quality Data Model (QDM) in the US quality reporting infrastructure
  • Understand how Health Level Seven (HL7) is aligned with ONC, CMS, and NQF in support of an end to end quality reporting process
  • Understand the HL7 standards being developed to support quality reporting

Outline of Topics:

First half:

  • Provide an overview of the measure development and endorsement process to provide measures for public reporting.
  • Describe the unique aspects of quality reporting from Electronic Health Records with respect to the quality data workflow from capture to aggregation.
  • Describe the shift in thought process required for clinical guideline and measure developers, EHR vendors, system implementers, and clinicians to move from abstraction and attestation measures to eMeasures.
  • Describe the NQF Quality Data Model (QDM) and how it manages semantics and context for consistent expression and reporting of clinical information.
  • Describe the relationship of measures to phenotype expression using QDM for research, post-market surveillance and distributed decision support.
  • Describe the role of ONC, CMS, and National Quality Forum (NQF) in defining an end to end quality reporting process.
  • Describe Meaningful Use (MU), and how it is driving quality reporting in the United States.

Second half:

  • Introduce the notion of "end to end" quality reporting.
  • Describe how HL7 is addressing end to end quality reporting from a big picture view.
  • Describe how HL7 is aligning with ONC to enable Meaningful Use objectives for quality reporting.
  • Describe the various HL7 standards that together address the end to end quality reporting requirements.
  • Describe how the HL7 standards work together to support a seamless end to end quality reporting process.

T-08: Managing Stakeholder Dissonance in Healthcare Informatics: Theory & Applications CANCELED

Content Level: 40% basic, 40% intermediate, 20% advance
Fee: $190 member/student $300 non-member

Intended Audience: Clinicians, IT professionals, healthcare managers, researchers, patient advocates, policy makers You should attend … if you want to gain the basic knowledge and tools required to identify, measure, and control SD for your organization’s HIT efforts, or you are an informatician, clinician, information technologist, manager, who wants to better understand the root causes for difficulties and failures in realizing the benefits of HIT. CME/CE=6

George Samaras, Samaras & Associates, Inc.; Elizabeth Samaras, University of Colorado-Pueblo; Harrie Samaras, ADR & Law Office of Harrie Samaras

Stakeholder dissonance (SD) is defined as the conflict between the Needs, Wants, and Desires (NWDs) of stakeholder groups. SD is unrelated to cognitive dissonance and always requires two or more stakeholders. The existence of errors, workarounds, threats to patient safety and organizational profitability, and outright rejection of Health Information Technologies (HIT) are diagnostic for SD. SD may be viewed as a clash of values. SD threatens the viability of any HIT effort and must be managed (identified, measured, and controlled). In this tutorial, you will understand the conceptual models, learn to apply concrete tools, and gain the knowledge to create and analyze strategies to resolve, reduce or mitigate SD across the full lifecycle of HIT implementations.

At the end of the tutorial, the participants will be able to:

  • Understand the fundamental concepts of SD and how to manage SD risks
  • Understand the principles and techniques of recognizing and measuring conflicting NWDs
  • Understand the concepts of mediations and alternate dispute resolution techniques
  • Understand the concepts of verification and validation and how to determine successful SD reductions

Outline of Topics:

  • Introduction to SD & SD Management
  • Case Study Analysis and Select/Create Roles
  • Eliciting SEES, Identifying NWDs, and Mapping SD
  • Mock Focus Group & Kano Questionnaires
  • Mediation Concepts & Alternate Dispute Resolution
  • SD Risk Analysis & Prioritizing Dissonance Mitigations
  • Deployment Design Verifications & Validation
  • Verifying Dissonance Reductions

T-09: R and Open Source Solution for Computational Biology

Content level: 20% basic, 50% intermediate, 30% advanced
Fee: $190 member/student $300 non-member

Intended Audience: Academic and professional wanting to gain hands-on skills to analyze biomedical or clinical data as well as an overview of R possibilities. Translational scientists and students interested in analyzing their genomic data and to learn how to integrate them with external resources. You should attend … if you want a basic introduction to the R language through practical examples and you want hands-on experience to learn how to analyze biomedical or clinical data. If you are a translational scientist or student interested in analyzing genomic data and learning how to integrate them with external resources. CME/CE=6

David Ruau, Joel Dudley, Stanford University

Contemporary biomedical research requires integrative approaches that require
knowledge and expertise across multiple methods, software tools, and molecular profiling technologies.

This includes analysis and interpretation of traditional RNA and SNP microarrays, tools and methods for manipulating next-generation sequencing (NGS) data locally or in the cloud, to leveraging available biomedical knowledge found across various databases. The remarkable diversity of data available from public repositories and numerous tools and methods to combine and analyze them presents daunting informatics challenges to biomedical research.

In this tutorial we propose to provide an introduction to R, one of the most popular statistical computing platforms for biomedical research, and also provide an in-depth perspective of the relevant open source tools and resources available for analyzing genomic data. There are more than 3,200 general statistical packages available for R, with 500+ packages providing bioinformatics functionality alone. However, like other statistical software, the learning curve can present a formidable hurdle to the effective use of the R platform’s capabilities--even for those with programming experience. This tutorial is based on the successful workshop “Introduction to R programming” taught at Stanford and will include examples from Stanford Biomedical Informatics courses, as well as clinical genomics examples based on the forthcoming book, Exploring Personal Genomics, by Joel Dudley and Konrad Karczewski.

The first part of the tutorial will be dedicated to the R platform. This tutorial is based on the successful workshop “Introduction to R programming” taught at Stanford. Participants will be introduced to the basic of the R language through practical examples from real biomedical research projects. We will show advance techniques on how different resources can be plug into R to perform an analysis and produce publication ready graphics.

At the end of this part, participants will be able to:

  • To import/export and transform data from different resources, including databases
  • Perform exploratory graphical analysis
  • Write R functions and objects
  • Example of how to analyze microarray data
  • Interpret their results using metadata from KEGG and GO
  • Have an overview of the tools to perform GWAS and NGS analysis

Outline of topics:

  • Introduction to the R console and programming language.
  • Producing publication grade quality graphics easily
  • Directly downloading raw data from public microarray repositories
  • Clustering and graphical solutions available in R
  • Knowledge database and metadata accessible through R package repositories
  • Advance topics (GWAS, high level graphics, reproducible research ... )

The second part of the tutorial will cover approaches for performing integrative and translational bioinformatics.

At the end of this part, participants will be able to:

  • Integrate data from different data resources
  • Visualize integrated data
  • Interface R with other software and programming languages
  • Run computationally intensive code using parallel programming techniques

Outline of topics:

  • Data integration using statistical methods and structured identifiers
  • Network visualization
  • Interfacing R with Ruby and Python
  • Parallel and multicore programming packages for R
  • Specific tutorial examples to integrate multiple molecular data, perform clinical genome interpretation

WG-02: Natural Language Processing Working Group Pre-Symposium – a doctoral consortium and a data workshop

Content Level: TBD
Fee: $190 member/student $300 non-member

Intended audience: Anyone interested in clinical NLP is welcome. Doctoral students working on biomedical and clinical NLP projects and researchers who want to learn and share NLP knowledge are strongly encouraged to attend. CME/CE=6

Presented by the AMIA Natural Language Processing Working Group
Wendy Chapman, University of California at San Diego; Peter Haug, University of Utah and Intermountain Healthcare; Stephane Meystre, University of Utah; Jon Patrick, University of Sydney; Guergana Savova, Harvard Medical School and Children’s Hospital Boston; Imre Solti, Cincinnati Children’s Hospital Medical Center; Ozlem Uzuner, University at Albany; Hua Xu, Vanderbilt University

Natural Language Processing (NLP) technologies have received great attention in the clinical domain and have demonstrated numerous uses in many biomedical applications. The pre-symposium of the AMIA NLP working group provides a unique platform for close interactions among students, scholars, and industry professionals who are interested in clinical NLP. The event will consist of two sections: 1) a doctoral consortium, where students can present their work and get feedback from experienced researchers in the field; and 2) a workshop with a focused theme for each year. This year, our focus is data in clinical NLP research, including all aspects such as their availability, the character of the documents, and issues of annotation. Our excellent podium and poster presentations will provide participants a complete picture of how to find, create, and use different data sets for their clinical NLP applications.

Sessions and Goals:

The pre-symposium will be divided into two 3-hour sections:

Section 1 – The Doctoral Consortium

The purpose of the doctoral consortium is to provide opportunities for direct interactions between students and researchers in the clinical NLP field, so that we can help students 1) refine their research focus; 2) answer specific questions about study design, algorithm development, or evaluation plan; 3) provide critiques and suggestions about their dissertation work; and 4) establish possible collaborations.

