There is a web app for that: Artificial intelligence (AI) monitors urological health using the sounds of urine streams

There is a web app for that: Artificial intelligence (AI) monitors urological health using the sound ...

According to a press release released on July 2nd, an artificial intelligence (AI) algorithm can now listen to patients pass urine in order to accurately and efficiently identify abnormal flows and the corresponding health conditions. The deep learning tool is named Audioflow, and it has thus far performed approximately as well as a specialist machine used in clinics and provided similar results to urology residents.

Evaluating the sound produced by urine

"There is a trend towards using machine learning in many fields because clinicians do not have a lot of time." At the same time, particularly since the epidemic, there is a shift towards telemedicine and less hospital-based care, according to Dr. Lee Han Jie from Singapore General Hospital, the study's lead.

Researchers want to develop a self-sufficient app that patients can use to monitor themselves at home. Current uroflowmetry is efficient at assessing urinary-related conditions, but requires that patients urinate into a machine during outpatient visits.

The COVID-19 epidemic has restricted access to clinics. Han Jie and his colleagues desired to develop a more cost-effective way to monitor urine at home without any medical assistance and therefore they sought the help of the engineering department to develop a urine-assessing algorithm.

Between December 2017 and July 2019, the researchers recruited 534 male participants. Participants used a regular uroflowmetry device in a soundproofed room and recorded their urine using a smartphone.

Results that exceeded professional expectations

The AI was able to analyze flow rate, volume, and time accurately using a mere 220 recordings, all of which can indicate an obstruction or bladder disease.

"Our AI can outperform some non-experts and comes close to senior consultants," said Han Jie. "The real benefit is having a consultant in the bathroom with you every time you go. We are currently working on the algorithm being able to operate when there is background noise in the normal home environment, and this will make the real difference for patients."

Audioflow achieved levels of agreement comparable to a conventional uroflowmetry machine and a panel of six urology residents. For over 80% of recordings, the AI obtained results that were in line with conventional uroflowmetry, and, compared to the specialist urologists, achieved an 84% rate of agreement.

Researchers are hopeful that the new artificial intelligence (AI) would soon work wonders in home environments.

Audioflow will soon be released as a smartphone app to be tested in a real and very noisy environment. It does however have one drawback: it has so far only been tested on male urinary flow, which is different from the female one. Is there a possibility of a female-focused version?

You may also like: