This new AI assesses both urine flow and doctors

An artificial intelligence (AI) algorithm can now listen to patients urinate to successfully and efficiently identify abnormal flows and corresponding health problemsaccording to a press release published on July 2. The deep learning tool is aptly called Audioflow and so far has performed almost as well as a specialist machine used in clinics and offers comparable results for urological residents.

Evaluation of the sound made by urine

“There is a trend towards using machine learning in many areas because clinicians don’t have a lot of time. At the same time, especially since the pandemic, there has been a shift towards telemedicine and less hospital-based care. We were eager to develop a way to educate our patients. to see how they fare in between hospital visits,” says Dr. Lee Han Jie of Singapore General Hospital, who led the study.

The current algorithm evaluates the sound of urine produced in a soundproof environment, but researchers hope to develop an app that is self-sufficient enough so that patients can monitor themselves at home. current uroflowmetry is effective in assessing urinary-related conditions, but requires patients to urinate into a machine during outpatient visits.

However, the COVID-19 pandemic has limited access to clinics. Han Jie and colleagues wanted to develop a more effective way to assess urine at home without medical assistance, so they enlisted the help of the engineering department to develop a urine assessment algorithm.

To train and validate this algorithm, they recruited 534 male participants between December 2017 and July 2019. The process was quite simple: participants used the usual uroflowmetry machine in a soundproof room and recorded their urination with a smartphone.

Results that matched professional results

Using just 220 recordings, the AI ​​learned to accurately evaluate flow rate, volume and time, all of which together could indicate an obstruction or bladder problems.

“Our AI can outperform some non-experts and come close to senior consultants,” explains Han Jie. “But the real benefit is that you have the equivalent of a consultant in the bathroom every time you go. We are now working on making the algorithm work when there is background noise in the normal home environment, and this will be the real difference for patients.”

Indeed, Audioflow produced results that could compete with a conventional uroflowmetry machine and a panel of six urology residents. The AI ​​produced conclusions in agreement with conventional uroflowmetry for more than 80% of the admissions and, compared to the specialist urologists, it reached an agreement of 84%.

Now the researchers hope the new AI can do that quickly turn out to be beneficial in home settings.

Audioflow will soon be rolled out as a smartphone app for testing in the real and very noisy world. However, it has one drawback: it has so far only been tested for urine flow in men which is different from that in women. Could there be a female-focused version in the offing?

Leave a Comment

Your email address will not be published. Required fields are marked *