AI and robots could help detect urinary tract infections earlier
It’s a high-tech approach to a long-standing problem. Women are more than three times more likely to develop UTIs than men, but UTI symptoms vary, and it can take days to get a reliable diagnosis. Meanwhile, physical discomfort may persist and complications may arise.
Everything from urinary pain and incontinence to temperature changes and confusion can indicate a UTI, and patients awaiting diagnosis can progress to urosepsis, in which the infection spreads from the urinary tract to the bladder and kidneys.
UTIs are particularly common in nursing homes and hospitals due to catheter use, and are one of the most common hospital-acquired infections.
They are also common, even among those who do not use catheters; more than 50 percent of women will get a UTI during their lifetime. Women are much more likely to develop UTIs than men because the female urinary tract is close to the anus.
The project will place sensors and socially supportive robots with people living in care homes. The sensors will monitor possible signs of infections, including changes in walking function or sleep patterns. If the program’s AI-powered platform detects those signs, it will trigger interactions with the robot and, ultimately, a clinician.
The researchers hope that the program can help fight antibiotic overuse.
“As the second most common reason for prescribing antibiotics, the infection makes a significant contribution to the increasingly worrying problem of drug-resistant bacteria,” Kia Nazarpour, the project leader and a professor of digital health at the University of Edinburgh’s School of Informatics, said in a news release. Since lab results can take up to two days to come in, clinicians often start patients on antibiotics right away.
In the United States alone, UTI hospitalizations cost an estimated $2.8 billion annually.
