Jeffrey Klann*, Partners HealthCare and Massachusetts General Hospital, Harvard Medical School, Boston, United States Adam Wright, Brigham and Women's Hospital, Harvard Medical School, Boston, United States Allison Mccoy, School of Biomedical Informatics, Health Science Center at Houston, The University of Texas, Houston, United States Dean Sittig, School of Biomedical Informatics, Health Science Center at Houston, The University of Texas, Houston, United States Shawn Murphy, Partners HealthCare and Massachusetts General Hospital, Harvard Medical School, Boston, United States Track: Practice Presentation Topic: Web 2.0 approaches for clinical practice, clinical research, quality monitoring Presentation Type: Oral presentation Submission Type: Single Presentation Building: Joseph B. Martin Conference Center at Harvard Medical School Room: Auditorium Date: 2012-09-15 02:00 PM – 02:45 PM Last modified: 2012-09-10

If you are the presenter of this abstract (or if you cite this abstract in a talk or on a poster), please show the QR code in your slide or poster (QR code contains this URL).

Imagine you are a physician preparing to see a patient. You load her record into your EHR (electronic health record system) to figure out what you need to know to properly treat her. You are presented with page after page of notes, lab results, medications, diagnoses, and tests. You try to synthesize in your mind an understanding of the whole person. You mastered this skill in medical school, but this is a complex patient with several chronic problems. It is the end of a long day and you feel overwhelmed. But you have no choice - this is the only interface available to you because it is the only one provided in the product your practice has purchased. Although you can perform synthesis and summarization, your EHR cannot.

Enter SHARP, a $60 million government initiative that seeks to conquer well-understood challenges in medical informatics through breakthrough research. Instead of remaining frustrated, you log on to the SMART medical app store. There you download a patient summarization app, which uses physician-validated models to present a brief overview of complex patients. With a few clicks, it integrates with your EHR, and you have a problem-oriented patient summary. You see active problems alongside the relevant treatment information: medications being used to treat each problem, recent laboratory test results to help you understand whether this treatment is succeeding, and links to the most relevant progress notes.

This vision is available today, through the integration of three advanced technologies. i2b2, deployed in over sixty locations throughout the country, is an open-source central data repository for multiple clinical systems. SMART is an evolving platform for building reusable, platform-agnostic medical applications. The National Center for Cognitive Informatics and Decision Making (NCDD) is developing methodologies for modeling and summarizing complex patient records. We have: (1) created a SMART app based on NCDD methodologies, and (2) enabled i2b2 to run SMART apps. Now, the many sites using i2b2 can view a patient summary using data from their EHR using these freely available tools.

Herein, we will demonstrate this NCDD SMART app running in an i2b2 instance at Partners Healthcare. We will explain the technical architectures and cognitive models that enable these technologies. Finally, we will discuss both the challenges and limitations arising from and the opportunities made possible through this large collaboration.