• Nov 4 - 8, Washington, D.C.

    AMIA 2017 Annual Symposium

    Precision Informatics for Health: The Right Informatics
    for the Right Person at the Right Time

AMIA 2017 Pre-symposium Workshops

Individual registration is required for each workshop you wish to attend. Please select only one workshop per time slot. Seats are limited.

Collaborative Workshops are intended to encourage participation and collaboration using mechanisms such as discussion forums (e.g., shorter didactic presentations or panels followed by group discussions), research forums (e.g., presentations and discussions related to scientific advancements in a targeted areas of informatics innovation and practice), or a challenge/competition (e.g., individual or group submissions addressing a specific topic or scientific/technical challenge).

Instructional Workshops include a combination of didactic and interactive content delivery, as well as participant interaction. They are designed to address the needs and interests of individuals at all levels of experience relative to the selected topic area(s), and are led by individuals with appropriate subject matter expertise.

CME/CE/MOC eligibility:

  • Half-day workshops = 3 CME/CE credits
  • Full-day workshops = 6 CME/CE credits

For sessions offering MOC-II credit, check the Self-assessment Booklet of Multiple Choice Questions.

Saturday, Nov. 4, 8:30 a.m. – 12:00 p.m.

Collaborative Workshop

W01: Current and Emerging Issues for Public and Population Health Informatics (sponsored by the Public Health Informatics Working Group)

H. Kharrazi, Johns Hopkins University; C. Stephan, University of Missouri-Columbia; J. Loonsk, CGI Federal, Johns Hopkins University

Advancing population health outcomes is of prime interest to many informaticians both in healthcare and public health. This strong interest was demonstrated by the great success of AMIA’s Population Health Informatics (PHI) pre-symposium workshop in, making it the second most attended workshop in recent years. This year, multiple healthcare and public health factors are driving the PHI workshop to the next level including: post-Meaningful Use 2 (MU2) activities; evolving population-health focused MU3 objectives; and enactment/enforcement of new CMS population policies (e.g., MACRA).

In this workshop, healthcare and public health informatics participants will discuss, assimilate, and advance current and emerging population health informatics issues. Faculty and presenters will frame different sides of each issue to demonstrate various developments and promote understanding of a common vocabulary. Participants will then discuss each issue to further advance a shared understanding. Consensus statements designed to move the management of each issue forward will be developed and communicated broadly.

Timely issues to be included in the session topics that are associated with advancing population health outcomes inside of clinical care and public health such as: the role of -based tools such as population health management dashboards in supporting surveillance needs; connecting registries in clinical care, in Public Health Agencies and in Health Information Exchanges, as well as other organizations; using population data for the public good; public health challenges with MU; decision support for reporting and population health workers; implementing two way “reporting” between public health and healthcare; population health informatics needs for chronic disease management and prevention; community health interventions, and other emerging topics.

Instructional Workshops

W02: Designing Gamified Applications for Empowering Patients

G. Giunti, Salumedia Tecnologias, University of Oulu; E. Gabarron, Norwegian Centre for e-Health Research; Y. Solad, Yale New Haven Hospital System; S. Jessen, Oslo University Hospital, University of Oslo

Patient empowerment provides patients with an ability to actively influence their health. Increased adoption of wearable technologies and “smart” devices can simplify the collection of patient generated data and provide the means for educating patients; however, information alone does not always suffice. In order to be effective, interventions have to be delivered at the appropriate time and be both meaningful and actionable for patients. Targeted actions that inspire and motivate have higher chances modify behaviors in a positive way. Gamification uses game elements in non-game contexts. The use of gamification in health apps has gained traction and is now a popular strategy in both commercial and academic fields to drive user behavior. Can these gamification strategies simplify the development of engaging and impactful health applications? How can effective gamified interventions be designed? This workshop offers participants the chance to learn the basics of gamification and engagement strategies, and to explore new design trends and approaches for building health applications that motivate patients.


W03: Qualitative Approaches to Design Thinking for Informatics (sponsored by the Consumer and Pervasive Health Informatics, People and Organizational Issues, and Public Health Informatics Working Groups)

B. Massoudi, RTI International; R. Valdez, University of Virginia

The aim of this instructional workshop is to introduce informaticians to qualitative approaches that can be used within a design thinking process, putting the user, rather than the technologist, at the center of the design effort. Design thinking is a newer iteration of a holistic engineering design process. 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 the resulting systems is often challenging, and redesign and development efforts can be prohibitively costly and time consuming. This workshop provides a hands-on orientation to qualitative approaches in the design thinking process, which are essential to informatics development, but not commonly taught in informatics curricula.

