Algorithm Provides Insights into Physician Turnover Trends

Using an algorithm, Weill Cornell Medicine researchers discovered that the period from 2010 to 2018 resulted in a 43 percent increase in physician turnover, highlighting the need to determine the reasons for this trend and ultimately improve retention rates.

Regardless of whether it is due to mobilization or retirement, physician turnover is a common issue that often impacts patients. Because of this, understanding it is critical.

“It is important to study turnover because it can hurt the continuity and quality of patients [sic] care,” said study author Lawrence Casalino, MD, PhD, professor emeritus of population health sciences at Weill Cornell Medicine, in a press release.  “There’s a lot of mutual trust that builds between a doctor and patient over time that’s difficult to replace.”

Casalino and a group of researchers created a method to measure turnover between 2010 and the initial three quarters of 2020. The primary data source they used to create this algorithm was the Medicare Data on Provider Practice and Specialty (MD-PPAS), which contains information on clinician characteristics, including age, sex, and specialty.

Between 2010 and 2018, the turnover rate jumped by 43 percent. Over the eight-year period, the annual turnover rate ranged from 5.3 to 7.6 percent. Although researchers do not know the reasoning behind this increase, they have further details surrounding the trend.

The period from 2010 to 2014 marked the most noticeable turnover rate, largely due to providers halting their practices. Despite the absence of data alluding to why, there is a suspicion that the growth of EMRs had an effect.

“As we speculate in the article, those were the years when the electronic medical record became a requirement,” said Casalino. “Some prior studies have suggested a link between electronic health record use and physician burnout, and it may be that burned out physicians are more likely to stop practicing or move to another practice.”

From 2014 to 2017, rates of turnover were stable but then increased slightly in 2018. However, the rates were slightly lower during the second and third quarters of 2020 compared to the same quarters in 2019.

The algorithm also allowed researchers to understand the physician characteristics that potentially contribute to turnover.

They found that providers from rural areas were more likely to move or stop practicing compared to urban providers. Female physicians, those in larger practices, and those who cared for more Medicare- and Medicaid-eligible patients were also more prone to turnover.

Further, although there was a suspicion that turnover did not necessarily rise in the early stages of the COVID-19 pandemic, the coming years will help to determine pandemic-related impacts on turnover.

Similar efforts have also aimed to gather insight into physician turnover through new methods.

A study from Yale University in February shared details regarding the creation of a machine-learning model that aimed to provide researchers with insights into physician turnover. This effort aimed to use data for developing interventions, ultimately improving retention rates.

Researchers used three years’ worth of EHR data to review behavioral patterns and discover trends. Their goal was to determine whether they could use a three-month period of information to determine physician departure within the following six months.

Using data from 319 physicians, researchers focused on various measures. They found that the model was 97 percent accurate in predicting physician departure and achieved a sensitivity of 64 percent and a specificity of 79 percent. Alongside this success rate, the model also showed the ability to help identify factors that may be a cause of turnover risk.