• AMIA Symposium Student Design Challenge

  • Nov. 14-18, San Francisco

    AMIA 2015 Annual Symposium

AMIA 2015 Student Design Challenge

The Human Side of Big Data – Facilitating Human-Data Interaction

AMIA is pleased to announce the 3rd Annual Student Design Challenge (SDC). In this challenge students from different scientific disciplines and of various backgrounds proposed creative solutions to a specified problem related to healthcare. This year the Student Design Challenge submissions focused on novel and original ways to facilitate engagement between humans and computing data-analytic systems. “Big data” has become a popular buzzword both in academics and industry. New data streams and ever-increasing amounts of rich, complex, and multi-faceted data have the potential to lead to new discoveries and inform decision-making of both clinicians and consumers. However, to fully harvest this potential, data-analytic systems must allow their users to engage with the data in meaningful ways.

Student teams were asked to envision new ways for clinicians and/or patients to engage with data-analytic systems that take advantage of both emerging computational capabilities and uniquely human intelligence and reasoning.

Seven semi-finalists present during Poster Session 1

Monday, November 16
5:00 p.m. – 6:30 p.m.
Grand Ballroom, Ballroom Level

KaryoViz: Designing a Karyotype Visualization Platform for Clinical Decision Support
Z. Abrams, S. Raje, The Ohio State University

The EH Tracker: Using Dynamic Environmental Health Data for Improved Decision-making of Health
J. Burke, D. Hyun Lee, R. James, University of Washington

Improving User Engagement and Insight through Contextualized Quantified Self
T. Callahan, University of Colorado Denver/Plurl Health; T. Lorberbaum, A. Yahi, Columbia University/Plurl Helth

Interactive Data Visualization Dashboard for MyApnea
A. Choi, B. Cordier, P. Das, J. Li, Oregon Health & Science University

I-SMILE: Similarity based Just-in-time Recommendation System for Public Health
E. Choi, Georgia Institute of Technology; J. Dcruz, Centers for Disease Control and Prevention; S. Lin, Georgia Institute of Technology; K. Ryder, Association of Schools and Programs of Public Health; , A. Singh, H. Su, Georgia Institute of Technology

Learning from the Data: Exploring a Hepatocellular Carcinoma Registry Using Visual Analytics to Improve Multidisciplinary Clinical Decision-making
M. Hribar, L.N. Sanchez-Pinto, K. Fultz Hollis, G. Ren, D. Woodcock, Oregon Health & Science University

Accelerating Biomedical Informatics Research with Interactive Multidimensional Data Fusion Platforms
S. Raje, The Ohio State University

Four finalists will present their solutions in Session S74

Tuesday, November 17
1:45 p.m. – 3:00 p.m.
Grand Ballroom, Ballroom Level

The EH Tracker: Using Dynamic Environmental Health Data for Improved Decision-making of Health
J. Burke, D. Hyun Lee, R. James, University of Washington

Improving User Engagement and Insight through Contextualized Quantified Self
T. Callahan, University of Colorado Denver/Plurl Health; T. Lorberbaum, A. Yahi, Columbia University/Plurl Helth

Interactive Data Visualization Dashboard for MyApnea
A. Choi, B. Cordier, P. Das, J. Li, Oregon Health & Science University

Learning from the Data: Exploring a Hepatocellular Carcinoma Registry Using Visual Analytics to Improve Multidisciplinary Clinical Decision-making
M. Hribar, L.N. Sanchez-Pinto, K. Fultz Hollis, G. Ren, D. Woodcock, Oregon Health & Science University

Contact

Please read the entire Challenge description. If you have any questions about this process, please send an email to studentdesignchallenge@amia.org


Problem Introduction
Call For Submissions
SDC Committee

In recent years, the healthcare community has witnessed an explosion in the amount and richness of data available to both clinicians and patients. These data come in different forms and may originate from a variety of sources (1). Some of these data are generated within traditional healthcare settings and through computational analysis of records within electronic patient record. Other data come from novel sources, for example from individuals’ health monitoring technologies, their use of social media and other online behaviors, and through capture of environmental characteristics pertinent to their health, such as quality of air or noise levels. In response to these trends, new data science methods focus on computational analysis of complex, heterogeneous, dynamic data streams.