Using both didactic and participatory techniques, we will introduce the design thinking process; present the benefits and implications of qualitative approaches as part of the design thinking process as it relates to public health and consumer health information systems development efforts; and, introduce specific qualitative methods and techniques. This tutorial will include mock data collection activities that illustrate how these tools are integrated and used in practice. Participants will be engaged in developing and presenting a design thinking approach to a system development effort they are currently working on, and will receive feedback on their approach from the instructors and their peers. Based on previous tutorials we have presented and conversations at AMIA, we have learned from our colleagues about the need for training that focuses on qualitative methods within the design process.

Saturday, Nov. 4, 8:30 a.m. – 4:30 p.m.

Collaborative Workshops

W04: CMIO Workshop

P. Fu, Harbor-UCLA Medical Center/Los Angeles County Department of Health Services; J. Hollberg, Emory Healthcare; J. Kannry, Mount Sinai Medical Center; R. Schreiber, Geisinger Holy Spirit Hospital

More than 1,400 physicians were board certified in clinical informatics by the American Board of Preventive Medicine during the first 4 years of subspecialty certification and are now required to participate in the ABPM Clinical Informatics Maintenance of Certification program.[i] There are 24 Clinical Informatics Fellowship Programs accredited by the Accreditation Council for Graduate Medical Education.[ii] There are more non-board certified/eligible practitioners who need training in state-of-the-art applied clinical informatics. AMIA is uniquely suited to be the academic home for this community, because it provides a combination of personal experience and anecdote with firm grounding in evidence-based biomedical informatics literature, informatics theory, foundational knowledge, and proven best practices. A major part of that support is outreach to Chief Medical Information Officers (CMIOs) and those in similar roles (such as Medical Directors for Information Systems) who are charged with leading informatics change within their organizations, both large and small. More than 210 individuals have attended since 2011, some attending more than once, ranging from seasoned CMIOs of large systems to those who are just beginning their applied clinical informatics careers. The 2017 CMIO Workshop will focus on leadership development, implementation of population health initiatives, effective clinical decision support, interoperability, the challenges of EHR migration, and preparing for the board exam and available MOC resources. Didactic presentations will be integrated with structured group discussions. The CMIO workshop is a bridge between the more applied iHealth conference and the breadth of annual symposium offerings, with practical offerings that participants can integrate into their daily workflow and help their organizations realize the potential benefits of health IT.

[i] ABPM Subspecialty Pass Rates [Internet]. Chicago: American Board of Preventive Medicine; c2017 [cited 2017 Feb 28]

[ii] Clinical Informatics Fellowship Programs [Internet]. Bethesda: American Medical Informatics Association; c2017 [cited 2017 Feb 28]


W05: Hopes and Challenges for Primary Care Informatics in the New Administration (sponsored by the Clinical Information Systems and Primary Care Informatics Working Groups)

S. Morgan, Partners Healthcare Inc.; M. Parkulo, Mayo Clinic; D. Pandita, Park Nicollet Health System; D. Dorr, OHSU; A. Zuckerman, Georgetown University; J. Weinfeld, Georgetown University; R. Hausam, Hausam Consulting, LLC; M. Jenkins, Rutgers University

The new administration has promised new approaches to regulation, reimbursement, and improving value in healthcare. This workshop will explore hopes and challenges building on last year’s pre-symposium workshop: Primary Care Informatics in the Second Decade of Health Information Technology; Challenges, Lessons Learned and Work Remaining to be Done regarding the failure to achieve EHR certification and meaningful use goals. This year, each presentation will be followed by audience discussion to document what is working, what is sub-optimal, and to set priorities and new strategies for meeting primary care practice needs. The structure of this session will be divided into four sections of ninety minutes in length. Each subsection will consist of brief presentations of the topic followed by collaborative sessions to discuss and strategize on solutions to the problems presented.

Beginning with an overview of the challenges and constraints on primary care informatics in a changing world of reimbursement and regulation, we will explore MACRA, the Trump Administration and Primary Care Informatics, highlighting the new reporting requirements. Continuing our previous exploration of new primary care models, we will examine SmartCare: An Innovative Health Care Delivery option for Primary Care, an example of informatics facilitating practice change.

