For the study, researchers from the University of Surrey in England placed sensors in the homes of 53 dementia patients for at least 30 days to gather environmental data.
Researchers then used a technique called Non-negative Matrix Factorization to analyze the data for latent factors associated with UTIs. This information, combined with machine learning algorithms, allowed them to identify early UTI symptoms.
“We have developed a tool that is able to identify the risk of UTIs … allowing [clinicians] to produce more effective and personalized plans for patients,” Payam Barnaghi, PhD, professor of machine intelligence at University of Surrey, said in a press release.
More articles on clinical leadership and infection control:
How detecting false penicillin allergies helps physicians fight antibiotic resistance
San Francisco General nurse: Why I’m against naming hospital after Mark Zuckerberg
84% of patients receive antibiotics for infection-like symptoms, survey finds