Section 2 – The Data Workshop

Specific goals of the DATA workshop include:

  • Learn about existing data sets for clinical NLP research and know how to obtain them if available
  • Be aware of issues of annotation and be familiar with annotation tools and annotation processes
  • Understand essential designs for creating data sets for research projects
  • Obtain knowledge on data management, maintenance, and distribution
  • Learn how to use the data to develop robust models

Outline of topics:

  • Available data sets for clinical NLP research
  • What are they?
  • How to obtain them?
  • What are the uses?
  • Introduction to clinical data
  • How are they generated?
  • Document types and related issues
  • Data storage and management
  • Annotation of clinical text
  • Annotations tools
  • Annotation guideline development
  • Annotation processes
  • Annotation quality control
  • Study design related to data creation
  • Reference standards (development and maintenance)
  • Performance measurement
  • Model development from data
  • Model types and hybrid models (regular expressions, rules, machine learners)
  • Model development
  • Error analysis of models
  • Applications
  • Problem types and their contexts (document classification, records retrieval, information retrieval, information extraction, question answering, care protocol auditing)
  • Application systems (existing systems used by clinicians and researchers)
  • Hybrid applications (CLP inside other systems)

WG-04: Using Electronic Health Records for Quality Reporting of Nurse Sensitive Outcomes

Content Level: 100% intermediate
Fee: $190 member/student $300 non-member

Intended Audience: Informatics professionals from all areas of practice (vendors, clinicians, researchers, and educators) should find this tutorial contemporary and relevant to current issues with Meaningful Use. CME/CE=6

Presented by the AMIA Nursing Informatics Working Group
Connie Delaney, University of Minnesota; Beth Franklin, Rosemary Kennedy, National Quality Forum; Judith Warren, University of Kansas School of Nursing; Patricia Dykes, Brigham and Women’s Hospital; Laura Heermann Langford, Intermountain Healthcare; Judy Murphy, Office of the National Coordinator for Health Information Technology

The tutorial will be introduced with a panel presentation describing national quality measurement initiatives and regulations related to electronic health record (EHR) certification and the Centers for Medicaid and Medicare Services (CMS) “Meaningful Use” (MU) requirements.

National initiatives related to meaningful use of certified EHR technology clearly state the need for electronic quality reporting. This requires electronic capture of health information in a coded format to support decision support at the point of care, as well as, reporting of clinical quality measures. This tutorial will focus on data considered essential for quality reporting, as defined by national initiatives, using patient falls as one of the nurse sensitive outcome areas. The
tutorial will explain the quality data infrastructure necessary to support electronic quality reporting, covering the Quality Data Model (QDM), which ensures that clinical concepts found within quality measures are represented in a standardized and unambiguous format within EHRs. This unambiguous representation enables the creation of eMeasures which is the electronic format for quality measures using the QDM and the Healthcare Quality Measure Format (HQMF), an HL7standard. Participants will learn methods to represent evidence-based data related to nursing outcomes within EHRs.

Through hands-on exercises, participants will apply data modeling principles to clinical scenarios, using patient falls as one of many nurse sensitive outcome areas.

By the end of this tutorial, participants will be able to:

  • Describe the national initiatives and regulations related to meaningful use of EHRs and quality reporting;
  • Identify three major nursing sensitive outcomes areas and the role for the EHR and quality reporting;
  • Describe the role of the QDM in supporting quality reporting from the EHR;
  • Apply the Health Quality Measure Format as a standard for representing a quality measure as an electronic document
  • Define methods for using the QDM and structured terminology to support evidence-based patient falls documentation screens

Outline of Topics:

  • Overview of the national quality agenda and the role of ONC, CMS, NQF, in defining an HIT infrastructure for quality reporting.
  • Overview of the relationship between the national quality agenda, ANA, and NDNQI.
  • Overview of national initiatives and regulations related to quality reporting from EHRs as directed by meaningful use criteria.
  • Nursing sensitive outcome areas and the association with respect to evidence-based nursing and quality reporting.
  • eMeasure life cycle and the association with quality measure representation, clinical documentation, quality reporting, and evidence-based care.
  • Overview of the Quality Data Model and the associated relationship with semantic representation of evidence-based documentation and quality reporting, using patient falls as the use case example.
  • The role for the Health Quality Measures Format (HQMF) and Clinical Document Architecture specifically the Quality Reporting Document Architecture (QRDA) in reporting quality data.

WG-05: HIT Best Practices and Worst: Learning from Success and Failure

Content Level: TBD
Fee: $190 member/student $300 non-member CME/CE=6

Presented by the AMIA Clinical Information Systems, Ethical Legal and Social Issues, Evaluation, People & Organizational Issues and Regional Informatics Action Working Groups
Jos Aarts, Erasmus University Rotterdam; Jennifer Boehne, Epic; Catherine Craven, MU Informatics Institute; Paul R. DeMuro, Latham & Watkins LLP; Joseph Kannry, Mount Sinai Medical Center; Bonnie Kaplan, Yale University; Ross Koppel, University of Pennsylvania; Jonathan Leviss, Dearborn Advisors, LLC and Thundermist Health Center; Larry Ozeran, Clinical Informatics, Inc. and University of California, Davis Health System; Minakshi Tikoo, University of Connecticut Medical School; Heleen van der Sijs, Erasmus University Medical Center; Charlene Weir, University of Utah School of Medicine Associate Director, Education and Evaluation, VA SLC GRECC, Salt Lake City, UT

This Working Group Pre-symposium is a collaborative effort of several working groups offering a broad overview of best practices to follow in HIT and poor practices to avoid. Faculty are drawn from these working groups in order to provide the breadth of expertise to support the educational objectives and will supplement the didactics by contributing to the discussion and conversation with the audience. Attendees will learn about selection, implementation, and optimization issues through tips and tactics from the front line, from real implementation scenarios at multiple settings of care, including in rural communities, as well as vendors and consultants that work with them. Topics will cover the broad scope of factors in the lifecycle of the software that determine if HIT implementations are HIT or miss.

By the end of this tutorial, participants will be able to:

  • Define and explain the software selection process
  • Understand the contractual obligations in the purchase of HIT
  • Integrate the demands of vendors, competing priorities, and people customizing the software in their institution
  • Develop test scenarios for implementation and optimization
  • Understand the implementation process, indicators that support safety and quality, and how to reduce unintended consequences
  • Describe the role of workflow
  • Identify issues with site specific customizations
  • Understand several different cultures in healthcare (providers, IT departments, vendors, and organizational executives) and how those cultures impact management of HIT
  • Differentiate the various causes of problems, e.g. software error or implementation mistake
  • Develop and implement reporting strategies for safety issues
  • Delineate the key legal issues which clinicians and others face today with the implementation and operation of healthcare technology
  • Integrate the role of ethics in HIT projects

Outline of topics:

  • HIT selection process
  • Pre-implementation planning, including workflow planning and the dangers of workarounds
  • Involving all stakeholders in all parts of the HIT lifecycle
  • Developing for selection, implementation, and optimization
  • Considering legal issues, including contracting throughout the lifecycle
  • Managing customizations to balance risks and benefits,
  • Ensuring adequate training in all phases including implementation and optimization
  • Updating / upgrading systems
  • Patient safety and CPOE: Errors caused by system and ensuring appropriate alerts (specificity and sensitivity)
  • Designing and supporting interoperability / connectivity
  • Safety reporting and early failure monitoring, promoting a failure-ready culture
  • Buying an EHR Effectively ... Evaluation strategies and pitfalls to avoid
  • Legal Issues Associated with Emerging Technology in the Healthcare Space, including Contract Considerations
  • Implementation ... including pre-implementation analyses, vendor fixes, customization, "builds"
  • Communication … Getting clinicians to speak up and report problems and then listening; workarounds
  • Maintaining relationships - working with your IT folk, vendor relations
  • Continuous monitoring and evaluation - tools and methods
  • Case Studies-Learning from Failure
  • Managing Failure
  • Ethics

Saturday, November 3, 8:30 a.m. – 4:30 p.m. AND Sunday, November 4 8:30 a.m. – 12:00 p.m.

Both Tutorials are 9 hour session finishing on Sunday morning.


T-10 CMIO registration is only available ONLINE. Onsite registration in Chicago will not be available for this session.

This is a 9-hour, 2-day tutorial, which will continue on Sunday, November 4, 8:30 a.m. – 12:00 p.m. There will also be a reception with hors d’oeuvres on Saturday evening for CMIO/CNIO Tutorial registered participants only.

