This work is funded by a R01 grant from NLM, NIH.

As electronic medical records (EMRs) capture increasing amounts of data per patient, compiling a clinical narrative becomes cognitively more demanding. This information overload is particularly challenging in settings such as the intensive care unit (ICU) where a new data point may be added to a patient’s record almost every minute. Moreover, the display of patient data in current EMRs is not specific to the clinical context and burdens the physician.

An EMR that focuses the physician’s attention on relevant patient data could help reduce the time needed to assess the patient’s condition and improve the quality of the resulting judgments, enabling improved decision making, reduced medical errors, and greater efficiency. We built a prototype LEMR system that records how physicians view EMR data, which we used to train models that predict which EMR data will be relevant in a given patient. We call this approach a Learning EMR (LEMR).

• Shyam Visweswaran, MD, PhD - PI (Biomedical Informatics, University of Pittsburgh)
• Gregory F. Cooper, MD, PhD - Co-I (Biomedical Informatics, University of Pittsburgh)
• Harry Hochheiser, PhD - Co-I (Biomedical Informatics, University of Pittsburgh)
• Gilles Clermont, MD, MSc - Co-I (Critical Care Medicine, University of Pittsburgh)
• Milos Hauskrecht, PhD - Co-I (Computer Science, University of Pittsburgh)
• Dean Sittig, PhD - Co-I (Biomedical Informatics, The University of Texas Health Science Center)
• Titus Schleyer, DMD, PhD - Collaborator (Biomedical Informatics, Regenstrief Institute & Indiana University School of Medicine)
• Andrew J. King, MS - PhD student (Biomedical Informatics, University of Pittsburgh)
• Luca Calzoni, MD - PhD student (Biomedical Informatics, University of Pittsburgh)
• Gaurav Trivedi, MS - PhD student (Intelligent Systems Program, University of Pittsburgh)
• Mohammadamin Tajgardoon - PhD student (Intelligent Systems Program, University of Pittsburgh)
• Hoah-Der Su, Honest Broker & Data Extraction
• Yu (Louisa) Zhang, Software Design/Development
• Toni Porterfield, Administrator

Using eye-tracking to support a Learning Electronic Medical Record system.
Visweswaran S.
Presented at the AMIA 2019 Clinical Informatics Conference. Atlanta, GA. May 2019.

A study using machine learning to predict the information seeking behavior of clinicians when using an electronic medical record system.
King, AJ, Cooper, GF, Hochheiser, H, Clermont, G, Hauskrecht, M, Visweswaran, S.
In: AMIA Annual Symposium Proceedings. 2018 Nov 7.

Developing a learning electronic medical record system.
Visweswaran S.
Presented at the AMIA 2018 Clinical Informatics Conference. Scottsdale, AZ. May 2018.

Development of a Learning Electronic Medical Record system.
Visweswaran S.
Presented at the Department of Neurology Grand Rounds Series. University of Pittsburgh, Pittsburgh PA. May 2018.

Overview of a system that learns how to selectively highlight information in an EMR.
Cooper, GF.
Presented at University of Utah School of Medicine. April 2018.

A learning electronic medical record system: Providing decision support using machine learning.
Visweswaran S, King AJ, Cooper, GF, Hochheiser H, Clermont, G.
Presented at the STEM Junction Symposium. Fox Chapel Area High School, Pittsburgh PA. Nov 2017.
(presentation)

Exploring novel representations of clinical data in a learning electronic medical record.
Calzoni, L.
Presented at the Critical Care Medicine CRISMA (Clinical Research, Investigation, and Systems Modeling of Acute illness) Weekly Research Conference. University of Pittsburgh Department of Critical Care Medicine, Pittsburgh PA. Nov 2017.
(presentation)

Interactive natural language processing on clinical text.
Trivedi G.
Presented at AMIA NLP Working Group. AMIA Annual Symposium Nov 2017.
(presentation)

Exploring novel graphical representations of clinical data in a learning EMR.
Calzoni, L, Clermont, G, Cooper, GF, Visweswaran, S, Hochheiser, H.
In: AMIA Annual Symposium Proceedings. 2017 Nov 7.
(poster)

Learning cycle of a Learning Electronic Medical Record.
King AJ, Cooper GF, Hochheiser H, Visweswaran S.
Presented at University of Michigan—University of Pittsburgh Collaborative Scholarship Meeting. Cleveland, OH. May 2017.
(poster)

Eye-tracking for clinical decision support: A method to capture automatically what physicians are viewing in the EMR.
King AJ, Hochheiser, H, Visweswaran, S, Clermont, G, Cooper, GF.
In: AMIA Joint Summits Translational Science Proceedings. 2017 Mar 27-30; 2017:512-21.
(Awarded First Place in the Student Paper Competition at the AMIA Joint Summits Clinical Research Informatics, 2017)
(abstract) (paper)

Rethinking the EMR.
King AJ.
Presented at the Critical Care Medicine CRISMA (Clinical Research, Investigation, and Systems Modeling of Acute illness) Weekly Research Conference. University of Pittsburgh Department of Critical Care Medicine, Pittsburgh PA. Feb 2017.
(presentation)

Using a low cost eye tracking device to automatically label information usage patterns.
King AJ, Cooper GF, Hochheiser H, Visweswaran S.
Presented at DBMI Annual Training Program Retreat. University of Pittsburgh Department of Biomedical Informatics, Pittsburgh, PA. Aug 2016.
(poster)

Development and preliminary evaluation of a prototype of a learning electronic medical record system.
King AJ, Cooper, GF, Hochheiser, H, Clermont, G, Visweswaran, S.
In: AMIA Annual Symposium Proceedings. 2015 Nov 17; 2015:1967-75.
(Awarded First Place in the Student Paper Competition at the AMIA Annual Symposium, 2015)
(abstract) (paper)

Training a Learning Electronic Medical Record.
King AJ, Cooper GF, Hochheiser H, Visweswaran S.
Presented at DBMI Annual Training Program Retreat. University of Pittsburgh Department of Biomedical Informatics, Pittsburgh, PA. Aug 2015.
Best poster
(poster)

Development and evaluation of a prototype of a Learning Electronic Medical Record System.
King AJ, Cooper GF, Hochheiser H, Visweswaran S.
Presented at NLM Informatics Training Conference. NIH, Bethesda MD. Jun 2015.
(poster)