Last year, a limited set of essential priorities and requirements emerged to meet core goals. Topics selected in advance by the PCIWG through webinars and surveys are expected to include: efficient documentation, integrating data from communications into EHR, transfer of complete patient records to other systems, portable and sharable tools for quality assessment and clinical decision support, export of data to clinical data repositories, and data visualization tools. Implementing these priorities will employ two strategies identified last year: Fast Health Interoperability Resources (FHIR) to facilitate extending vendor provided EHR, and education to improve the understanding of providers, vendors, and patients.

Concluding with a strategy for dissemination of priorities, we plan to generate a policy paper summarizing findings of the workshop, and initiate collaborations with other groups such as the new AMIA Interoperability and Health Information Exchange working group and various primary care professional societies.


W06: 2nd Social Media Mining for Health Applications Workshop & Shared Task (sponsored by Clinical Research Informatics, Consumer and Pervasive Health Informatics, Natural Language Processing, and Pharmacoinformatics Working Groups)

G. Gonzalez Hernandez, A. Sarker, University of Pennsylvania; A. Nikfarjam, Stanford University; M. Paul, University of Colorado Boulder; P. Zweigenbaum, French National Center for Scientific Research; C. Paris, CSIRO Australia; N. Collier, University of Cambridge

Leadership and management of change is one of the four core content areas of the clinical informatics subspecialty and is frequently referenced as a key determinant of success in transformational efforts.

Social networks have seen an unprecedented growth in terms of users worldwide. According to the Pew Research Report, 1 nearly half of adults worldwide and two-thirds of all American adults (65%) use social media, including 35% of those 65 and older and over 90% of 18-29 year olds. This workshop aims to provide a forum for AMIA community members to present and discuss advances in social media mining for health applications, following on the success of a Session and accompanying Workshop on the topic that was hosted at the Pacific Symposium in Biocomputing (PSB) in 2016. The workshop seeks to attract researchers interested in automatic methods for the collection, extraction, representation, analysis, and validation of social media data for health informatics, including epidemiological and behavioral studies. It serves as a unique forum to discuss novel approaches to text and data mining methods that are applicable to social media data and may prove invaluable for health monitoring and surveillance. The workshop will include peer-reviewed paper presentations in the research forum (3 hours) and shared task participant presentations and discussions (3 hours). The shared task will involve three subtasks relevant to medication-related postings in social media: (i) automatic classification of adverse drug reaction (ADR) posts, (ii) automatic classification of posts indicating personal intake of medications versus other medication mentions, and (iii) normalization of ADR mention extracts into UMLS CUIs (Unified Medical Language System Concept IDs).


W07: Data Mining for Medical Informatics (DMMI) – Causal Inference for Health Data Analytics (sponsored by the Knowledge Discovery and Datamining Working Group)

K. Ng, IBM Research; B. Ray, S. Ma, NYU; K. Zhang, CMU; F. Wang, Weill Cornell

The biomedical sciences and healthcare are contributing significantly to the big data revolution through advances in genomic sequencing technology and imaging, clinical and personally-generated data. Data mining and machine learning techniques have played an increasingly important role in medical informatics with the goal of discovering knowledge and insights from various data sources. Causal inference is an important methodological pool from which one can draw powerful techniques for knowledge discovery and data-driven insights. Causal discovery methods were developed to address the financial and ethical concerns associated with randomized controlled trials. An attestation to their significance is that they have been recognized with both the Turing Award (to Judea Pearl) and the Nobel Prize (to Clive Granger). Discovery of causality is a major goal in basic, translational and clinical science. In computational biology, neuroscience, epidemiology and biomedicine one often faces the daunting task of finding causal relationships in very large-dimensional data. This highlights the necessity to develop and evaluate algorithms and tools to improve the current state of the art in causal discovery from experimental, quasi-experimental and non-experimental (i.e., observational) data. The main theme of the workshop this year is causal inference for health data analytics, which aims to address both the theoretical and experimental underpinnings of these methods. This includes development and applications of the methods and discussions on how to make them practically useful to clinicians, patients and other healthcare stakeholders. This topic is timely and has received a lot of interest recently. We would like to invite researchers from both academia and industry who are interested in this topic to participate in this workshop, share their opinions and experience, as well as discuss future directions.