Content level: 20% beginners, 40% intermediate, 40% advanced
Fee: $385 member/student $485 non-member (includes box lunch and reception)

Intended Audience: New CMIO/CNIOs seeking new skills; Established CMIO/CNIOs seeking to develop new skills and build knowledge; Individuals aspiring to serve in the role of CMIO/CNIO seeking to understand the position and its challenges. CME/CE=9

Jane Carrington, University of Colorado, Denver; Adam Cheriff, Weill Cornell Medical College; Paul Fu, Jr., Harbor-UCLA Medical Center; Jonathan Gold; Linda Harrington, Catholic Health Initiatives; Julie Hollberg, Emory Healthcare; Joseph Kannry, Mount Sinai Medical Center; David Liebovitz, Northwestern University; Mary Beth Mitchell; Richard Schreiber, Holy Spirit Hospital; Ferdinand Velasco, Texas Health Resources

The goal of this tutorial is to introduce new and provide continuing education for established CMIOs, CNIOs, (and others who play similar roles such as Medical Directors for Information Systems, etc.,) to a set of topics that will help them carry out their professional responsibilities and also provide them with a deeper understanding of the field of informatics. The offering will help to assure that their organizations realize the potential benefits that health IT can bring and also to assure that the organizations will meet their meaningful use requirements.

Objectives for attendees:

  • Link back to something practical that attendees can bring back “home” and use, especially for the CMIO and CNIO in the community hospital
  • How to advance in academic medicine when what you’re doing is “operations”
  • Obtain up-to-date practical information on selected biomedical informatics topics

Outline of topics:

  • CMIO/CNIO evidence-based practice
  • CMIO/CNIO practical toolkit
  • How to read and apply informatics literature
  • CMIO/CNIO year in review
  • Evaluating new technologies
  • Implementing Clinical Decision Support
  • Leading Meaningful Use
  • CMIO/CNIO partnerships
  • CMIO/CNIO and evolving models of care

WG-03: Current Issues for Population Health Informatics in Healthcare and Public Health

The WG-3 Pre-symposia session is supported by CGI Federal

This is a 9-hour pre-symposium, which will continue on Sunday, November 4, 8:30 a.m. – 12:00 p.m.

Content level: TBD
Fee: $190 member/student $300 non-member

Intended Audience: public health practitioners from the state, local and clinical care levels; healthcare informatics professionals who are interested in population health practice, research and outcomes; Public Health Informatics Workgroup members; students and young practitioners and researchers. CME/CE=9

Presented by the AMIA Public Health Informatics Working Group
Rita Altamore, University of Washington; Laura Conn, Centers for Disease Control and Prevention; Paul Fu Jr., David Geffen School of Medicine at UCLA and UCLA School of Public Health; Janet Hamilton, Florida Department of Health; John W. Loonsk, CGI Federal; J. Marc Overhage, Siemens Healthcare; Catherine Schenck-Yglesias, Christina L. Stephan, University of Missouri

Webcast Option

Webcast registration is also $95. In Webcast format, this Pre-symposia is not eligible for CME/CEs.

To attend the WG-3 Pre-symposia Webcast

  • Register online for the Symposium (profile required)
  • Change the default setting on the pull down menu marked “Reg Type” to Webcast.
  • Select the Webcast under “Event Fees”
  • Save and proceed to checkout.
  • Once registered a link for the Webcast will be emailed

Many informaticists strive to advance population health outcomes whether they are working in healthcare or public health organizations. This year, with the opportunities of Meaningful Use and no dedicated national public health informatics conference, it is especially important to bring public health and healthcare informatics professionals together to discuss timely population health informatics issues and suggest paths forward.

In this pre-symposium, healthcare and public health informatics participants will understand, discuss, and advance current population health informatics issues. Faculty will frame different sides of each issue to develop understanding and a common vocabulary for discussion. Pre-symposium participants will then discuss each issue to further a shared understanding and common ground. Finally issue consensus statements designed to move the management of each issue forward will be developed and communicated broadly.

Timely issues will be included (in session topics list) that are associated with advancing population outcomes in Accountable Care Organizations, supporting non-syndromic surveillance needs, viability of federated query for public health, registries at the EHR, ACO, and health department levels, using population data for the public good, public health challenges with Meaningful Use, decision support for population health workers, the viability of two way communication between public health and healthcare, and more.

Description of Session

Goals for this workshop include:

  • Bring public health and AMIA informatics professionals together to discuss timely population health issues and explore collaboration
  • Expose and engage AMIA healthcare informatics participants in broader public and population health practice and research needs
  • Expose more public health and CDC professionals to AMIA professionals
  • Advance the discussion of fundamental and pressing population and public health informatics issues

Saturday, November 3 - Each individual session will be led by two or more faculty members who will make short framing presentations that present different perspectives on an issue. The faculty with then lead a structured discussion of each issue by all participants to develop more shared depth of understanding and work toward common ground. Before the pre-symposium and on Saturday night, possible consensus statements that move the issues forward will be developed.

Sunday, November 4 - The possible consensus statements will be reviewed by the faculty, discussed and additional refinements suggested. The final common ground consensus statements will be subsequently communicated broadly.

Topics to be covered

Potential issues for individual session framing, discussion and consensus statements:

Information Exchange for Detection and Monitoring - Clinical Care to Health Departments

  • Issue: Public Health Surveillance needs are met by syndromic data and lab results
  • Issue: Federated query can supplant public health reporting

Information Exchange for Communication and Coordination - Health Department to Clinical Care

  • Issue: Healthcare provider needs for public health information are clear and feasible

Best Practices for Health Registries

  • Issue: Registries should exist at the: 1) EHR level, 2) Accountable Care Organization level, 3) Health Department level, 4) All of the above

Balancing Personal and Population Privacy Needs

  • Issue: Public discussion of public health needs for identifiable data lead to less data sharing
  • Issue: The third data class (identified, de-identified, and ?) needs better definition for better protection

Health Departments and HITECH / ACA

  • Issue: Meaningful use is not meaningful to public health
  • Issue: Public health infrastructure cannot support existing demands

Long Term Objectives for Working Population Issues

  • Issue: ACO’s should promote a healthcare – public health relationship more like the European model
  • Issue: Clinical decision support obviates the need for population health workers

WISH 2012

Fee: $190 member/student $300 non-member

Addressing the complex interplay between human, organizational, and technological systems in healthcare is a significant research area with the potential to impact quality, safety, efficiency, and effectiveness of health care in America. Although new research initiatives aim to better align health information technology, real clinical practices, and design of technologies informed by the best practices in Human Factors and Human-Computer Interaction, current efforts exist in several disjointed research communities, without established pathways for transfer of knowledge and expertise.

At WISH 2012, researchers and practitioners with an interest in health information technology will come together to create deeper and more profound connections among the biomedical, informatics, human-computer interaction, medical sociology and anthropology communities that can lead to the development of new methods, approaches, and techniques to remove the barriers for the adoption of HIT. This workshop is designed to foster conversation, bridge communities, and develop a shared body of knowledge across these communities.

WISH 2012 has an exciting program, including keynote speakers, peer-reviewed panel and poster submissions, and mentoring program. This event is open to all interested parties, even without a submission to the workshop. If you have any questions about WISH, please contact the workshop organizers at wish2012workshop@gmail.com

Saturday, November 3, 1:00 p.m. – 4:30 p.m.

T-11: Introduction to workflow technology: Representation of healthcare processes in a workflow editor and their execution in a workflow engine

Content Level: 60% basic, 20% intermediate, 20% advanced
Fee: $95 member/student $150 non-member

Intended Audience: Those with some prior interest in workflow technology, but little or no prior practical exposure to it. In terms of professional roles, informatics scientists or healthcare administrators interested in using WT, computer scientist, system developers, and programmers. You should attend … if you have had little or no prior practical exposure to workflow technology and would like to attain an understanding of workflow processes and software tools designed for process authoring, execution and mining. CME/CE=3

Vojtech Huser, National Institutes of Health; Harm Scherpbier, Main Line Health

This tutorial will provide an introduction to workflow technology, also known as Business Process Management (BPM). In the first part, the tutorial will provide historical overview, evolution and introduction into Workflow Management Systems and introduce the benefits of formal representation of processes. The second part will provide overview of the current process representation standards and in detail describe the XPDL standard (XML process definition language) from Workflow Management Coalition. Finally, in the third part, the participants will be able to see (and follow) a hands-on demonstration of use of an open source workflow editor, engine, workflow mining tool and view and modify examples of healthcare process definitions. Relationship of decision support engines to workflow engines will also be discussed.

