Smartwatch app could maximise stroke recovery

 Tracking social contacts does NOT aid recovery. You need to provide 100% recovery, so survivors feel confident in social situations. Does no one in stroke know how to think about survivor recovery?

Smartwatch app could maximise stroke recovery

A smartwatch app that tracks social contact in hospitalised stroke survivors may aid recovery, new research suggests.

Researchers developed SocialBit, a machine learning app for Android smartwatches that detects social interactions in people with and without neurological conditions.

It is currently available only for research use.

Speech and language problems after stroke are common, including dysarthria, which affects speech muscles, and aphasia, which impairs language. Socialising is linked with better recovery.

In prior work, lead author Amar Dhand found socially isolated stroke survivors had worse outcomes at three and six months.

He said: “We created a tracker of social life customised for stroke survivors.

“Tracking human engagement is crucial, and social isolation can now be identified in real-world situations.

“This may be addressed by notifying the patient, family members, caregivers and health care professionals of social isolation.”

Dhand is an associate professor of neurology in the division of stroke and cerebrovascular disorders at Mass General Brigham in Boston.

The study recruited 153 adults during hospitalisation for ischaemic stroke.

Participants wore an Android smartwatch running SocialBit from 9 a.m. to 5 p.m. daily for up to eight days, some after transfer to a rehabilitation hospital.

The app logged minutes of social interaction using acoustic patterns of the participant or another person talking.

At the same time, human observers reviewed livestream video and recorded minute-by-minute interactions.

Compared with human observers, SocialBit was 94 per cent as accurate at recognising social interactions, and 93 per cent in people with aphasia.

Performance held up despite TV noise, side conversations, different settings and across Android watch models.

Greater stroke severity was linked with less social time, with about a 1 per cent drop in total interaction minutes for each 1-point rise on the NIH Stroke Scale, a standard measure of stroke severity.

Dhand said: “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.

“The SocialBit app may also help people recover from brain injuries. It can support therapies like speech, occupational and exercise therapy.”

Future studies could use SocialBit to flag patients at risk of social isolation in hospital and after discharge, and to examine links with depression and other post-stroke mental health changes. Researchers also plan to test it in other brain injuries and healthy ageing.

One limitation was that detailed social-interaction assessments were conducted only in hospital or rehabilitation settings.

Commenting on potential uses, stroke specialist Cheryl Bushnell said: “This research is fascinating in its capture of social interactions, which I presume can distinguish between conversations from case managers, nurses, therapists and the care team from non-hospital personnel.

“If not, then the amount of social interaction could be dependent on the size of the care team, or the nurse-to-patient ratio.

“If the app does distinguish hospital from non-hospital personnel, then distance from the hospital and the number of family and friends become major factors.

“Regardless, 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.”