W08: Natural Language Processing Graduate Student Consortium, Highlight, and Codeathon (sponsored by the Natural Language Processing Working Group)

H. Liu, Mayo Clinic; R. Xu, Case Western Reserve University; S. Meystre, Medical University of South Carolina; S. Arabandi, Ontopro; K. Wagholikar, Massachusetts General Hospital; D. Demner-Fushman, National Library of Medicine; J. Patrick, Health Language Analytics; G. Savova, Boston Children's Hospital; O. Uzuner, SUNY; C. Weng, Columbia University; H. Xu, UTHealth; P. Zweigenbaum, LIMSI

The application of Natural Language Processing (NLP) methods and resources to clinical and biomedical text has received growing attention over the past years, but progress has been limited by difficulties to access shared tools and resources, partially caused by patient privacy and data confidentiality constraints. Efforts to increase sharing and interoperability of the few existing resources are needed to facilitate the progress observed in the general NLP domain. To answer this need, the AMIA NLP working group pre-symposium continues the tradition since its inception in 2012 to provide a unique platform for close interactions among students, scholars, and industry professionals who are interested in clinical NLP. The event will consist of three sections: 1) a graduate student consortium, where students can present their work and get feedback from experienced researchers in the field; 2) a highlight session, where significant NLP articles in clinical and biomedical domains will be presented followed by a panel discussion; and 3) a ‘codeathon’ of NLP tools, where user developers of NLP tools will interact with tool developers to implement tools on practical NLP tasks in groups.


W09: Clinicians on FHIR: What Nurses Need Know (sponsored by the Nursing Informatics Working Group)

L. Heermann Langford, Intermountain Healthcare/Healthcare Services Platform Consortium; R. Leftwich, Intersystems; V. Nguyen, Leidos; D. Ariosto, Vanderbilt University; E. Harper, University of Minnesota; E. Jones, Allscripts; R. Hausam, Hausam Consulting, LLS; S. Matney, Intermountain Healthcare/Healthcare Services Platform Consortium; J. McClay, UNMC

Beginning in 2010 HL7 created Fast Healthcare Interoperability Resources (FHIR) as a next generation standard to address clinical data interoperability. Clinicians on FHIR evolved in 2014 as an event held at each HL7 Working Group Meeting (3 times yearly) to educate clinicians about HL7 FHIR and provide feedback to the HL7 FHIR team regarding the clinical viability and usability of the FHIR standard. This AMIA pre-symposium will bring the Clinicians on FHIR activity to a broader clinical audience, specifically the nursing audience, attending the AMIA Fall Symposium. The workshop is designed to educate attendees about HL7 FHIR and tools available to access, review, and provide feedback to the HL7 FHIR team regarding the evolving HL7 FHIR standard. It is also intended to make the audience aware of the potential of FHIR for innovation in their organizations. The faculty will provide lectures describing HL7 FHIR history, background, and fundamental principles. Examples of applications using the SMART on FHIR platform will also be discussed. After this initial overview of FHIR, the attendees will break into small groups of 6-10 where they will be guided through using online tools to examine HL7 FHIR Resources (the basic building blocks of FHIR) and build FHIR Profiles (implementation guides for specific use cases) for care plan and care coordination use cases.

Saturday, Nov. 4, 1:00 p.m. – 4:30 p.m.

Instructional Workshops

W10: Analysis of Human Interactive Behavior for Improving Health IT Usability and Minimizing Patient Safety Risks

T. Kannampallil, University of Illinois; K. Zheng, University of California at Irvine; V. Patel, 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 IT, can cause considerable cascading effects in the clinical processes, workflow, and consequently, on throughput and efficiency. A 2011 IOM report [1] called for a socio-technical approach for designing and incorporating health IT in clinical settings. 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.

In this workshop we will discuss a set of convergent methodologies for analyzing human interactive behavior both with technology and with other humans or artifacts. These methodologies can help in capturing underlying patterns of human interactive 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). Such analysis of interactive behavior can also provide significant input to patient safety outcomes through the design of safe and efficient health IT.

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; (d) provide participants hands-on experience in using data collection and data analysis tools; and (e) discuss the implications of these techniques for the design of health IT and patient safety initiatives.