While there is much enthusiasm in regards to the new discoveries possible with new data science methods, there also remains considerable skepticism regarding their impact on health and healthcare. Recent studies suggested that many novel self-monitoring technologies, particularly wearable technologies, have a short lifespan and are often abandoned after only 6 months of use raising concerns regarding their usefulness in the long run (2). Clinical decision support systems that continue to rely on alerts to deliver conclusions and recommendations arrived at with data analytic mechanisms often lead to “alert fatigue”, thus negatively impacting their ability to inform clinicians’ decisions (3). Many factors prevent these technologies from realizing their true potential, one of them being reliance on the “black box” model, in which human users are excluded from setting goals and priorities, and from the analytical process (4). Arguably, the success of the new data-driven technologies and data science methods will depend not only on their ability to identify signal in the collected data, but also to engage human users, and lead to insight, discovery, improved decision-making, and enhanced quality of life.

With the ever-increasing amount and complexity of the available data, these challenges are likely to amplify. The question becomes then how to design computing systems that are driven by data-analytic systems yet engage their users in uniquely human ways and take advantage of their human intelligence, expertise, and intuition, and reflect their goals, values and priorities.

In this Student Design Challenge, we call on undergraduate and graduate students and trainees in Biomedical Informatics and related fields to propose original design solutions for facilitating interaction between humans and data-driven analytic systems. We are inviting solutions that address different types of systems, from those that use self-monitoring data to inform individuals’ decisions regarding their health and wellness, to those that utilize multiple streams of data to inform clinical decision-making. In both of these scenarios, the focus of the solutions should be on novel ways of engaging users of in collection and analysis of the data that lead to insight and informs their choices.

References

  1. Weber GM, Mandl KD, Kohane IS. FInding the missing link for big biomedical data. JAMA. 2014 Jun 25;311(24):2479–80.
  2. Ledger D. Inside Wearables - Part 2 [Internet]. Endeavour Partners LLC; 2014 Jul. Available from: http://endeavourpartners.net/assets/Endeavour-Partners-Inside-Wearables-Part-2-July-2014.pdf
  3. Kesselheim AS, Cresswell K, Phansalkar S, Bates DW, Sheikh A. Clinical Decision Support Systems Could Be Modified To Reduce “Alert Fatigue” While Still Minimizing The Risk Of Litigation. Health Aff. 2011 Dec 1;30(12):2310–7.
  4. Bell MZ. Why Expert Systems Fail. The Journal of the Operational Research Society. 1985 Jul 1;36(7):613–9.

To qualify for participation, teams should include only students in degree-pursuing graduate programs (including post-doctoral fellows pursing MA or MS degrees) or Graduate Certificates. Undergraduate students are welcome to participate in design teams, provided that they are supervised by graduate students. Given the nature of the creative process, we suggest that teams include no more than 4 or 5 individuals. No faculty advising is required for participation; in fact, we encourage teams to work independently and without faculty supervision.

Each team will be asked to identify a specific challenge related to the proposed theme. We recommend that teams select a specific area where new data streams have the potential of generating new discovery and insight. These could include individuals’ health and wellness management, or specific clinical problem that can be addressed with new data. In both of these scenarios the focus of the solution should be on new ways individual users can interact with the system and its data-analytic engine. Some potential areas of focus could include:

  • Identifying new ways to engage individuals in collection and analysis of data generated with wearable health monitoring devices
  • Increasing transparency of clinical data analytic systems through novel data visualizations
  • New ways of engaging users of data-analytic systems in hypothesis generation and analysis of evidence for the conclusions

Competition Process

Each team will submit an extended abstract (5 page maximum) dEach team will submit an extended abstract (5 page maximum) discussing their description of the specific challenge related to Beyond Patient Portals: Engaging Patients with their Healthcare Providers, the proposed solution, and their design process. Supplementary materials (including storyboards and mockups, or source code and sample output) can be submitted as PDF. The supplementary material would not count against the 5 page maximum. The submission process will be done through ScholarOne (more details on the submission process are to follow). The submissions will be evaluated through a peer-review process by the SDC steering committee.

