An Adaptive Tutor for Improving Visual Diagnosis
Principal Investigator: Martin V. Pusic, MD, PhD
An Adaptive Tutor for Improving Visual Diagnosis, a two-year project funded by the U.S. Department of Defense, aimed to create an adaptive tutor that determines the baseline proficiency of individuals interpreting electrocardiograms, or ECGs, and then tailored case-based learning until reliable competency was achieved.
The research project had several objectives:
- to assemble an online ECG library from authentic field cases collected from an emergency department
- to develop ontologic and statistical models of the ECG cases to inform the rational design of the adaptive learning system
- to develop an evidence-based learning adaptation algorithm to ensure efficient and reliable development of skills at scale
NYU Langone Co-Investigators
Jennifer Hill, PhD
Jeffrey Lorin, MD
Barry Rosenzweig, MD
Silas Smith, MD
Marc Triola, MD
Collaborative Co-Investigators
David Cook, MD, Mayo Clinic
Rose Hatala, MD, University of British Columbia
Matthew Lineberry, PhD, University of Kansas Medical Center
Project Personnel
Greta Elysée, Program Coordinator
Eric Feng, Programmer
Ilan Reinstein, Data Scientist
diagnostic ECG cases to be added to an online library
healthcare professionals, including physicians, residents, and more, to be recruited
medical schools collaborating on this project (3 in the United States and 1 in Canada)