W11: Patient and Consumer Engagement in Health Information Technologies

J. Wald, RTI, Society for Participatory Medicine; D. Sands, Beth Israel Deaconess Medical Center, Harvard Medical School, Society for Participatory Medicine

Patient engagement has been called the “blockbuster drug of the century.” While patient and consumer engagement concepts vary among different stakeholders, health care professionals and patients intrinsically understand its power. Over the last decade, patients and caregivers, along with their clinicians have employed connected technologies to enhance self-care and manage their conditions to better engage in their health and health care. Innovative use of technologies such as patient portals, mobile applications, and mHealth services are enhancing communication, access to clinical records, use of medical reference information, participation in online communities, self-diagnosis, self-management, and tracking/sharing of biometric and other health information. However, the impact and adoption of these technologies for patient engagement have been limited by challenges including weak or conflicting drivers, technology silos, device and data incompatibility, information gaps, workflow obstacles, and policy or cultural conflicts.

This workshop will offer clinicians, system administrators, IT developers, policymakers, and patients (we are all patients, eventually!) examples of how these tools are used successfully to enhance patient engagement. Instructors will present material from research and practical perspectives, with a particular focus on identifying and addressing the challenges of patient engagement and the use of patient portals, patient-generated health data, and other technologies to promote patient-provider partnerships.

Drawing from decades of experience in the patient engagement space, Dr. Wald with RTI and formerly with Partners HealthCare and Cerner Corporation, and Dr. Sands with Beth Israel Deaconess Medical Center, Onduo, and the Society for Participatory Medicine, will provide an experience-based, practical introduction to consumer-facing health technologies and patient engagement, with particular attention to the clinical challenges of engaging patients through health IT and what the published literature has shown to be important.


W12: A Systematic Method for Identifying Data Attributes in Preparation for Information Visualization

A. Arcia, Columbia University; S. Stonbraker, Columbia University/Clínica de Familia

The purpose of the method presented in this interactive instructional workshop is to facilitate the early design stages of information visualizations by gaining a thorough understanding of the variables and data to be visualized. Data attributes can limit the types of graphical formats appropriate for visualization but can also suggest exciting design opportunities. Optimal visualization design may also be influenced by practical considerations related to visualization automation and deployment. Therefore, it is worthwhile to invest in a thorough exploration of data attributes in order to streamline the design process. In this workshop, we will present a simple, systematic method for discovering the data attributes that influence visualization design. Through a series of interactive exercises, participants will work through the method from start to finish, culminating in preliminary design sketches.

The method for identifying data attributes consists of answering a series of questions related to the precise meaning of a variable, the values that are possible and likely for the variable, and the interpretation of those values. Special attention is given to the theoretical underpinnings of latent variables, possible/desirable data transformations, treatment of extreme and non-missing zero values, and the value judgments, cutpoints, and normed scores that are associated with some variables. The presentation is illustrated throughout with case studies drawn from our visualization work, and informed by key lessons learned. Participants will get hands-on, small group practice for each step of the method and will then have the opportunity to share their findings with the full group. Participants also will be provided with a list of practical information visualization resources.


W13: Effective Change Management Techniques for Health IT Implementation and Optimization (sponsored by the People and Organizational Issues Working Group)

R. Murphy, University of Texas; C. Shea, R. Kitzmiller, University of North Carolina-Chapel Hill

Leadership and management of change is one of the four core content areas of the clinical informatics subspecialty and is frequently referenced as a key determinant of success in transformational efforts.

This workshop will provide attendees with practical guidance and tools for leading technology-driven change efforts to improve quality in their organizations. These change efforts may involve implementation of new technology or optimization of existing technology and may be inspired by internally derived quality improvement goals, external reporting demands and/or reimbursement requirements.

The instructors will begin by demonstrating the importance of aligning technology-driven change efforts to an organization’s strategic goals as well as establishing the business case for managing such change efforts effectively. Using an interactive, case-oriented approach as well as Poll Everywhere technology to facilitate participation, the instructors will then guide attendees through key aspects of leading implementation and optimization, including governance and stakeholder analysis, organizational readiness assessment, workflow modeling, and communication strategy. Through guided discussion of these topics, attendees will (1) identify barriers to implementation and optimization; (2) apply tools useful for leading their organizations through these barriers; and (3) gain insight into various methods for evaluating the level of success of an implementation or optimization effort.

