Researchers at the Icahn School of Medicine at Mount Sinai have developed an artificial intelligence approach that uses wearable-device data to forecast periods of prolonged sitting in women with chronic pelvic pain disorders.
The research, published online September 30 in npj Women’s Health, could eventually support personalized digital health systems that prompt individuals to move shortly before an extended sedentary period begins.
Chronic pelvic pain affects an estimated one in seven women and can occur alongside conditions including endometriosis, adenomyosis and uterine fibroids.
Pain, fatigue and other symptoms associated with those conditions can contribute to prolonged periods of sitting, while standard recommendations to increase physical activity may not account for the daily realities of patients living with chronic pain.
Mount Sinai researchers examined whether wearable devices could go beyond retrospectively counting activity and instead predict when sedentary behavior was likely to occur.
The team analyzed data from 134 women with chronic pelvic pain disorders, primarily endometriosis, along with 61 healthy participants serving as a comparison group.
Participants wore Fitbit devices for up to 90 days, generating minute-by-minute information about physical activity, heart rate and sleep.
Using approximately 10 days of data for each participant, researchers trained personalized models to forecast activity levels one hour into the future.
They then evaluated whether those forecasts could identify upcoming 15-minute sedentary periods during waking hours, creating an opportunity for a brief movement break that researchers referred to as an “exercise snack.”
The study found that relatively simple and interpretable models predicted prolonged sitting as accurately as the more computationally demanding deep-learning approaches evaluated by the team.
That finding could make future systems more practical to run directly on a smartphone or wearable device rather than relying on remote computing infrastructure.
On-device processing could also reduce the amount of sensitive health information that needs to be transmitted elsewhere.
Researchers found that the models continued performing under conditions involving incomplete wearable data, which can occur when users remove devices or fail to synchronize them.
The team is now working to integrate the forecasting framework into a just-in-time adaptive intervention.
Future clinical trials will examine whether personalized AI-guided movement prompts can actually reduce sedentary behavior, improve symptoms and enhance quality of life in women with chronic pelvic pain disorders.
Researchers also believe the approach could eventually apply to other chronic conditions where prolonged sitting contributes to poorer health outcomes.
KEY QUOTES:
“Our goal was to determine whether everyday wearable devices could serve as an early-warning system for prolonged sitting in women living with chronic pelvic pain. Rather than offering generic advice after the fact, we wanted to determine whether we could anticipate these moments and support people with simple, well-timed prompts that fit naturally into their daily lives.”
“This study suggests that predicting prolonged sitting is feasible, even if the individual has chronic conditions that might impact their daily routine. The next step is determining whether delivering personalized movement prompts based on those predictions actually helps reduce sedentary time, improves symptoms, and enhances quality of life. Those questions will require prospective clinical trials.”
Ipek Ensari, Ph.D., Assistant Professor of Artificial Intelligence and Human Health at the Icahn School of Medicine at Mount Sinai
“We were surprised by how well the simplest models performed. More complex AI is not always better. Lightweight, interpretable models can accurately forecast sedentary behavior while being practical enough to run directly on a person’s own device, which also helps protect privacy.”
Jannes Jegminat, Ph.D., Former Postdoctoral Research Fellow at the Icahn School of Medicine at Mount Sinai
