Becker's Healthcare February 2, 2023
Yale researchers found a machine-learning program could predict which physicians would leave the job and identified four variables that lead to high departure risk.
The study, published Feb. 1 in the journal PLOS One, analyzed electronic health records for 319 physicians representing 26 medical specialities over a 34-month period. Data included time physicians spent using EHRs, clinical productivity measures such as patient volume, and physician demographics, including age and length of employment. During the analysis period, 13.8 percent of physicians departed.
The machine-learning model was able to predict which physicians would depart within six months with 97 percent accuracy. The AI also identified how strongly different variables contributed to turnover risk and what variables changed when a physician transitioned from...