A new study in South Korea suggests that an AI-powered home monitoring system using contactless Internet of Things sensors could flag the elevated risk of stroke among solo-living seniors by identifying relevant behavioural patterns.
The team analysed more than 13,000 data points collected over 14 days, including data on physical activities, periods of inactivity, sleep patterns, and indoor conditions, captured by motion, door, and temperature and humidity sensors.
Findings reported in an early-access paper in npj Digital Medicine showed that the best-performing AI model, TabNet, achieved an AUPRC of 85% in identifying the prodromal group and an AUROC of 91% in distinguishing previously diagnosed participants from those with no history of cerebrovascular disease.
The research team said that the findings suggest the AI-powered contactless home monitoring could eventually complement clinical assessment by helping identify potential warning signs earlier, particularly among older adults living alone who may not immediately recognise changes in their health.
【MORE】