By the end of the tutorial, participants will be able to:

  • Understand how processes can be modeled in a workflow editor and executed in a workflow engine and properly define key workflow technology terms
  • Explain how workflow technology evolved in the past, the current representation standards and use of workflow technology in healthcare and other industries
  • Provide examples of processes and be familiar with exemplary software tools for process authoring, process execution and process mining

Outline of topics:

Part 1: Introduction to workflow technology (business process management)

  • Need for specifying workflow within IT systems
  • History of workflow technology (prior 1960s-1980s)
  • Overview of development after 1990
  • Components of workflow technology (process definition, execution engine, analytical components)
  • Benefits of implementing a workflow server within a generic IT system
  • Major workflow vendors and open-source workflow technology tools
  • Workflow Technology in healthcare
  • Future development and research challenges

Part 2: Workflow technology standards, standard developing organizations and related theories

  • Workflow management coalition’s (WfMC) standards
  • Definition of WT terms (Terminology and Glossary)
  • XML process definition language (XPDL)
  • Other standardization efforts
  • Research-originated WT standards
  • Petri Nets theory and its relationship to workflows

Part 3: Practical tools demonstrations and case studies of use of workflow technologies

  • Demo of an open-source, XPDL-based workflow editor and engine (Enhydra)
  • Demo of an open-source process mining tool (ProM)
  • Brief overview of other workflow technology software
  • Overview of non-healthcare industries using WT
  • Published case studies of use in healthcare/informatics research
  • Main Line Health and Siemens Soarian case study
  • Marshfield Clinic case study
  • What are the differences between a decision support engine and a workflow engine

T-12: Using Electronic Health Records to facilitate clinical, genomic, and pharmacogenomic research: Experiences from the eMERGE and PGRN Networks

Content level: 30% basic; 50% intermediate; 20% advanced
Fee: $95 member/student $150 non-member

Intended audience: Clinical and genetic researchers; providers interested in reuse of EHR data; translational bioinformaticians and medical informaticians. You should attend … if you want to better understand the basic principles of genetic analysis; use of standard vocabulary in representing phenotype data, use of standards-based approaches for constructing and representing phenotype algorithms. CME/CE=3

Jyotishman Pathak, Mayo Clinic; Joshua Denny, Hua Xu, Vanderbilt University

This tutorial will cover basic themes about use of Electronic Health Records (EHRs) for generating cohorts of patients to serve as cases and controls for given clinical phenotypes. EHRs can be used for many different types of research include disease-based, response to treatment, clinical biomarkers, redefining “normal”, and analysis of changes over time of clinical variables and parameters. Deriving such phenotypes from EHR data can be challenging. Methods typically involve use of structured data such as billing codes, medication records, and laboratory data, as well as unstructured data such as narrative reports, for which natural language processing (NLP) system are often used.

After derivation of these phenotypes, populations can be used for clinical research. Linkage to DNA biobanks also enables the possibility of genomic and pharmacogenomic associations. Research within the eMERGE and PGRN networks have demonstrated success with EHR-based genome-wide association studies (GWAS). In addition, use of EHR-linked genetic data uniquely enables phenome-wide associations studies (PheWAS), which allows an unbiased scan of what diseases may be associated with a given genotype.

This tutorial will review the design of EHR-linked biobanks; methods for creating phenotype algorithms with integrated use of NLP, billing codes, laboratory and test results, and medication records (with review of a number of case studies); basic principles of genetic analysis (candidate gene, GWAS, exome chips, and other platforms); use of standard vocabulary in representing phenotype data, use of standards-based approaches for constructing and representing phenotype algorithms; and application of PheWAS to further characterize clinical variants.

At the end of this tutorial, the participants will be able to:

  • Learn how to query EHR data and general approaches for phenotype algorithm development and evaluation.

Outline of Topics:

  • Introduction to genome wide association studies (GWAS)
  • Examples of “GWAS” reuse for new phenotypes, with significant new findings
  • Approaches
  • When to use a fully-automated phenotyping approaches vs. “computer assisted” approach, and the importance of specific review interfaces (with demonstrations)
  • Phenotyping algorithms
  • Case studies in several eMERGE and PGRN algorithms: what has worked, and what hasn’t
  • Discussion of experiences with cross-institution implementation of phenotype
  • NLP methods
  • Phenotype data standardization and representation of phenotype algorithms
  • Standards-based representations of phenotype elements, demographics, and comorbidities
  • Phenome-wide association studies (PheWAS) using EMR data for relevant genomic variants

T-13: Best Practices for Teaching Informatics

Content level: 80% basic; 10% intermediate; 10% advanced
Fee: $95 member/student $150 non-member

Intended Audience: Informatics educators; Training directors, Industry with interest training in Informatics, health care professionals, informatics researchers You should attend … if you are an informatics educator or researcher with an interest in best practices for informatics education. CME/CE=3

Vimla L Patel, The New York Academy of Nursing; Judith Warren, University of Kansas School of Nursing; Mark Carroll, University of California, Davis; Michael Chiang, Oregon Health & Science University

The practices of teaching and learning are intimately related. The best practices in teaching relate to the best learning outcomes, and they follow from a combination of activities: encouraging faculty development as teachers; engaging students with high levels of thinking in their studies, using most current instructional methods available; and implementing regular, thoughtful, and periodic assessment procedures to provide ongoing feedback: to students about the progress of their learning, and to program faculty about how well their program is meeting its objectives. The best teaching, just like the best science and the best medicine, is a moving target and so the process of pursuing best practice is just a process, something fluid and dynamic that we all try to stay actively involved with as much as we possibly can.

Informatics is a multidisciplinary field and it lives equally in both the world of practice and the world of science. This is what makes the field complex in terms of training. As a science, it is concerned with the structuring and representation of knowledge and models of information processing in human beings and computers. Practice in informatics focuses on the design and implementation of systems and tools that facilitate the delivery of information, such as health care, and can be used to train practitioners as well as to support research. Innovative methods of training students in Informatics to work with our industrial partners—such as HIT vendors, healthcare organizations, and HIE organizations, to create learning opportunities outside the traditional laboratory is critical in this time of health care reform and meaningful use of health information technology.

This tutorial will attempt to capture the current status of the field in terms of instruction in Informatics, and the nature of what makes a successful training program, successful. Lectures and discussions will be lead by four faculty members, who have expertise in teaching and learning in informatics from variety of perspectives. It will cover theoretical foundations, as well as practical experiences with introducing new informatics program sat different schools, and teaching of informatics using various available tools.

By the end of the tutorial, participants will be able to:

  • Identify the relationship between the theoretical foundation and the evaluation of practical problems in training in biomedical informatics
  • Identify and approach challenges related to teaching introductory biomedical informatics courses to diverse groups of students
  • Structure a program to the population of interest: researchers, IT professionals, clinicians, industry, and population health
  • Create opportunities to collaborate with employers and other stakeholders to develop meaningful evidence –based biomedical informatics training programs

Outline of Topics:

  • Overview of concepts from learning and cognitive sciences
  • Informatics as a diverse discipline
  • Informatics as science and as practice
  • Basic understanding of best practices in teaching
  • Lessons from teaching introductory biomedical informatics
  • Challenges in teaching to diverse students
  • Open-ended discussions with audience about problems in teaching Informatics course
  • Review of principles of good practice in education.
  • Approaches for selecting courses, assignments and evaluation strategies
  • Demonstrate the assignments for teamwork as mentioned in the IOM reports
  • Learning and evaluating informatics knowledge, skills, and abilities
  • Similarities and differences: Training for Industry, academia and practice

T-14: Fundamentals of EHR Usability

Content Level: Basic, 75%; Intermediate, 20%; Advanced, 5%
Fee: $95 member/student $150 non-member

Intended Audience: Those involved in designing, developing, maintaining and implementing EHRs including: EHR developers and programmers; EHR designers; EHR software quality assurance personnel; Information Technologists charged with assisting the EHR acquisition process; Physicians, nurses, and other healthcare professionals; Graduate students and postdoctoral fellows. You should attend … if you have minimal experience in usability and human factor and want to learn the fundamental principles of usability and human-centered design. CME/CE=3

Jiaije Zhang, University of Texas; Amy Franklin, UT Health; Muhammad Walji, University of Texas School of Dentistry at Houston

A current and significant challenge in the design and implementation of health information technology (HIT) is to deal with the high failure rate of HIT projects. Most of these failures are not due to flawed technology, but rather due to the lack of systematic considerations of human factors and other non-technology issues in the design and implementation processes. In other words, designing and implementing HIT is not so much an IT project as a project about human-centered computing akin to human-computer interaction, workflow, organizational change, and process reengineering. Due to the complexity and unique features of healthcare, human-centered methods and techniques specifically tailored for this domain are necessary for the successful development of health information systems such as electronic health records (EHRs). Good usable design would engender systems that increase efficiency and productivity, are easy to use and straight forward to learn, increase user adoption, retention, and satisfaction, and decrease medical errors, development time and cost. In this tutorial we will focus on teaching two methods appropriate for assessing EHR usability. After the half-day tutorial, the attendees should have a basic understanding of the usability issues in health IT and have gained skills enabling them to evaluate the usability of EHRs and related products using these methods.