The 8 best proposals will be asked to present their solutions during a poster session at AMIA 2015. At least one member from each of the 8 teams will be expected to attend the conference to present a poster illustrating their solution, discuss their solution, and the design process with conference attendees. AMIA will wave registration fee for one presenter from each of the eight teams, with the expectation that the presenter holds a student membership with either AMIA or ACM.

Four teams will also be notified prior to the symposium that their proposal has been selected as a finalist for the AMIA SDC Award. They will be asked to give a presentation about their solution during the AMIA Student Design Challenge session. The 4 finalists will give an oral presentation and, where appropriate, demonstration of their design to the panel of SDC Judges and AMIA attendees. The judges will rank the solutions and presentations to identify the winner and subsequent 2nd and 3rd place teams. The winners will be announced during the last day of AMIA Annual Symposium and acknowledged during the AMIA Closing Plenary.

Abstract Preparation

The participants will prepare an extended abstract (five pages maximum) written in the AMIA format that should include:

  • Definition of the selected challenge related to the interaction between humans and data-analytic systems grounded in deep understanding of an identified health problem
  • Description of the proposed solution
  • Discussion of alternative solutions considered
  • Discussion of the strengths and weakness of the chosen solution as compared to the alternatives
  • Proposed implementation and dissemination plan (what it would take for this solution to be adopted on a large scale)
  • Proposed evaluation plan (the participants will be expected to outline potential directions for evaluation, but not to perform it)

The Supplementary Materials should include:

  • For interactive solutions: a mockup or storyboard illustrating the proposed functionality and the interaction of the proposed solution, a link to a video demo of the system.
  • For computational solutions: source code of the solution as a text file or a link to the team’s github repository as well as sample output file (in a PDF document)

The completed abstract and any supplementary documents should be submitted using ScholarOne by 11:59 p.m. EDT on June 1st, 2015. If you do not already have a ScholarOne account, you will need to create one. AMIA member log-in will not provide access to ScholarOne. If you are not sure if you already have an account or if you have one, but do not remember your user name and password, please contact Dasha Cohen at dasha@amia.org

Review Criteria

All proposed solutions will be reviewed by the SDC Steering Committee, consisting of distinguished members from the AMIA and HCI communities. The members of the Steering Committee will review the abstracts and assess their quality, focusing on both the actual proposed solution, and its description and justification in the proposal, based on the following criteria:

  • Understanding of the clinical process (does the solution address an important clinical problem in a realistic way and does it demonstrate a deep understanding of the clinical process)
  • Fit to the problem (how likely is the proposed solution to address the selected problem?)
  • Innovation (how novel and original is the solution?)
  • Transformative potential (how likely is it to transform the nature of engagement between humans and data-analytic systems?)
  • Completeness (is the solution is well thought-out and complete)
  • Clarity of the design process (how well the solution and the design process described in the abstract)
  • Clarity of the strengths and weaknesses discussion (do the teams have a realistic and thoughtful assessment of the strengths and weaknesses of their solutions?)
  • Appropriateness of the evaluation approach (is the evaluation plan appropriate for the solution?)

Awards

The SDC awards ceremony will take place during the last day of AMIA Annual Symposium.

Timeline

  • June 1, 2015 – proposal submission deadline
  • August 1, 2015 – notifications to authors
  • September 10, 2015 – final accepted revision submission deadline

Contact

If you have any questions about this process, please send an email to studentdesignchallenge@amia.org

Lena Mamykina, PhD, Assistant Professor
Department of Biomedical Informatics, Columbia University

Dr. Mamykina’s broad research interests include individual’s sensemaking and problem-solving in context of health management, collective sensemaking within online health support communities, clinical reasoning and decision-making, communication and coordination of work in clinical teams, and ways to support these practices with informatics interventions.

