Diagnosing Physician Error: A Machine Learning Approach to Low-Value Health Care

61 Pages Posted: 20 Aug 2019 Last revised: 15 Apr 2022

See all articles by Sendhil Mullainathan

Sendhil Mullainathan

University of Chicago

Ziad Obermeyer

University of California, Berkeley

Date Written: August 2019

Abstract

How effective are physicians at diagnosing heart attacks? To answer this question, we contrast physician testing decisions with a machine learning model of risk. When the two deviate, we use actual health outcome data to judge whether the algorithm or the physician was right. We find physicians over-test: tests that are predictably useless are still performed. At the same time, physicians also under-test: many predicted high-risk patients are untested and then suffer adverse health events (including death) at high rates. A natural experiment using shift-to-shift testing variation confirms these findings: increasing testing improves health and reduces mortality, but only for patients flagged as high-risk by the algorithm. The simultaneous existence of over- and under-testing cannot easily be explained by incentives alone, and instead suggests errors. We provide suggestive evidence on the psychology behind these errors: (i) physicians use too simple a model of risk, suggesting bounded rationality; (ii) they over-weight salient information; and (iii) they over-weight symptoms that are representative or stereotypical of heart attack. Together, these results suggest the need for health care models and policies to incorporate not just physician incentives, but also physician mistakes.

Suggested Citation

Mullainathan, Sendhil and Obermeyer, Ziad, Diagnosing Physician Error: A Machine Learning Approach to Low-Value Health Care (August 2019). NBER Working Paper No. w26168, Available at SSRN: https://ssrn.com/abstract=3439178

Sendhil Mullainathan (Contact Author)

University of Chicago ( email )

1101 East 58th Street
Chicago, IL 60637
United States

Ziad Obermeyer

University of California, Berkeley ( email )

310 Barrows Hall
Berkeley, CA 94720
United States

Do you want regular updates from SSRN on Twitter?

Paper statistics

Downloads
65
Abstract Views
428
rank
455,299
PlumX Metrics