Related Experiment Video
Updated: Jul 27, 2026
12:18
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
7.4K
Qualitative Verification of Machine Learning-Based Burnout Predictors in Primary Care Physicians: An Exploratory
Daniel Tawfik1, Stefanie S Sebok-Syer2, Cassandra Bragdon3
1Department of Pediatrics, Stanford University School of Medicine, Palo Alto, California, United States.
Applied Clinical Informatics
|April 28, 2025
Summary
Electronic health record (EHR) usage measures can predict physician burnout, but qualitative insights reveal significant messaging and documentation burdens impacting primary care physicians. Addressing these EHR-related work burdens is key to improving physician well-being.
Area of Science:
- Medical Informatics
- Primary Care Medicine
- Physician Well-being
Background:
- Electronic health record (EHR) usage metrics can quantify physician activity and identify burnout risk.
- However, the relationship between EHR usage and physicians' lived experiences remains unclear.
Purpose of the Study:
- To investigate primary care physicians' EHR-related experiences and well-being.
- To compare these experiences with EHR usage metrics linked to burnout prediction via machine learning.
Main Methods:
- Qualitative study utilizing semi-structured interviews with primary care physicians and clinic managers.
- Analysis of clinics with varying burnout scores and changes over time (2020-2022).
- Inductive and deductive coding focused on patient load, documentation, messaging, orders, and physician distress/fulfillment.
Main Results:
- Physicians face high messaging and documentation burdens, exceeding available work hours.
- EHR burdens, despite challenges, also offer patient care benefits.
- Staffing shortages and turnover intensify workload demands, contributing to burnout.
Conclusions:
- Quantifiable EHR work burdens are significant sources of distress for primary care physicians.
- Organizational recognition, adequate staffing, and support are crucial for mitigating EHR-related burdens and reducing burnout.