Dr. Mamykina received her B.S. in Computer Science from the Ukrainian State University of Maritime Technology, M.S. in Human Computer Interaction from the Georgia Institute of Technology, Ph.D. in Human-Centered Computing from the Georgia Institute of Technology, and M.A. in Biomedical Informatics from Columbia University. Her dissertation work at Georgia Tech focused on facilitating reflection and learning in context of diabetes management with mobile and ubiquitous computing. Prior to joining DBMI as a faculty member, she completed a National Library of Medicine Post-Doctoral Fellowship at the department.

Madhu Reddy, PhD, Associate Professor
College of Information Sciences and Technology (IST) Center for Integrated Healthcare Delivery Systems (CIHDS) Penn State University

Dr. Reddy’s research focuses on issues of collaboration in healthcare. He is particularly interested in how healthcare providers collaborate during information seeking and decision-making activities and the role that HIT plays in supporting these types of collaboration in clinical settings.

Dr. Reddy received his M.S. in Health Care Administration from the California State University, Long Beach, M.S. in Information and Computer Science from the University of California, Irvine, and Ph.D. in Information and Computer Science from the University of California, Irvine.

Patricia Flatley Brennan, Ph.D, Moehlman Bascom Professor
Industrial and Systems Engineering, University of Wisconsin-Madison

Dr. Brennan's research focuses on designing and evaluating home care community computer systems for use by patients. Her work ranges from the development and evaluation of computer networks as a mechanism for delivering nursing care to homebound ill persons and their caregivers to assessing the impact of patient-centered computer technology on the health outcomes of persons following coronary artery bypass graft surgery. Her most current projects include exploring how individuals and families manage health information in their homes, studying the usability of secure email use in clinics, and is developing information tools and resources to support self-care and health self-management.

James Durrell, MBA
Sr. Director, Siemens Healthcare

Jim Durrell is Sr. Director, Clinical Solutions, for Siemens Healthcare. In this role, he is one of the core team members for the Soarian Clinicals EHR. He is responsible for R&D teams in the U.S., India, and Romania, including the team building the Soarian Mobile solution. Prior to joining Siemens, Jim was CTO of Health Monitoring Solutions, which provides public health reporting for several hundred hospitals across the U.S. Jim received both his B.S. in Computer Science and his MBA from Penn State University and was formerly an adjunct professor in the University of Pittsburgh School of Information Science.

Paul Gorman, MD
Associate Professor,
Department of Biomedical Informatics, Oregon Health & Science University

Dr. Gorman's research is focused on the use of information by experts, mainly clinicians, in real-world problem-solving, mainly patient care. Most often, his work uses observational methods to study the activities of individuals and groups as they use information to perform real world tasks, e.g., information needs, seeking and use, naturalistic decision making, distributed cooperative problem solving, distributed cognition, and social informatics.

George Hripcsak, MD, MS, Chair, Department of Biomedical Informatics
Vivian Beaumont Allen Professor of Biomedical Informatics Director, Medical Informatics Services, NYP/Columbia

George Hripcsak, MD, MS, is Vivian Beaumont Allen Professor and Chair of Columbia University’s Department of Biomedical Informatics, Director of Medical Informatics Services forNewYork-Presbyterian Hospital, and Senior Informatics Advisor at the New York City Department of Health and Mental Hygiene. Dr. Hripcsak is a board-certified internist with degrees in chemistry, medicine, and biostatistics. He led the effort to create the Arden Syntax, a language for representing health knowledge that has become a national standard. Dr. Hripcsak’scurrent research focus is on the clinical information stored in electronic health records. Using data mining techniques such as machine learning and natural language processing, he is developing the methods necessary to support clinical research and patient safety initiatives.