By the end of the tutorial, participants will be able to:

  • Understand the principles of usability and human-centered design
  • Understand the significance of usability and human-centered design and the consequences of technology-driven development
  • Describe usability methodologies and techniques to evaluate health information systems
  • Perform user testing and expert reviews to detect usability problems in health information systems

Outline of topics:

  • Role of usability in adoption and meaningful use of EHRs
  • Fundamental principles of usability and human-centered computing
  • Usability Methods
  • Group discussion on how to integrate usability techniques into development lifecycle

T-15: The Informatics of Health Information Exchange

Content Levels: Basic 40%; Intermediate 40%; Advanced 20%
Fee: $95 member/student $150 non-member

Intended Audience: Developers of systems for regional and supra-regional health information exchange; Purchasers of systems for health information exchange; Researchers in informatics techniques applicable to health information exchange; Policy leaders involved in the development of and support for HIE infrastructures; Students interested in health information exchange and the informatics techniques that can be brought to bear on it. You should attend … if you want to understand what “health information exchange” is, what benefits it offers in theory, and why it is so difficult to achieve in practice; as well as a number of specific informatics techniques for addressing some of the most difficult challenges to HIE. CME/CE=3

Walter Sujansky, Sujansky & Associates, LLC

Health information exchange (HIE), the electronic sharing of patient data among disparate health care enterprises, has emerged as a critical component in realizing the full value of EHRs and the “meaningful use” of clinical information systems. Although such sharing has long been envisioned, it has rarely been realized for a host of technical, legal, business, and policy reasons. This tutorial explores the practical challenges of health information exchange and the specific informatics solutions that exist or are under development to address these challenges.

The tutorial provides background on the structure of the U.S. health care system, how this structure impedes the electronic sharing of health information, and what benefits would accrue for patient care, public health, and medical cost containment in overcoming these impediments. The discussion then covers several different technical architectures that have been developed for exchanging health information, including direct peer-to-peer communications, brokered data retrieval across federated information sources, and centrally managed data repositories; it also addresses the different operational models for sharing information, such as sender-initiated (“push”) data transmissions and receiver-initiated (“pull”) data queries. The advantages, limitations, and challenges of these various architectures and models are explored, including the specific technical challenges raised by each.

The tutorial then explores a number of specific informatics techniques for addressing certain of the most important challenges to health information exchange, including the establishment of effective interoperability standards, the assurance of private and secure data transmissions, the reliable matching of patients to their data across enterprises, and the anonymization/pseudonymization of data for research and other secondary uses. The tutorial concludes with a survey of contemporary initiatives at the national and local levels for applying these technique to achieve real-world health information exchange.

By the end of this tutorial, the participant should be able to:

  • Understand what “health information exchange” is, what benefits it offers in theory, and why it is so difficult to achieve in practice
  • Learn about the basic architectures and operational models for health information exchange and the advantages/limitations of each
  • Learn about a number of specific informatics techniques for addressing some of the most difficult challenges to HIE, and the degree to which the state-of-the-art in these techniques does or does not succeed in overcoming these challenges
  • Understand how current initiatives to build HIE infrastructure at the national and state levels are applying the described informatics techniques to address the impediments to HIE

Outline of topics:

  • What is “health information exchange” and why is it important?
  • The challenges of health information exchange
  • Different models for achieving HIE in our health care system
  • Informatics techniques for overcoming certain HIE challenges
  • Case studies of contemporary HIE initiatives and how they apply informatics techniques

WG-06: Clinical Research Informatics Infrastructure: What Is It, How to Get There

Content Level: TBD
Fee: $95 member/student $150 non-member

Intended audience: This pre-symposium is targeted to individuals who are creating strategies for supporting clinical research with informatics tools. This can include Clinical Research Informatics Officers, who have specific responsibilities to acquire the components of the catalog, to informatics professionals who may be using a subset of the tools to support research and need a broader framework for understanding the field, to researchers who want to know what types of informatics support exists to support clinical research. CME/CE=6

Presented by the AMIA Clinical Research Informatics Working Group
John Sharp, Case School of Medicine; Adam Wilcox, New York Presbyterian Hospital; Umberto Tachinardi, University of Wisconsin-Madison

We have created a comprehensive catalog of components that are part of a modern clinical informatics infrastructure. This includes capabilities for data warehousing, trial management, research data management, bioinformatics research, and other activities. Based on our experience from our three different current institutions, and experience with other researchers and systems in clinical research informatics, we identified applications and organized them around the functions they support. In this workshop, we will review our infrastructure component catalog, discuss the functions supported, and review strategies for acquiring components and supporting the functions. Our goal is to help individuals both assess the clinical informatics infrastructure at their own institution, identify capabilities needed to extend research operations, consider and prioritize different options for acquiring needed functionality, and create strategies for maximizing the infrastructure.

We have identified and organized components considered part of a clinical research informatics infrastructure. We have also identified research functions that are supported by this infrastructure and organized the components around these functions:

  • Research data warehousing
  • Trial management
  • Research data management
  • Biobanking
  • Bioinformatics tools
  • Foundational functionality

The pre-symposium will be divided into three parts. First, we will introduce the catalog, how we created it, and how it might be used. The second part, which is the majority of the pre-symposium, involves the different instructors describing the various components of the catalog, how they are relevant to clinical research, and various strategies for acquiring and using them. The last part will be interactive with the participants, where we discuss possible refinements of the catalog, and the strategies for newly-identified components.

At the end of this tutorial, the participants will be able to:

  • Identify various informatics capabilities that support clinical research
  • Identify functions that may be limited without research informatics support
  • Consider possible strategies for acquiring and using informatics capabilities
  • Develop strategies for building a more complete clinical research informatics infrastructure.

Sunday, November 4, 8:30 a.m. – 12:00 p.m.

T-10: CMIO/CNIO continuation from Saturday session

WG-03: Current Issues for Population Health Informatics in Healthcare and Public Health – Continuation from Saturday session

WISH 2012 continuation from Saturday session

T-16: Leveraging Electronic Health Records for Clinical Quality Measurement and Performance Reporting

Content Level: 50% basic, 50% intermediate
Fee: $95 member/student $150 non-member

Intended Audience: Informaticians who would like an overview of the various issues surrounding quality initiatives and how the EHR can be leveraged for this purpose; Healthcare providers who would like to understand the role that health information technology, the EHR plays in quality measurement; Medical directors and quality directors who would like to develop a multi-disciplinary group to steer quality projects based on EHR implementations. You should attend … if you are an informatician or health care provider who would like to better understand the role that health information technology plays in quality measurement, or you are a medical director/quality director who would like to develop a multidisciplinary group to implement an EHR plan. CME/CE=3

Anil Jain, Explorys, Inc.; Stephen Hayden, Cleveland Clinic

Performance measurement and subsequent reporting of outcomes is critical in the current healthcare climate and a central focus of the EHR-incentive programs from CMS as well as payment reform models in the Accountable Care Act.

EHR and EHR-derived data are essential for efficient measurement and reporting of patient-specific process and outcomes measures. Governance issues, workflow consistency and technical challenges remain obstacles for institutions that have implemented an EHR for clinical purposes and that are now challenged with supporting local, regional and national quality initiatives. We illustrate the evolution of clinical quality measurement and reporting at our institution to support performance initiatives.

We will use local, regional and national reporting obligations such as our Aligning Forces for Quality community and the “meaningful use” EHR-incentive program to demonstrate our process. Finally, we will focus on overcoming governance and clinical workflow challenges, extending investments already made in the health IT infrastructure and developing a team to manage the complexity of secondary use of EHR data to measure quality. The tutorial will provide an overview of how institutions can approach the use of EHR data in generating performance measures and clinical outcomes data.

At the end of the tutorial, participants should be able to:

  • Understand the issues in defining and prioritizing EHR-based performance measurement and outcomes projects
  • Demonstrate how electronic health record can be used for performance measurement and quality improvement
  • Review the challenges and limitations of using an EHR derived clinical data
  • Articulate the resources and personnel required to measure performance in an EHR-centric institution

Outline of topics:

  • Clinical Quality Process and Outcome Measures
  • Overview of Health IT, Meaningful Use and the EHR at our institution
  • Group Activity
  • Review of the role of the EHR and registries in measuring performance and outcomes
  • Review the process to standardize and validate clinical data from EHR databases for use in performance measurement and outcomes
  • Introduce concept of multidisciplinary team to manage governance of a quality reporting group
  • Group Activity– Quality and EHR change management

T-17: Practical Modeling Issues: Representing Coded and Structured Patient Data in EHR Systems

Content Level: 50% intermediate, 50% advanced
Fee: $95 member/student $150 non-member

Intended Audience: Anyone interested in the principles and practice of clinical data models and the practical use of standard coded terminologies should attend. This would include physicians, nurses, developers of clinical software, and clinical systems architects and designers. You should attend … if you want to better understand: the importance of adhering to terminology and modeling standards in developing or purchasing interoperable EHR systems; how standard coded terminologies are referenced by detailed clinical models, and the different roles that SNOMED CT and LOINC play in the models; the various alternative logical models for implementing clinical models; ms, measurements and observations; and national and international activities for sharing models that enable interoperability of EHR systems. CME/CE=3

Stanley Huff, Intermountain Healthcare

This tutorial will describe the need for formal data models (detailed clinical models) for the EHR and how standard terminologies are used in the models. Starting with use cases encountered while developing EHR systems at Intermountain Healthcare, the instructor will discuss the basic name-value pair paradigm for flexible representation of patient data; the proper roles for standard terminologies like LOINC, SNOMEDCT, First Data Bank, and RxNORM; approaches to handling pertinent negative findings and negation; support for precoordinated data entry while storing the data in a post coordinated database; and storage of data that belongs to another patient (baby or donor) in the patient record.

