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 low to high risk of departure.
The top four factors that predicted departure risk were how long the physician had been employed, their age, the complexity of their cases and the demand for services.
"As physician burnout is an increasingly recognized problem, healthcare systems, hospitals, and large groups need to figure out what they need to do to ensure the emotional and physical health and well-being of the physicians and other clinicians who do the actual caring for patients," Robert McLean, MD, medical director of Northeast Medical Group, said in a news release from New Haven, Conn.-based Yale . "Many healthcare systems already have wellness officers and wellness committees who could have the responsibility of collecting and analyzing this data and developing conclusions, which then would lead to implementation plans for changes and hopefully improvements."