PULLMAN, Wash. — Washington State University (WSU) researchers have developed an innovative method using smartwatches to monitor everyday activities such as working, eating and running errands.
The team’s work, published in the IEEE Journal of Biomedical and Health Informatics, could enhance understanding of cognitive health and disease management by using a computer algorithm and a vast dataset from smartwatches that accurately identifies daily activities 78% of the time, WSU said in a release.
Diane Cook, a WSU Regents Professor, emphasized the importance of this technology: “If we want to determine whether somebody needs caregiving assistance in their home or elsewhere and what level of assistance, then we need to know how well the person can perform critical activities.”
This development addresses a significant challenge in healthcare: assessing the management of daily activities for the sick or elderly. Comprehensive data on how individuals handle tasks such as paying bills or cooking is crucial for health assessments, WSU said.
“Lack of awareness of a person’s cognitive and physical status is one of the hurdles that we face as we age,” Cook said, citing the new method offers a potential solution by automating indicators of cognitive and physical status, thus promoting independence.
WSU said the researchers collected data over eight years from 503 participants, using self-reported activities to train their AI model. This model predicted activities with nearly 78% accuracy, utilizing more than 32 million data points.
Cook noted, “A foundational step is to perform activity recognition because if we can describe a person’s behavior in terms of activity in categories that are well recognized, then we can start to talk about their behavior patterns and changes in their patterns.”