By the end of the tutorial, participants will be able to understand:

  • The assumptions and motivation for formal definitions of detailed clinical models
  • How standard coded terminologies are referenced by detailed clinical models, and the different roles that SNOMED CT and LOINC play in the models
  • The various alternative logical models for implementing clinical models related to diagnoses, problems, measurements and observations
  • The importance of adhering to terminology and modeling standards in developing or purchasing interoperable EHR systems
  • National and international activities for sharing models that enable interoperability of EHR systems

Outline of topics:

  • What are detailed clinical models?
  • Why are detailed clinical models important?
  • What are the requirements for defining and using detailed clinical models?
  • Name-value pair (NVP) and entity-attribute-value (EAV) strategies for representing clinical data
  • What are the proper roles for use of LOINC, SNOMED CT, drug codes (First Data Bank, RxNorm) and classifications in the models
  • The necessity of supporting both pre and post coordinated models in a clinical system
  • Approaches to the representation of negation and pertinent negative findings
  • Storing data that belongs to another person (relative, family member, donor) in the patient record
  • Specific alternatives for modeling including observations, diagnoses, and problems
  • Open candid discussion of ideas that the participants have about ways that the modeling issues can be addressed
  • Importance of supporting open consensus standards for EHR systems that are purchased or developed
  • Brief discussion of various national and international activities related to formal clinical data models

T-18: Practical Guide to Clinical Computing Systems: Design, Operations, and Infrastructure CANCELED

Content level: 70% basic, 20% intermediate, 10% advanced
Fee: $95 member/student $150 non-member

Intended Audience: Physicians, nurses, and other healthcare professionals; informatics trainees; anyone who wants to learn more about the practical side of clinical computing. You should attend … if you want to understand the options for supporting clinician users during routine operations and downtimes and learn about the approaches and challenges to interfacing clinical computing systems. CME/CE=3

Thomas Payne, University of Washington; Soumitra Sengupta, Columbia University

This tutorial is intended for those who find themselves adding informatics to their existing responsibilities, those in graduate or fellowship training in informatics who intend to have informatics careers, and anyone who wants to learn more about the practical side of clinical computing. We will cover the architecture of clinical computing systems in medical centers, the realities of building HL7 interfaces, interface engines, maintaining a stable technical infrastructure, medical record requirements, providing ongoing user training and support, and what it takes to keep clinical computing systems continuously available. There are many good articles and books covering implementation of clinical computing systems. However, most of our time and energy will be spent keeping existing systems operating so that EMRs, CPOE systems, decision support systems, and other clinical computing systems can be used efficiently and reliably.

By the end of the tutorial, participants will be able to:

  • Understand architecture of clinical computing systems in a medical center
  • Know approaches and challenges to interfacing clinical computing systems
  • Understand options for supporting clinician users during routine operations and downtimes.
  • Appreciate importance and complexity of supporting hosts, networks, workstations and other infrastructure required for dependable clinical computing system operations
  • Understand how clinical computing systems fit into medical center governance and oversight
  • Feel better prepared to assume membership or leadership of clinical computing operations in your medical center

Outline of topics:

  • Introduction and Overview of Clinical Computing Systems within a Medical Center
  • Architecture of Clinical Computing Systems
  • Creating and Supporting Interfaces (What you don’t learn at HIMSS)
  • Infrastructure and Security
  • Troubleshooting: What Can Go Wrong and How to Fix It
  • Working with the User Community
  • Health Information Management and Legal Aspects of the Electronic Medical Record
  • Working with Organizational Leadership

T-19: Personal Health Records, Portals, and Patient-facing Health Information Technologies

Content level: 50% basic, 30% intermediate, 20% advanced
Fee: $95 member/student $150 non-member

Intended Audience: Clinicians, managers of patient portals, health educators, public health practitioners, engineers and computer scientists who work with distributed information systems, integration of disparate databases or network-level authorization, authentication, or privacy policies. You should attend … if you are a healthcare professional who wants to learn more about the PHRs, PatientPortals and similar technologies and their design and how this technology can help in achieving clinical goals. CME/CE=3

Patricia Flatley Brennan, University of Wisconsin-Madison; Jonathan Wald, RTI International

Consumer information technology solutions are assuming increasing importance in engaging people in self care and disease management. Personal health information tools provide lay people with access to subsets of their clinical records and with the health information management tools needed for self-care and effective health care utilization. Taking on many forms, including PHRs, iPhone apps, patient portals, stand-alone applications, mHealth and Web 2.0 services, these innovative IT tools may also enable better access to the health care systems resources, including health information, appointment scheduling and provider communication, and personal health tracking. Through case studies this tutorial will introduce clinicians, systems administrators, and IT developers to critical issues regarding the design and deployment of PHRs and other personal health information management tools.

The aim of this tutorial is to provide an experienced-based, practical introduction to patient-facing HIT, with particular attention to the clinical consequences of engaging patients through HIT. Drawing from the experiences of Project HealthDesign, an initiative of RWJF involving 14 different teams from around the US, innovations in patient-centered design, clinical care experiences, and patient-gathered and contributed health observations will be explored. Drawing from 10 years of experience directing EHR-connected Patient Portal deployment, we will examine portal functions, clinician response, eHealth strategy, and the opportunities and limitations of patient engagement.

During the tutorial, participants will have an opportunity to examine and critically evaluate existing tools & applications, explore patient portals, and discuss technical, ethical and policy considerations related to the deployment of personal health records tools. An update of the national environment and trends enabling (or interfering with) deploying IT tools for direct-to-consumer will be provided: meaningful use, privacy policies, payment schemes, accountable care organizations and health reform. Participants are encouraged to appraise their institutions' current plans for deploying consumer facing HIT and to come prepared to engage in discussions regarding implementation challenges and anticipated benefits.

By the end of the tutorial, participants will be able to:

  • Determine how consumer-facing HIT, including PHRs and patient portals help achieve clinical goals
  • Pose solutions to the clinical and usability challenges of effective consumer-facing HIT
  • Evaluate the technical requirements, ethical considerations and social value of PHRs, portals, etc.

Outline of topics:

  • PHRs, PatientPortals and consumer facing technologies
  • Design of Patient facing technologies
  • Policy and the View from the National Scene

T-20: Imaging Informatics: Foundations and Clinical Applications

Content Level: 60% basic, 20% intermediate, 20% advanced
Fee: $95 member/student $150 non-member

Intended Audience: This tutorial is directed broadly to those in the informatics community, including scientists; researchers; physicians, nurses, and other healthcare professionals; educators, computer scientists, system developers, leaders in healthcare or other organizations, researchers, policy makers, IT professionals, and programmers who work with or are interested in learning about using medical images in their work. You should attend … for an overview of the foundational methods and emerging clinical applications in imaging informatics, including the key methodologies for acquiring and analyzing images as well as informatics approaches for working with images as a unique type of biomedical data. CME/CE=3

Daniel Rubin, Stanford University

Medical imaging is a vital component of patient information. The rapidly growing image-related data in clinical records and research studies provides enormous opportunities for discovery and personalization of patient care, analogous to similar advances from biomedical informatics. Imaging provides information about patient phenotype, characterizing the anatomic, functional, cellular and molecular features of disease; however, this rich image-based information is only partially utilized, since images are largely viewed and interpreted qualitatively. More recently the paradigm of “quantitative imaging” is emerging, spurring opportunities for imaging informatics to leverage computational approaches to managing and using objective data derived from images.

The role of informatics in imaging is rapidly expanding as the number of images explodes, and as researchers look to relate phenotype information in images to molecular and clinical characterizations of disease. Themes such as semantic annotation of images, integrating imaging with molecular and textual data, image mining, content based image retrieval, and image-based decision support, are arising as crucial themes in informatics to advance medical practice and biomedical discovery. Developing these imaging informatics methods and applications will ultimately improve our ability to diagnose disease, enable tailoring optimum treatment, permit automated tracking disease response, and enable predicting clinical outcomes. Making these advances will require large-scale data-driven analyses of rapidly expanding image databases in hospitals and research institutions. Imaging informatics methods to access and manage the complexity of the information latent in images will also be needed to enable these essential data to be optimally used in clinical care, scientific research, and health policy activities.

