Tuesday, May 19
8:00 a.m. – 10:00 a.m. PDT/11:00 a.m. – 1:00 p.m. EDT
J. Herigon, Boston Children's Hospital, Harvard Medical School; C. Uptegraft, Boston Children's Hospital, Harvard Medical School, U.S. Air Force
This workshop consists of four sections. During the first two sections, we will briefly overview SMART on FHIR, how EHR vendors are implementing the FHIR standard, and cover basic application design principles and resources for development. The third section encompasses the hands-on portion of the workshop where we will guide participants as they build a functioning SMART on FHIR application tested against a publicly available FHIR server. Participants may build one of our step-by-step guided applications or may build one on their own using a provided FHIR resource ‘cheat sheet’. Lastly, we will conclude with an overview of the practicalities of implementing a SMART on FHIR application within the production environment, with experiences from past implementations across different EHR settings.
8:00 a.m. – 12:30 p.m. PDT/11:30 a.m. – 3:30 p.m. EDT
J. Manning; E. Olson, Atrium Health's Carolinas Medical Center; J. Nielson, Northeast Ohio Medical University; E. Puster, Regenstrief Institute, Inc., Indiana University Health; A. Marshall, Beth Israel Deaconess Medical Center
Informaticians are often frustrated by the poorly-designed user interfaces that they use every day. This workshop teaches informaticians how to harness Flutter — an open-source front-end toolkit for simultaneous iOS and Android app development — to create next generation “Best of Breed” software. During last year’s CIC workshop, attendees live-coded a mockup of the AMIA CIC app. We will build directly off this work to refresh the basics, then we will cover intermediate concepts. We will also introduce the changes that have occurred in the last year, such as Flutter’s expansion beyond mobile to also include web and desktop development. This will be an interactive, guided workshop with the opportunity for questions, suggestions, and discussion throughout. The goal is to impart our audience with the skillset to build their own workflows and user interfaces via a simple and easy-to-use tool. By live-coding with other informaticians who are subject matter experts in this field, attendees of this workshop will be empowered to turn their own designs into products. Bring your laptops and come ready to code! To make the most of this event, it is strongly recommended to watch the Flutter4CME videos.
A. Davison, Johns Hopkins University School of Medicine; P. Gorman, Oregon Health & Science University; J. Zavodnick, Jefferson; H. Lehmann, Johns Hopkins University School of Medicine; S. Panchanathan, University of Arizona
In this workshop, attendees will engage in a robust discussion around the intersection of Entrustable Professional Activities (EPAs) and Clinical informatics. During this transformative time in U.S. healthcare, we must think broadly about how medical students are trained and assessed on inputting, interpreting, and extracting data to and from not just EHRs, but wearables, mHealth apps, telemedicine platforms, chatbots and other technologies. The Association of American Medical Colleges (AAMC) has been piloting a competency-based approach to medical student education with the development of 13 core EPAs. Yet questions remain: Within each EPA, what are the specific competencies and behaviors that have technology-based imperatives? How can we standardize the approach to training and assessment in a vendor and institution agnostic manner? Each of the core EPAs have specific behaviors and functions that require medical students to demonstrate critical thinking and clinical acumen in the context of modern health information technology. While most EPAs implicitly involve the use of technology, some explicitly reference health IT tools. For example, one of the competencies in EPA 8 (Give or receive a patient handover) involves explicit mention of updating an electronic handover tool. This workshop will be a great opportunity for clinical informatics educators to share best practices on teaching and assessing medical students on the essential competencies they need to be entrusted with prior to starting residency. The output of this workshop will be a foundational framework for viewing the EPAs through a clinical informaticians’ lens. This discussion will then serve as a springboard for future work on developing and validating assessments of EPAs.
10:30 a.m. – 12:30 p.m. PDT/1:30 p.m. – 3:30 p.m. EDT
R. Rocha, S. Maviglia, Semedy/Harvard Medical School/ Brigham and Women’s Hospital; D. Aronsky, Semedy/Vanderbilt University Medical Center
Healthcare institutions build increasingly large amounts of clinical knowledge assets. They are responsible for the accuracy, transparency and updating of the content. Inconsistent, incomplete, and outdated clinical knowledge assets represent unnecessary patient safety risks. Unfortunately, many organizations limit their knowledge management activities to a reactive and an ad-hoc approach, lacking a formal content review and maintenance process, and a system that supports an institution-wide knowledge management strategy. This workshop will provide an introduction to clinical knowledge management topics that include the cataloguing of knowledge assets, authoring and modeling of metadata, managing relationship and dependencies among data, importing and exporting knowledge assets from and to other clinical applications, guaranteeing structural and semantic integrity when knowledge assets change, and comprehensive asset lifecycle process. The workshop includes practical experiences, challenges, and lessons learned.
