AI Model Predicts Prolonged Sitting in Chronic Pelvic Pain

Chronic pelvic pain affects an estimated one in seven women and can occur with conditions such as endometriosis, adenomyosis, or uterine fibroids. Pain, fatigue, and other symptoms may contribute to prolonged sitting, while general advice to sit less may not reflect the challenges of living with these conditions. Recognizing the need for more individualized support, researchers have developed an approach that uses wearable data to predict when prolonged sitting is likely to occur.

At the Icahn School of Medicine at Mount Sinai (New York, NY, USA), researchers developed personalized artificial intelligence (AI) models to forecast activity levels one hour ahead. Wearable devices collected minute-by-minute information about physical activity, heart rate, and sleep. The researchers tested whether the forecasts could identify upcoming 15-minute periods of sedentary behavior during waking hours. Such forecasts could eventually help time a reminder to stand or take a short walk.

The team analyzed data from 134 women with chronic pelvic pain disorders, primarily endometriosis, and 61 healthy participants in a comparison group. Participants wore Fitbit devices for up to 90 days, with approximately 10 days of data from each individual used to train personalized forecasting models.

Relatively simple, interpretable models predicted prolonged sitting as accurately as the more computationally intensive deep-learning approaches evaluated in the study. The models also remained robust when wearable data were incomplete. The findings were published online on September 30, 2026, in npj Women’s Health.

The researchers are now working to incorporate the forecasting framework into a just-in-time adaptive intervention. Future work will test whether personalized, AI-guided movement prompts can reduce sedentary time and improve symptoms. Prospective clinical trials will still be needed to determine whether the approach improves symptoms and quality of life.

“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,” said Ipek Ensari, Ph.D., assistant professor of artificial intelligence and human health at the Icahn School of Medicine and a member of the Hasso Plattner Institute of Digital Health at Mount Sinai.

Related Links
Icahn School of Medicine at Mount Sinai