This tutorial will provide an overview of the foundational methods and emerging clinical applications in imaging informatics, including the key methodologies for acquiring and analyzing images as well as informatics approaches for working with images as a unique type of biomedical data. We will stress the synergy of imaging informatics methods with those in use in biomedical informatics more broadly, and the implications for data integration, discovery, and clinical decision making. At the conclusion of the tutorial, attendees will have a deeper understanding of the exciting developments driving the imaging informatics field, the use of informatics methods to access and work with image contents, new imaging algorithms/techniques, and the forthcoming image-related applications that will enable discovery in research and improvement in healthcare quality.

By the end of the tutorial, participants will be able to:

  • Have an overview of the key methodologies and overview of some key applications of biomedical imaging informatics
  • Recognize the generalizability of imaging informatics methods to other imaging domains such as pathology as well as to the biomedical informatics field in general
  • Have a deeper understanding of the exciting developments driving the imaging informatics field
  • Understand the use of informatics methods to images, the new algorithms/techniques, and the forthcoming applications that will enable discovery in research and improvement in healthcare quality

Outline of topics:

  • Data explosion, Variation in practice, quality issues;
  • Computing with images (quantitative and semantic features, imaging knowledge representation, “imaging phenotype”)
  • PACS 1.0 vs. 2.0
  • Overview of imaging modalities: biological and medical imaging modalities and research/clinical applications
  • The Radiology Workflow Order Protocol Procedure Steps Display QC Image interpretation
  • Reporting (text reporting, structured reporting)
  • Imaging information systems and Major imaging-related standards (DICOM, HL7 messaging, CDA, IHE)
  • Image interpretation (embedded reference materials, StatDx, CAD)
  • “Structuring” images and text

T-21: An Introduction to Clinical Natural Language Processing

Content Level: 70% basic, 30% intermediate
Fee: $95 member/student $150 non-member

Intended Audience: Any clinician or medical informatician with an interest in learning more about clinical NLP. You should attend … if you want to learn more about Clinical Natural Language Processing and different approaches to clinical NLP. CME/CE=3

Leonard D’Avolio, Veterans Administration Healthcare System; Wendy Chapman, University of California, San Diego; Dina Demner-Fushman; National Library of Medicine

Natural language processing is the umbrella term used to describe the automated structuring and extraction of information formatted as free text. The demand for natural language processing technologies in medicine will grow significantly in the coming years. This growth will be fueled by the continuing adoption of the electronic medical record, increasing emphasis on quality measurement and improvement initiatives, and the growing need for evidence to be used as part of evidence-based medicine. This half-day tutorial is designed to introduced clinicians and informaticians to the practice, tools, techniques, and science of clinical natural language processing.

Instruction will be hands on, inter-active, and case driven. The tutorial’s primary focus will be on clinical NLP, although related uses and methods such as literature-based NLP and text mining will be discussed to lend context. Topics covered include: an overview of clinical NLP and its uses in medicine; a brief history of clinical NLP and the evolution of NLP methods; the challenges to NLP; the number of approaches used to process natural language and the strengths and weaknesses of each; implementation considerations, creating annotated corpora as training / test sets, evaluation of NLP, and a review of open source tools for natural language processing. Demonstrations and in-class exercises will be used to help tie the theory of NLP to everyday research problems addressed by these technologies. The tutorial will be taught by three instructors experienced as researchers, developers, and users of a variety of tools and approaches to clinical NLP. Users will also be exposed to several open source technologies for clinical NLP including the Unstructured Information Management Architecture (UIMA) and Knowtator for manual annotation, and the Automated Retrieval Console (ARC).

By the end of this tutorial, attendees should be capable of:

  • Describing the current uses of clinical NLP
  • Describe the relationship between clinical NLP and related techniques such as text and data mining
  • Understand the challenges to clinical NLP
  • Describe the various approaches to clinical NLP and their strengths and weaknesses
  • Understand the process of clinical NLP and its various components
  • Find available open source clinical NLP components, frameworks, and packages
  • Identifying potential implementation concerns and challenges
  • Understand the process of creating and using annotated corpora
  • Interpret the performance of published clinical NLP research

Outline of topics:

  • Overview: What is NLP and how is it being used in medicine?
  • What makes clinical NLP so difficult?
  • Different approaches to clinical NLP
  • The clinical NLP process
  • Available open source tools and components
  • Implementation considerations
  • Evaluating clinical NLP (in greater detail)

T-22: An Introduction to the Theory and Practice of Clinical Data Mining

Content levels: 50% basic, 50% intermediate
Fee: $95 member/student $150 non-member

Intended Audience: Clinicians, researchers, programmers, informatics professionals, and policy makers You should attend…if you are an informatics professional interested in learning about the principles of data mining and how to use Weka as a tool for more effective data mining. CME/CE=3

John Holmes, University of Pennsylvania

This tutorial will illustrate, via demonstration and hands-on experience, the application of data mining methodologies to clinical databases. A knowledge discovery life cycle model will be employed as the conceptual framework for the tutorial. Attendees will obtain practical experience in mining a database for use in clinical research, and ultimately for assisting with statistical analysis. We will focus on a well-known, public domain dataset (Pima Indians Diabetes) for exploration in the tutorial, and we will learn and use the Weka data mining suite. Weka is freely available in the public domain, and runs on even modestly equipped computers within a Java runtime environment (JRE). Weka and the dataset will be distributed to attendees prior to the tutorial session via the Web or at the meeting on USB drives free of charge.

By the end of this tutorial, participants will be able to:

  • Describe the Knowledge Discovery Life Cycle and identify the tasks associated with each phase of the life cycle model
  • Use a well-known data mining software platform (Weka) to perform basic data mining tasks, such as data preparation, feature selection, rule discovery, and decision tree induction
  • Evaluate the results of applying a data mining algorithm to a clinical database

Outline of Topics:

  • General characteristics of biomedical data
  • Principles of data mining
  • Introduction to Weka and the dataset
  • The Knowledge Discovery Life Cycle
  • Data visualization
  • Methods for preparing biomedical data for mining
  • Methods for data reduction
  • Data mining tools for classification and prediction
  • Machine learning approaches to knowledge discovery
  • Evaluation metrics for knowledge discover
  • The Weka Knowledge Flow tool: A graphical approach to data mining

T-23: Clinical Decision Support: A Practical Guide to Developing Your Program to Improve Outcomes

Content level: 60% basic; 40% intermediate
Fee: $95 member/student $150 non-member

Intended Audience: Clinicians and administrators interested in quality improvement and patient safety; physicians, nurses and other health care professionals; and computer scientists, system developers and programmers interested in understanding applications of health information technology to clinical decision support. You should attend … if you want to learn what factors drive CDS initiatives and understand how to maintain CDS interventions. CME/CE=3

Robert Jenders, National Institutes of Health; Jerome Osheroff, TMIT Consulting LLC; Jonathan Teich, Elsevier; Dean Sittig, University of Texas Health Sciences Center; Robert Murphy, Memorial Hermann Healthcare System

This tutorial will provide attendees with a practical approach to developing and deploying clinical decision support (CDS) interventions that measurably improve outcomes of interest to a health care delivery organization. The instructors initially will examine in detail the key building blocks of a CDS program, including creating and enhancing organizational structure for CDS success; identifying information systems for providing the data that drive CDS interventions; leveraging clinical workflow to optimize CDS interventions; processes and systems for measuring the outcomes of these interventions; and knowledge management to acquire and maintain the expert clinical and scientific knowledge that informs these interventions. The instructors then will show how to leverage these building blocks to address key steps in developing, implementing,anaging and evaluating CDS interventions, including how to select interventions to deliver targeted improvements in health care; configuring those interventions in specific environments; putting the interventions into action; measuring the results of the CDS interventions and in turn refining the program based on the results.

Additional discussion will touch on the role of national programs relevant to CDS, including knowledge sharing; structured guidelines; meaningful use; special considerations for CDS for small clinical practices, for hospitals and health systems and for vendors; and medico-legal considerations pertinent to CDS. Further, following interactive presentations by the instructors, attendees will divide into small groups and participate in a highly interactive exercise in planning and designing a CDS project to address a specific clinical target, facilitated by the instructors.

Overall, this systematic approach to CDS implementation will be presented in an interactive, case-oriented fashion, incorporating examples provided by tutorial leaders and participants’ experiences. The course content is drawn from the tutorial leaders' popular and award-winning guidebook series on improving outcomes with clinical decision support, the last two volumes of which (in 2009 and 2012) were co-published by AMIA.