Content for the workshop will be informed by the complementary fields of informatics, innovation theory, implementation science, and change management. The instructors will also draw upon examples from their experience with efforts to implement and optimize health information systems in both inpatient and ambulatory care settings. The combination of case study, polling technology, and guided discussions will enable attendees to reflect individually upon the content, learn from the experiences and insights of fellow attendees, and apply practical tools to specific implementation and optimization scenarios.

Sunday, Nov. 5, 8:30 a.m. – 12:00 p.m.

Collaborative Workshops

W14: Enabling Innovation and Collaboration in Informatics and Health Care Research

M. Edmunds, AcademyHealth; P. Payne, Washington University in St. Louis, School of Medicine; S. Greene, Health Care Systems Research Network; P. Franklin, University of Massachusetts of Medical School

This workshop will describe best practices and offer practical guidance about how to innovate and enable collaboration to accelerate progress in biomedical and clinical informatics and health systems research. Intended for all career stages and organizational settings, the hands-on session is based on the experiences of leaders of the EDM Forum, which evolved from 11 separate AHRQ-funded grants to a network of more than 4,000 members, including two communities of practice; an online, peer-reviewed, open access journal, and more than 400 freely accessible analytic products (e.g., issue briefs reports, peer-reviewed manuscripts) and resources (e.g., webinars, toolkits).

Institutional barriers to shared governance and data sharing can slow or prevent collaboration. Perhaps one of the most distinctive aspects of the EDM Forum community has been its commitment to work together to solve some of the most pervasive issues in health systems by viewing those issues as shared challenges. Using this collaborative approach, methods, ensuing data, and corresponding analytics, code, and tools become transparent, re-usable, and cumulative in their impact.

In the first hour, presenters will showcase three types of innovative tools that enable collaboration, including: CIELO, an open science platform for sharing health analytics data and code; Data Analytics for a Learning Health System (DALHS), a community of practice for researchers embedded in health care delivery systems; and PROACTIVE: Patient Reported Outcomes (PROs) Implementation Toolkit, a collection of best practices and tools for inclusion of PROs in research and clinical practice.

After these opening presentations, you will have an opportunity to meet with the presenters in groups for one hour to discuss your work in progress and to learn how they were able to cultivate spaces of innovation and collaboration. The final hour’s discussion will take place in different small groups based on shared challenges identified by participants.


W15: Does Integrative Data Analytics on Biomedical Imaging Bring Us Closer to Precision Medicine? (sponsored by the Biomedical Imaging Working Group)

A. Sharma, Emory University; W. Hsu, University of California; E. Siegel, University of Maryland School of Medicine; K. Cheng, Penn State Health; I. Dinov, University of Michigan

Biomedical imaging is an important component of precision medicine. Imaging is a frequent, non-invasive approach for acquiring data on patients spanning the scale from microscopic and molecular to whole body visualization. Imaging also encompasses many areas of medicine, such as radiology, pathology, dermatology, and ophthalmology. Biomedical imaging informatics is a discipline that focuses on improving patient outcomes through the effective use of images and imaging-derived information in research and clinical care.

The past 18 months have seen an unprecedented explosion in the application of machine learning and deep learning in a wide a variety of domains, including, most recently in medical imaging. The objective of this pre-symposium is to assemble an interdisciplinary group of experts to share methods and experiences in biomedical imaging informatics to effectively integrate imaging and image-derived data, with clinical/molecular data, thereby influence clinical decision making and advance towards precision medicine. This year’s overarching theme focuses on the usage of AI and integrative data analytics, to bridge phenotypic information from images with clinical and molecular characterizations for precision medicine. The event will touch upon topics such as the role of machine learning in image interpretation, the discovery of novel correlations between images and other biological scales, the characterization of novel quantitative imaging features, and the translation of hierarchical models of disease into practice. There will also be a broader discussion that examines the current state of AI in medicine and specifically in radiology, where we are headed and whether man can expect to be replaced by machine, within the next 20 years. These topics blend tightly with the broader informatics interests of the AMIA attendees and will raise awareness of the opportunities, and relevance of imaging informatics research to other biomedical informatics activities.