1:30 p.m. – 3:30 p.m. PDT/4:30 p.m. – 6:30 p.m. EDT
K. Unertl, Vanderbilt University Medical Center; S. Haque, RTI International
Successful implementation and use of health information technology requires attention to technical and organizational components. Organizational components include workflow, technology acceptance and sociotechnical factors, among others. Fields such as Organizational Theory and Change Management offer a substantial foundation of evidence-based guidance on how to navigate the human and organizational aspects of technology-based change. Support is needed to translate theory and concepts from multiple fields into clinical informatics practice in a way that’s accessible for organizations. The goal of this workshop is to draw from evidence in related fields to bridge the gap between theory and practice. This will be accomplished by providing participants with hands-on experience through exploration of real-world case studies and participatory exercises.
R. Hoyt, Virginia Commonwealth University
Machine learning and artificial intelligence have become a reality in clinical medicine. Very recently, artificial intelligence has exceeded human diagnostic accuracy in cardiology, dermatology, ophthalmology and radiology. Clinical informaticists need to have a working knowledge of these modalities because they are being used for predictive analytics, clinical decision support, image recognition, voice recognition and natural language processing.
The standard pathway to learn machine learning is through a Masters-level data science program, specifically learning one of the programming languages (R or Python). While this approach is optimal, it is not practical for those not in a degree program and there is a very steep learning curve associated with programming languages. In addition, knowledge of higher math (calculus and linear algebra) is generally required.
An alternate approach towards “democratizing machine learning” is through the use of machine learning software. This workshop will discuss seven such programs but focus only on RapidMiner which is felt to be the “best of breed.” This software package automates many of the data preparation, exploration and visualization phases (TurboPrep), as well as the modeling phase (AutoModel).
Workshop participants will learn how to perform data preparation, exploration and analysis using this platform. They will download datasets to predict heart disease (classification) and medical charges (regression). The machine learning software will automatically select multiple appropriate algorithms and then compare algorithm performance with standard measures of accuracy.
A. Solomonides, NorthShore University HealthSystem; A. Desai, VA; B. Middleton, Apervita; J. Platt, University of Michigan; J. Richardson, RTI International; P. Walker, Vanderbilt University
We have long envisioned integrated actionable knowledge in electronic health records (EHR). For those working at the cutting edge of biomedical informatics, this vision is still a major motivation. Yet there are common complaints of technology-induced provider burnout, of meaningless data, of inappropriate alarms, and of perfunctory discharge notes – all resulting in a failure to deliver upon the expected value proposition. The revitalized field of artificial intelligence (AI), especially in the form of adaptive machine learning, is promising anew to revolutionize medicine. Yet AI itself gives rise to ethical concerns: is it acceptable if the AI does not provide clear reasons for its decisions? Is it acceptable if its reasoning process is obscured by the “black box” in which it lies hidden?
The Learning Health System (LHS) movement has conceptualized the development of evidence through science and practice as an integral part of the delivery of healthcare and support for good health and wellbeing. Implicit in this concept is the idea that the knowledge developed, validated, curated and distributed throughout the LHS is not only actionable, but ideally is executable.
How do the issues of trust and policy impact the LHS movement and its diverse initiatives, including Mobilizing Computable Biomedical Knowledge (MCBK)? We wish to explore the fundamental characteristics of a knowledge commons that would warrant the trust of the many communities it would engage and serve: engineers who would develop the systems, informaticians who develop knowledge artifacts, providers and others who would use them, and patients—and their caregivers and advocates—who would be impacted. How will trust be established, how perceived, how maintained? Several frameworks for conceptualizing knowledge commons, establishing and maintaining trust, and incorporating executable knowledge will be explored and discussed.
K. Couperus, Madigan Army Medical Center
We can enhance training opportunities and improve learning efficiency through new innovative teaching platforms. Traditional lecture has been augmented by simulation, flipped classrooms, and more engaging teaching styles. We propose another addition to emergency medicine education: virtual and augmented reality. These technologies have vastly increased in capability and portability while decreasing in cost. Case Western is teaching medical school anatomy classes in 50 percent less time using tailored augmented reality programs, and other industries are showing similar results. Emergency medicine and first responders are well suited to leverage these technologies given our frequent encounters with low frequency high stakes cases. To our knowledge, we developed the first autonomous trauma simulator, leveraging $7 million in DoD physiology engine software to create a dynamic decision training platform for military medical providers. Broadly, these solutions can facilitate and/or automate educational processes through immersive simulation environments and guided educational content. This offers immense potential for core and continuing educational objectives. Our aim is to present current virtual, augmented, and mixed reality platforms. We will describe cost, current programs, funding opportunities, and discuss how educators can help shape this next evolution in training. We will bring devices for demonstration and/or use to further promote individual creativity. Finally, we will present the workflow we leveraged to develop our virtual reality content: picking a case, learning objectives, gameplay design, platform, funding source, and how to work with technical experts to achieve the desired training outcome. We will augment this by presenting telementoring use cases actively being researched through DoD funding. We appreciate your consideration of this proposal.