Machine learning predicts MS mental health during stay-at-home orders

A Carnegie Mellon researcher and colleagues used data from smartphones and fitness trackers to create machine learning models to predict depression, fatigue, poor sleep quality and worsening multiple sclerosis symptoms in plates.

Researchers have developed a machine learning model that can accurately predict how stay-at-home orders, such as those during the COVID-19 pandemic, affect the mental health of people with multiple sclerosis (MS).

Mayank Goel, MS, Ph.D., head of the Smart Sensing for Humans (SMASH) lab and associate professor at Carnegie Mellon University in Pittsburgh, developed the model, which was described in a recent article in the Journal of internet medical research. Goel has worked with colleagues from Carnegie Mellon, the University of Pittsburgh and the University of Washington.

Before the pandemic began, the initial research question was whether digital data from smartphones and fitness trackers of people with MS could predict clinical outcomes. In March 2020, when study participants were required to stay home, their daily behaviors were significantly altered, a press release said.

“The research team realized that the data collected could shed light on the effect of stay-at-home orders on people with MS,” the press release reads.

They used passively collected sensor data from smartphones and fitness trackers to create machine learning models to predict depression, fatigue, poor sleep quality and worsening of MS symptoms during pregnancy. unprecedented period of stay at home.

“This presented us with an exciting opportunity. If we look at data points before and during the stay-at-home period, can we identify factors that signal changes in the health of people with MS?” Goel said in the press release.

The research team collected data passively for three to six months, collecting information such as the number of calls to participants’ smartphones and the duration of those calls; the number of missed calls; and participants’ location and screen activity data. They also collected heart rate, sleep information, and step count data from their fitness trackers.

People with MS can suffer from several chronic comorbidities, which allowed the team to test whether their model could predict adverse health effects such as severe fatigue, poor sleep quality and worsening of symptoms. MS – in addition to depression, the press said.

“Building on this study, the team hopes to advance precision medicine for people with MS by improving early detection of disease progression and implementing targeted interventions based on digital phenotyping,” according to the press release.

The research could also help inform policymakers tasked with issuing future stay-at-home orders or other similar responses during pandemics or natural disasters. “When the initial COVID-19 stay-at-home orders were issued, there were early concerns about its economic impacts, but only a belated appreciation of the mental and physical health consequences for people – especially among populations. vulnerable such as those with chronic neurological diseases. conditions,” the press release reads.

“We were able to capture people’s change in behavior and accurately predict clinical outcomes when they are forced to stay home for long periods of time,” Goel said in the press release. “Now that we have a working model, we could assess who is at risk for worsening mental health or physical health, inform clinical triage decisions, or shape future public health policy.”

Sherry J. Basler