W16: Promoting Ethical and Professional Responsibility in Biomedical Informatics Education (sponsored by Education, Ethical, Legal and Social Issues, People and Organizational Issues, and Primary Care Informatics Working Groups)

B. Kaplan, Yale University; S. Liaw, University of NSW; V. Subbian, University of Arizona; K. Courtney, University of Victoria; H. Hochheiser, University of Pittsburgh; K. Goodman, University of Miami

Increasing use of information technologies in clinical care; concerns over the role of algorithmic decision-making in everyday life; collection of vast amounts of physical, social, and personal heath data through devices, social media, and the Internet of Things; and highly-visible, informatics-driven efforts such as the Precision Medicine Initiative, make calls for responsible technology use more important than ever. This rapidly-changing landscape challenges informaticians to understand the ethical, legal, and social (ELSI) implications of these developments and informatics educators to develop approaches for incorporating them into already-crowded curricula.

This workshop will promote discussion of approaches to incorporating ELSI competencies in biomedical informatics education, research, and practice, including: (1) a survey of foundations and competencies, (2) current approaches for teaching ELSI concepts, and (3) experiences, lessons learned, and novel proposals for ELSI instruction in biomedical informatics curricula.

AMIA’s core competencies include fundamental knowledge in “ethical, legal, social issues: for example, human subjects, HIPAA, informed consent, secondary use of data, confidentiality, privacy.” How should these competencies be included and evaluated in a course of study? Are they sufficient for socially responsible and ethical use of technology in biomedicine and health care? The paucity of such topics in biomedical informatics courses and curricula provides an opportunity to elicit diverse opinions and approaches about these questions. Presenters and audience will address them from varying perspectives and educational experiences.

In addition to their expertise in biomedical informatics research and teaching, presenters will draw on their different disciplinary backgrounds (engineering, history, information systems, bioethics, law, social studies of science, computer science, philosophy, human factors, nursing, anthropology, medicine, public health) and country perspectives (US, Canada, Australia) to explore ways to promote ethical and professional responsibility in biomedical informatics.

Instructional Workshops

W17: Bayes'd and Confused

M. Weiner, Temple University School of Medicine; H. Lehmann, Johns Hopkins University School of Medicine

In an ideal word, all diagnostic tests would make perfect predictions, all therapies would be completely effective and without harm, and available resources would be limitless. However, even with ongoing innovation in sophisticated machine learning algorithms that underlie the current era of precision medicine, for many clinical areas, prediction of outcomes remains imperfect, therapies are not completely effective and resources are most certainly limited. Given the imperfect environment in which sophisticated predictive algorithms are applied, the output of these algorithms must be placed in a realistic clinical context to support clinical decision making. Through incorporation of prior evidence-based knowledge and from the clinical valuation of outcomes and decision points, Bayesian analysis and synthesis plays a key role in translating results of machine learning algorithms into actionable information for clinicians at the point of care.

Bayesian analysis has been around since the 18th century, and became inexorably tied to clinical decisionmaking with the work on Ledley and Lusted in their 1959 seminal paper “Reasoning Foundations of Medical Diagnosis,” which applied Bayes theorem to predict the likelihood of disease on the basis of presenting symptoms. Over the ensuing years, the number and granularity of the disease predictors has increased, the principles were applied to a range of decision support systems, and algorithms that deal with these large data sets have become more sophisticated. Bayesian analysis helps define how accurate a test needs to be in the context of the effectiveness and the expense of existing therapies.

This workshop will provide attendees with an overview of Bayesian fundamentals, of decision-analytic fundamentals, and with experience in using those fundamentals.

This course will not help you win at the casinos, but will help you understand how the odds are stacked against you!


W18: FHIR -- Implementing the HL7 Interoperability Platform: The Technology, Data Integration, and Business Model Development Across the Spectrum of Research, Patient Care, and Precision Medicine

C. Jaffe, Health Level 7 International; J. Mandel, Boston Children's Hospital; R. Bloomfield, Duke University; S. Huff, Intermountain Healthcare; G. Alterovitz, Harvard Medical School; M. Tripathi, Massachusetts eHealth Collaborative

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. Traditional standards development processes are too slow and inefficient. Moreover, the means for exchanging data has not facilitated data reuse for a broad range of purposes, including quality evaluation, decision support, clinical research, primary medical science applications, and population health. Moreover, the standards innovation process must evolve more rapidly, despite an environment constrained by the limited availability of resources, by government regulation and by the soaring knowledge base. The report of the JASON Task Force provided a clear and achievable path to that goal, beginning with the enablement of Application Programming Interfaces (APIs). Ever increasingly, the FHIR (Fast Healthcare Interoperability Resources) platform is fulfilling these needs in mobile health, Precision Medicine, and value-based care. The Argonaut Project, a private-sector initiative, is helping to drive FHIR implementation. The FHIR Foundation provides much needed public resources for the implementation community.