Jonathan Nebeker, MD, MS
Associate Professor of Internal Medicine,
University of Utah, School of Medicine

Dr. Nebeker is currently interested in translating theoretical frameworks from social and cognitive psychology to medicine for designing and evaluating user interfaces for EHRs (with Charlene Weir and Frank Drews.) He led a project to translate the Contextual Control Model from a branch of Cognitive Systems Engineering. Guided by this translated model, his team developed a new paradigm for graphical user interfaces (GUIs) for EHRs. Instead of focusing on data, which is typical of current EHRs, the GUI focuses on thought- and workflow. The GUIs incorporate ideas from mindset, dual process, and communication theories. They featured information displays that are designed to reduce cognitive effort to understand what is going on with the patient. In a randomized controlled trial versus a widely used traditional interface, the new interfaces were significantly faster—despite minimal training in the unfamiliar interfaces.

Dr. Nebeker also has national leadership roles in VA. He is Director of VA Informatics and Computing Infrastructure (VINCI.) VINCI is a secure, powerful, virtualized computing environment with national clinical data back to 2000. In addition to directing the center, Dr. Nebeker leads GUI development for several applications. Dr. Nebeker is the Clinical Lead for the DoD-VA Integrated EHR Graphical User Interface. In this capacity he coordinates with national VA clinical leads and directs the vision for the new paradigm for the iEHR interfaces.

Wanda Pratt, Ph.D
Professor, Information School, Division of Biomedical & Health Informatics, University of Washington

Wanda Pratt is a Professor in both the Information School and the Division of Biomedical & Health Informatics in the Medical School at the University of Washington. She received her Ph.D. in Medical Informatics from Stanford University, her M.S. in Computer Science from the University of Texas, and her B.S. in Electrical and Computer Engineering from the University of Kansas. Her published papers span a wide range of topics whose central theme is to understand the problem of information overload in a variety of health contexts and to develop new types technology to address those problems. She received an NSF CAREER Award for her work on literature-based discovery systems.

Samuel Trent Rosenbloom, MD, MPH, FACMI
Dr. Rosenbloom is the Vice Chair for Faculty Affairs, the Director of Patient Engagement Technologies and an Associate Professor of Biomedical Informatics with secondary appointments in Medicine, Pediatrics and the School of Nursing at Vanderbilt University. He is a board certified Internist and Pediatrician who earned his M.D., completed a residency in Internal Medicine and Pediatrics, a fellowship in Biomedical Informatics, and earned an MPH all at Vanderbilt. Since joining the faculty in 2002, Dr. Rosenbloom has become a nationally recognized investigator in the field of health information technology evaluation. His research has focused on studying how healthcare providers interact with health information technologies when engaging patients, documenting patient care and making clinical decisions. Dr. Rosenbloom has successfully competed for extramural funding from the National Library of Medicine and from the Agency for Healthcare Research and Quality in the role of principal investigator. Dr. Rosenbloom’s work has resulted in lead and collaborating authorship on over 60 peer reviewed manuscripts, which have been published in Journal of the American Medical Informatics Association,Pediatrics, Annals of Internal Medicine, andAcademic Medicine, among others. In addition, Dr. Rosenbloom has authored and coauthored 5 book chapters and numerous posters, white papers and invited papers. He has been a committed member of the principal professional organization in his field, the American Medical Informatics Association (AMIA). He has served AMIA in leadership roles, including participating in: a Scientific Program Committee, the Journal of the American Medical Informatics Association (JAMIA) Editorial Board, a national Health Policy Meeting Committee, the JAMIA Editor in Chief search committee, and a Working Group on Unintended Consequences. As a result of his research success and service to AMIA, Dr. Rosenbloom was the annual recipient of the competitive AMIA New Investigator Award in 2009, and was elected to the American College of Medical Informatics (ACMI) in 2011. In addition, Dr. Rosenbloom has participated in study sections for the National Library of Medicine and the Agency for Healthcare Research and Quality’s Healthcare. He has also participated as a member of the HL7 Pediatric Data Special Interest Group and the American Academy of Pediatrics’ Council on Clinical Information Technology. In addition, Dr. Rosenbloom is an active reviewer several journals covering general medicine, pediatrics and biomedical informatics.