By the end of the tutorial, participants will be able to:

  • Understand the critical people, process and technology building blocks needed to implement a successful CDS program
  • Follow a systematic process for developing, implementing and evaluating clinical decision support interventions that measurably improve key health care outcomes.
  • Detail factors both external and internal to a health care organization that drive CDS initiatives, including medico-legal considerations
  • Understand the importance and details of knowledge management for maintaining CDS interventions

Outline of the topics:

  • Developing effective governance structures, stakeholder engagement and other key requirements for implementing a CDS program
  • Selecting CDS goals
  • Implementing goal-directed CDS interventions that improve outcomes, including the “CDS Five Rights”
  • Monitoring and measuring CDS interventions
  • Knowledge management and the refinement of CDS interventions based on results
  • National programs relevant to CDS, including knowledge sharing, clinical guidelines and meaningful use
  • Medico-legal considerations in the use of CDS

T-24: The EHR Usability Symposium 2012, "Usability and Meaningful Use"

Content level: TBD
Fee: $95 member/student $150 non-member

Strategic Health IT Advanced Research Projects – Cognitive (SHARPC)

EHR usability is a major barrier to the adoption and meaningful use of EHR. In the Proposed Rules for Meaningful Use Stage 2, usability certification will be included as one of the requirements for vendors to get their EHRs certified. After the successful Symposium on EHR Usability at AMIA 2011 with 150 attendees, SHARPC is organizing another symposium at AMIA 2012. AMIA members are invited to attend a collaborative discussion to learn about how EHR usability can be evaluated, measured, and improved to achieve meaningful use. Advanced software tools and comprehensive methods will be presented and discussed. Invited representatives from federal agencies, vendors, research institutions, and providers will provide their perspectives at this symposium.

By the end of the symposium, participants will be able to:

  • Understand usability as a science and a practice
  • Learn about the implications of EHR usability for the adoption and meaningful use of EHR
  • Learn about the tools and methods to evaluate, measure, and improve EHR usability to achieve meaningful use
  • Learn about the perspectives of federal agencies, EHR vendors, and providers

WG-07: Enhancing Participant Recruitment to Clinical Trials: Informatics Strategies and Future Directions CANCELED

Content Level: TBD
Fee: $95 member/student $150 non-member

Intended Audience: Clinicians, informaticians, and engineers involved in research informatics, research infrastructure development and those with clinical and translational scientific awards. CME/CE=3

Presented by the AMIA Primary Care Informatics Working Group
Ashish Atreja, Cleveland Clinic; Peter Embi, The Ohio State University; Paul Harris, Vanderbilt University; Michael Kahn, University of Colorado; Chunhua Weng, Columbia University

Clinical trials are critical to the advancement of medicine and form a critical link in the translation of basic biological research into routine clinical practice. Finding eligible participants for trials is one of the critical hurdles and major bottlenecks in the conduct of clinical research. Despite the great promise of existing health information systems, recruitment rates remain low and are frequently the cause for delays in the completion of trials and even trial failure. The need is great for fundamental, accessible, navigable, and comprehensible solutions to the challenge of participant recruitment. Overcoming these challenges is a fundamentally information-intensive endeavor, and informatics solutions to the problem of inadequate recruitment are beginning to take hold.

Through a series of speaker presentations, panel discussion, and breakout sessions, this pre-symposium will bring together thought leaders to address the challenge of clinical trial participant recruitment through various informatics strategies: (1) Registries, (2) Electronic Health Records, (3) Patient-centric platforms and (4) Social-media based solutions. The panel will discuss the evidence for current strategies and lay out a framework for the future through discussion and break-out groups.

Participants will learn various provider-centric and patient-centric approaches to enhance clinical trial recruitment within their research information ecosystems and how to objectively evaluate the effectiveness of these approaches. Through hands-on exercises and use-case scenarios, participants will understand how to combine different strategies to formalize a solution that bests fit with their institutional needs and environment.

By the end of this tutorial, the participants will be able to:

  • Understand various patient and provider centric recruitment strategies and informatics solutions to recruitment
  • Demonstrate the evidence for and use of novel recruitment solutions being used across various Institutions
  • Discuss the challenges in implementing informatics solutions and steps to overcome them
  • Review methods for rigorously evaluating the solutions and lay out a framework for integrating the solutions into healthcare settings

WG-08: Intensive Care Informatics: challenges, opportunities and road ahead

Content Level: basic 50%, intermediate 50%
Fee: $95 member/student $150 non-member

Intended Audience: physician and non-physicians interested in the topic of critical care informatics. CME/CE=3

Presented by the AMIA Intensive Care Informatics Working Group
Peter Haug, University of Utah and Intermountain Healthcare; Vitaly Herasevich, Mayo Clinic; Jim Fackler, Johns Hopkins University School of Medicine; Willa Drummond, University of Florida College of Medicine; John Zaleski, Nuvon, Inc; Brian Pickering, Mayo Clinic; Kathryn Kuttler, Intermountain Medical Center; Saif Khairat, University of Minnesota; Jeremy Pamplin, Brooke Army Medical Center

The focus of this tutorial is the research and development of technology which facilitates safe and effective patient care in the Emergency Department (ED), Intensive Care Unit (ICU) and the operating room. The acute care environment presents several unique medical informatics research challenges and opportunities including:

  • Rapid cycle of disease - there is a very short time between the development of acute conditions and outcomes. The typically cycle is less than 30 days. This is in contrast to chronic disease where the time to outcome can be measured in years. This makes the acute setting an ideal one in which to test the impact of health information technology based interventions on meaningful outcomes.
  • The care of patients in this environment typically generates large quantities of digital data with a resolution that varies from seconds (monitor data) to hours (laboratory data).
  • Human factors and systems based research opportunities- Complex patients present with a broad spectrum of diseases, are cared for by multidisciplinary teams of providers working in stressful conditions with frequent interruptions and patient care transitions. The environment is rich with opportunities to optimize the interactions and function of all of these moving parts.

By the end of this tutorial, the participants will have an overview of the main concepts and research topics in intensive care informatics.

Outline of topics:

  • Making technology work in ICU
  • Tools and methods for patients’ data acquisition
  • Information needs, use and misuse in the ICU
  • Real-Time Decision Support in Intensive Care
  • Human-Computer Interaction and Clinical Communication in ICU
  • Distributive Cognition in our Critical Care Battlefields: Getting it right

WG-09: Key Challenges in Consumer Health Informatics and mHealth CANCELED

Content Level: 30% basic, 50% intermediate, 20% advanced
Fee: $95 member/student $150 non-member

Intended Audience: Members and prospective members of the working groups who are interested in either an overview of consumer health informatics or are interested in an interactive working session designed to generate position papers and whitepapers on topics related to the foci of the working groups.

Presented by the AMIA Consumer Health Informatics and Knowledge In Motion Working Groups
Albert Lai, The Ohio State University; Lindsey Hoggle, Health Project Partners, LLC; Marion Ball, IBM Research; Kevin Clauson, Nova Southeastern University; Cynthia LeRouge, Saint Louis University

This tutorial is designed to both introduce attendees to the topic areas covered by the combined working groups as well as to provide a platform for discussion of identifying the challenges in the field of consumer health informatics. The tutorial will take the format of both a panel and a working session. The panel will provide an introduction to consumer health informatics and showcase some of the research activities working group members are undertaking that span both working groups. These topics will be used to form the basis of an interactive discussion and working session focused on identifying the most important research challenges for researchers in the field and the biggest challenges these researchers face. These discussions will be leveraged to further the working groups’ goals of generating position papers and white papers related to the foci of the Consumer Health Informatics and Knowledge In Motion working groups.

Topics to be Covered:

  • There has been a shift in the practice of health care, moving towards a patient centric care model. Dr. Ball will address the move to patient centric care and the consumer’s role in the new DESIRED Healthcare delivery system. In particular, she will focus on tools becoming available to self empower the consumer/patient to support a better understanding of their own healthcare and to support adherence
  • Assuring the quality of online health information is an ongoing challenge in the US and internationally. In order to characterize the approaches used, the World Health Organization (WHO) Global Observatory for eHealth administered a survey to national consensus panels of expert informants from Member States. One hundred and fourteen countries (i.e., WHO Member States) completed the Internet safety and security section of the survey. Mechanisms used by countries to address online health quality, government sponsored efforts in support of Internet literacy and safety, and recommendations will be discussed on the panel by the report’s lead author
  • “Baby boomers” (55-70 year olds) make up the largest cohort of the population in many countries (including the United States and Canada). Their sheer numbers will have a huge impact on the development of health programs and services. Likewise, the current elderly account for a large share of health care costs. mHealth is viewed as a way to improve health and well-being while reducing costs of care and fostering independent living. If we are to achieve maximum impact for mHealth as a vehicle for consumer health informatics, we need a better understanding of the baby boomer and elderly population needs, capabilities, preferences, and expectations of mHealth tools. Mobile phone handsets are the most popular mobile device in use (close to 90% of the U.S. population and mention China) and provide the most accessible mHealth platform for the baby boomer and consumer health market. This presenter will provide insights on phone use to support mHealth for these targeted populations based on both user-centered design projects in China as well as U.S. based survey data and challenge the audience to explore ways of meeting those challenges.