AI-assisted test diagnoses prostate cancer from urine with almost 100% accuracy

Credit: Korea Institute of Science and Technology(KIST).

Scientists in South Korea have developed a non-invasive, lightning-fast test that diagnoses prostate cancer with a stunning accuracy of up to 100%. Unlike traditional methods that require a biopsy, this test, which employs a smart AI analysis method, only needs a urine sample.

Prostate cancer is one of the most dangerous types of cancers out there, especially for older men, with about 99% of cases occur in those over the age of 50. It is the second-leading cause of cancer death for men in the United States. About 1 in 35 men will die from it.

Patients are typically screened for prostate cancer through the detection of prostate-specific antigens (PSA), a cancer factor, in the blood. The problem is that the diagnostic accuracy of screening for this cancer factor is just 30%. In order to cover the loose ends, doctors often recommend undergoing additional invasive diagnosis methods, such as a biopsy. These measures, although potentially life-saving if the cancer is caught early, can be painful and cause bleeding.

Dr. Kwan Hyi Lee and Professor In Gab Jeong from the Korea Institute of Science and Technology (KIST) may have come up with a much better test.

Their test screens for prostate cancer by looking for four cancer factors in the urine of patients rather than blood. These cancer factors are detected by an electrical-signal-based ultrasensitive biosensor that is sensitive enough to detect trace amounts of the selected molecules.

The team of researchers developed and trained an AI that identifies those with cancer prostate from the urine samples by analyzing complex patterns of the detected signals. For the 76 urinary samples that they used, the researchers reported almost 100% accuracy.

“For patients who need surgery and/or treatments, cancer will be diagnosed with high accuracy by utilizing urine to minimize unnecessary biopsy and treatments, which can dramatically reduce medical costs and medical staff’s fatigue,” Professor Jeong said in a statement.

The findings were reported in the journal  ACS Nano.

Leave a Reply

Your email address will not be published.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