AI Tool Predicts Prolonged Sitting In Women With Pelvic Pain, Promotes Activity

WEDNESDAY, Oct. 7, 2026 (HealthDay News) — Women with chronic pelvic pain disorders often find it more comfortable to sit for longer spells — easing their pain but potentially harming their overall health.

Now, a newly developed AI tool can forecast when women with pelvic pain might be at risk of sitting for prolonged periods and prompt them before it happens. The findings were recently reported in the journal npj Women’s Health.

Using the AI program, smartphones or smartwatches might one day encourage women to get up and take a short walk at ideal times, researchers said.

"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," senior researcher Ipek Ensari said. She is an assistant professor of artificial intelligence and human health at the Icahn School of Medicine at Mount Sinai in New York City. 

"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,” she said in a news release.

About 1 in 7 women are affected by chronic pelvic pain, which is linked to conditions like endometriosis and uterine fibroids, researchers said in background notes.

For the study, researchers analyzed Fitbit data from 134 women with chronic pelvic pain, primarily endometriosis, and 61 healthy volunteers. They gathered minute-by-minute info about physical activity, heart rate and sleep for up to 90 days for each woman.

The research team then trained the AI to forecast women’s activity levels one hour ahead using about 10 days of data from each participant. From there, researchers narrowed that window to predict 15-minute periods of sedentary behavior during waking hours.

Those 15-minute periods would be an ideal brief movement break that researchers called an “exercise snack.” The goal was to build a tool that could prompt women to walk or stand before they sat for a long period of time, researchers said. 

"We were surprised by how well the simplest models performed," lead researcher Jannes Jegminat said. He is a former postdoctoral research fellow at the Icahn School of Medicine at Mount Sinai.

"More complex AI is not always better,” Jegminat said in a news release. “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."

These simpler AI models could easily function on a person’s phone, smartwatch or wearable, researchers said.

Ultimately, they could form the basis for digital health tools that feel more like a personalized coach than an insufferable AI, researchers said. The AI would deliver a few meaningful prompts each day while minimizing annoying notifications that often cause people to tune out.

"This study suggests that predicting prolonged sitting is feasible, even if the individual has chronic conditions that might impact their daily routine," Ensari said. "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."

More information

The Mayo Clinic has more on chronic pelvic pain.

SOURCE: Mount Sinai, news release, Sept. 30, 2026