W19: Introduction to LOINC, the Global Vocabulary for Identifying Health Measurements, Observations, and Documents

D. Vreeman, Indiana University and Regenstrief Institute, Inc.; S. Abhyankar, Regenstrief Insitute, Inc.

LOINC® (Logical Observation Identifiers Names and Codes) is a freely available international standard for identifying laboratory and other clinical observations.1 Presently, LOINC is used by more than 44,000 users from 172 countries and has been adopted as a national standard in nearly 30 countries. LOINC has been translated into 18 variants of 12 languages and is used by healthcare organizations, reference laboratories, ministries of health and other federal agencies, professional societies, healthcare information exchange networks, insurance companies, healthcare IT vendors, instrument manufacturers, health application developers, and more.2 LOINC is now ubiquitous in health data systems worldwide, and is an essential ingredient of system interoperability.

This workshop will cover the basics of LOINC, including: its origin; how it is developed, distributed, and used; and its relationship to other vocabulary and messaging standards such as SNOMED CT and HL7. We will summarize the highlights of global adoption and use cases.

This workshop will explain the LOINC concept model and key features to help users pick out the differences between LOINC terms with subtle but important distinctions. Many informatics professionals are aware of LOINC’s coverage of laboratory tests, which we will explore, but we will also tour its rich content in other domains such as vital signs, clinical document titles, radiology procedures, patient assessment instruments, and patient reported outcomes measures.

This workshop will introduce the key tools and resources available for implementing LOINC. Our primary focus will be on how to get started with LOINC by mapping your local observation codes to LOINC codes. We will briefly describe some secondary uses of LOINC, such as automated electronic laboratory reporting to public health, use in clinical decision support systems, and clinical quality measurement. And last, we will describe some best practices for using LOINC that will prepare the participants for success in the long run.


W20: A Practical Introduction to Deep Learning Methods in Python (sponsored by the Natural Language Processing Working Group)

A. Jagannatha, J. Zheng, H. Yu, UMass Amherst

This workshop provides an introduction to recent advancements in deep learning and practical techniques to deploy deep learning models to real world problems. We have recently organized a successful workshop on deep learning (multi-layer neural networks) at Medinfo 2015 and have developed deep learning models for state-of-the-art natural language processing (including clinical event and phenotype detection in electronic health record notes document and sentence classification, semantic entailment and question answering). In this workshop we will cover the fundamentals of different Deep Learning models like FeedForward, Convolutional, and Recurrent Neural Networks. The focus will rest on using Deep Learning packages in Python programming language to quickly prototype and test different neural network models. Although the deep learning techniques are applicable to different AI tasks, in this workshop we will focus on natural language processing applications (e.g., named entity recognition).


W21: An Introduction to Natural Language Processing Methods and Applications in Clinical Research and Operation

O. Patterson, S. DuVall, P. Alba, VA Salt Lake City/University of Utah; Y. Huang, Med Data Quest, Inc.; H. Xu, University of Texas Health Science Center at Houston; J. Denny, Vanderbilt University

As the use of natural language processing (NLP) methods in preparing data for research and operation continues to increase, users should understand the benefits and limitations of such a tool. While NLP is not a “solved” science, there are many tasks that NLP can do reliably. Extracting concepts (symptoms, diseases, medications) and values (lab values, vital signs) that are stored in the text is one example. More complex tasks, such as determining what caused an event of interest or why a patient discontinued a medication can also be addressed using the right tools. This workshop will provide attendees with a general overview of NLP tools and methods used in health research and patient care. Synthetic clinical notes will be provided along with open-source tools that will allow participants to implement a working NLP system, including the eHOST annotation application, Unstructured Information Management Architecture Asynchronous Scaleout (UIMA AS)1, the Leo NLP libraries2,3, and the CLAMP system. In addition, two important applications of NLP: 1) to extract phenotypic information from EHRs to support precision medicine studies and 2) to facilitate real-time decision support systems in clinical operations, will be introduced. Attendees will experience the process of completing an NLP task and leave the tutorial with concrete examples of how NLP can be used at their institutions to benefit research studies or patient care.