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

12/11/2019

∙

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 this end, 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 affect performance, with linear models performing as well as neural networks.

READ FULL TEXT

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

Language models are susceptible to incorrect patient self-diagnosis in medical applications

This Patient Looks Like That Patient: Prototypical Networks for Interpretable Diagnosis Prediction from Clinical Text

Unsupervised Online Feature Selection for Cost-Sensitive Medical Diagnosis

Auto-Classification of Retinal Diseases in the Limit of Sparse Data Using a Two-Streams Machine Learning Model

Convolutional Neural Networks for Medical Diagnosis from Admission Notes

Empirical Optimal Risk to Quantify Model Trustworthiness for Failure Detection

COVID-19 in differential diagnosis of online symptom assessments

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

Related Research

Language models are susceptible to incorrect patient self-diagnosis in medical applications

This Patient Looks Like That Patient: Prototypical Networks for Interpretable Diagnosis Prediction from Clinical Text

Unsupervised Online Feature Selection for Cost-Sensitive Medical Diagnosis

Auto-Classification of Retinal Diseases in the Limit of Sparse Data Using a Two-Streams Machine Learning Model

Convolutional Neural Networks for Medical Diagnosis from Admission Notes

Empirical Optimal Risk to Quantify Model Trustworthiness for Failure Detection

COVID-19 in differential diagnosis of online symptom assessments