(HealthDay News) — Algorithms that combine Internet of Things (IoT) technologies and in-home sensory devices with machine learning techniques can be used to monitor the health and well-being of people with dementia, according to a study published online in PLOS ONE.

Shirin Enshaeifar, PhD, from the University of Surrey in the United Kingdom, and colleagues introduced a systematic approach to provide more effective and preventive care for patients with dementia living at home. IoT technologies and in-home sensory devices were combined with machine learning techniques to monitor health and well-being.

The researchers designed an algorithm to detect urinary tract infection (UTI), which represents one of the main causes of hospital admission in dementia patients. The algorithm was developed using a Non-negative Matrix Factorization technique, which extracted latent factors from raw observation and used them for clustering and identifying potential cases of UTI. Early symptoms of cognitive or health decline were identified using an algorithm that detected changes in activity patterns to provide personalized and preventive care services. An Isolation Forest technique was used to create a holistic view of patterns of daily activity.

“We have developed a tool that is able to identify the risk of UTIs so it is then possible to treat them early,” a coauthor said in a statement. “We are confident our algorithm will be a valuable tool for health care professionals, allowing them to produce more effective and personalized plans for patients.”

Related Articles

Reference

Enshaeifar S, Zoha A, Skillman S, et al. Machine learning methods for detecting urinary tract infection and analysing daily living activities in people with dementia. PLoS One. DOI:10.1371/journal.pone.0209909