A smartwatch application that measures social interactions among hospitalized stroke survivors may enable new treatments to preserve or enhance cognition, social engagement and quality of life after a stroke, according to a preliminary study to be presented at the American Stroke Association’s International Stroke Conference 2026. The research highlights how a machine learning algorithm called SocialBit, compatible with Android smartwatches, can detect social interactions through sounds in the environment, measuring interaction levels among stroke survivors in hospital settings.
Social interaction is known to support brain health and recovery after neurological injury. This technology could support strategies focused on strengthening social ties, which may lead to improved physical recovery and quality of life, even among stroke survivors with language difficulties. According to the American Stroke Association, the loss or change in speech and language profoundly alters the social life of stroke survivors. Yet, research has shown that socializing is one of the best ways to maximize recovery after a stroke.
Study lead author Amar Dhand, M.D., D.Phil., an associate professor of neurology at Mass General Brigham, noted that previous research demonstrated stroke survivors who are socially isolated have worse physical outcomes at 3 and 6 months after a stroke. "We created a tracker of social life customized for stroke survivors. Tracking human engagement is crucial, and social isolation can now be identified in real-world situations," Dhand said. This may be addressed by notifying the patient, family members, caregivers and health care professionals of social isolation.
In the study, 153 adults hospitalized for ischemic stroke wore a smartwatch with the SocialBit app in their rooms between 9 a.m. to 5 p.m. daily for up to 8 days. The app logged socialization time according to acoustic patterns indicating speech. Compared with human observers watching livestream video, SocialBit was 94% as accurate in recognizing social interactions. In patients with aphasia, SocialBit maintained accuracy at 93%. Its performance remained consistent despite TV noise, side conversations, different environments and across various Android smartwatch models.
Participants who had a more severe stroke had less social interaction, with about a 1% drop in total social interaction minutes for each 1-point increase on the NIH Stroke Scale. "I was surprised by how well the app performed for people with aphasia. We used SocialBit to capture sounds instead of words to protect privacy, and this feature ended up being helpful for people with limited language skills," Dhand said. He added that the SocialBit app may also help people recover from brain injuries by supporting therapies like speech, occupational and exercise therapy.
Future research could use SocialBit to measure how many people are at risk for social isolation while in the hospital and after they leave. It could also explore how this isolation is related to depression and other mental health changes that can happen after a stroke. "We can also test if this app can help with other brain injuries and in healthy aging to keep and improve brain health over time," Dhand said. One limitation was that detailed evaluations were only tested in hospital or rehabilitation settings.
Cheryl Bushnell, M.D., M.H.S., FAHA, chair of the American Heart Association Stroke Council, said, "This research is fascinating in its capture of social interactions. There are multiple interesting ways this app could be used in future studies, including measures of quality of hospital care and social interactions at rehab facilities and nursing homes." Bushnell, who was not involved in the study, noted the app's potential to distinguish between conversations from hospital personnel and non-hospital personnel, which could affect interpretation of social interaction data.
The study involved participants hospitalized at Brigham and Women’s Hospital between June 2021 and March 2025. No participants were in intensive care units where visitation was restricted. Some patients were moved to Spaulding Rehabilitation Center during assessment. Participants were excluded if receiving end-of-life care, had prior dementia diagnosis, or lacked English proficiency for informed consent. According to the American Heart Association’s 2026 Heart Disease and Stroke Statistics, stroke is now the #4 leading cause of death in the U.S. The abstract is available in the American Stroke Association International Stroke Conference 2026 Online Program Planner.
