Oral Presentations

The accuracy vs. coverage trade-off in patient-facing diagnosis models

4:57 PM–5:15 PM Mar 23, 2020 (America - Chicago)



Programmatic Theme: Informatics Implementation

Abstract: A third of adults in America use the Internet to diagnose medical concerns, and online symptom checkers are increasingly part of this process. These tools are powered by diagnosis models similar to clinical decision support systems, with the primary difference being the coverage of symptoms and diagnoses. To be useful to patients and physicians, these models must have high accuracy while covering a meaningful space of symptoms and diagnoses. To the best of our knowledge, this paper is the first in studying the trade-off between the coverage of the model and its performance for diagnosis. To study this trade-off, we learn diagnosis models with different coverage from EHR data. We find a 1\% drop in top-3 accuracy for every 10 diseases added to the coverage. We also observe that complexity for these models does not matter, with linear models doing as well as neural networks.

Learning Objective: Formulate research hypotheses and projects related to informatics and the health data sciences based on existing datasets or on the aggregation of data from disparate sources;

Demonstrate multidisciplinary collaborations in the biomedical research and clinical community to expand access to diverse expertise, sophisticated technologies, and unique tools and resources;


Anitha Kannan (Presenter)

Jason Fries, Stanford University
Eric Kramer, Curai
Jen Jen Chen, Curai
Nigam Shah, Stanford University
Xavier Amatriain, Curai

Keywords, Themes & Types