New AI app listens to you pee to detect early signs of this

By Mark Waghorn via SWNS

A new smartphone app measures peeing power, and the results could help indicate early signs of diseases including prostate and bladder cancer.

The app calculates flow rate, volume - and the time it takes men to finish.

Audioflow uses artificial intelligence trained to listen when you go.

In tests, it performed almost as well as a specialist machine used in clinics.

The deep learning device's assessments were as accurate as student doctors'.

Its performance was so impressive a clinical trial is already set to begin.

Audioflow is being rolled out to family doctors for real-world appraisals.

Project leader Dr. Lee Han Jie, of Singapore General Hospital, said: "Our AI can outperform some non-experts - and comes close to senior consultants.

"But the real benefit is having the equivalent of a consultant in the bathroom with you - every time you go."

A weak stream affects around six in 10 older men and women. It can mean an enlarged prostate gland, urinary tract bug, obstruction or even tumor.

Currently, outpatients pee into a funnel connected to a machine that collects the information.

The technique, called uroflowmetry, is an important tool in medical diagnosis.

During the pandemic access to clinics has been restricted. It can also take a long time - causing queues.

Audioflow is based on 534 men recruited between December 2017 and July 2019. They recorded themselves on smartphones in a soundproof room.

The algorithm learned to listen and analyze male flow - which is different from that of females. A separate sample will be needed for women.

Audioflow picked up more than 80 percent of abnormal readings identified by a conventional machine and a panel of six urology undergraduates.

Dr. Lee said: "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 pandemic there is a shift towards telemedicine and less hospital-based care.

"We were keen to develop a way to monitor our patients to see how they are doing between hospital visits."

He added: "We are now working towards the algorithm being able to work when there is background noise in the normal home environment. This will make the true difference for patients."

More datasets are also being collected from different noise environments.

Professor Christian Gratzke, a urologist at University Hospital Freiburg, Germany, who was not involved in the study, said: "Giving patients the ability to measure urinary flow at home is more comfortable for them and reduces time waiting in the clinic.

"This is a well-executed study with a significant number of patients and represents a promising approach to developing a portable app that can be used at home. I look forward to seeing the real-world results."

Audioflow was presented at a European Association of Urology meeting in Amsterdam.