A team from the Korea Institute of Science and Technology (KIST) uses AI on urine samples to detect prostate cancer.

Current methods detect prostate cancer with only 30% accuracy and require invasive surgery for a final determination through biopsies. This is highly inconvenient and often results in complications such as bleeding and pain. Prostate cancer is the most common cancer in men. (Science Codex)

Researchers at the Korea Institute of Science and Technology (KIST) led by Dr. Kwan Hyi Lee from the Biomaterials Research Center and Professor In Gab Jeong from Asan Medical Center have developed a process that identifies prostate cancer with nearly 100% accuracy. It uses AI and a urine sample, generating a report in merely 20 minutes.

Since the urine-based method is non-invasive, it is very convenient, quick, and inexpensive for patients.

How it works

The team combined an ultra-sensitive, electrical-signal-based biosensor with an AI model. The system measures trace amounts of selected four cancer factors in urine for diagnosing prostate cancer.

The researchers trained the AI model by using the correlation between the four cancer factors, measured by the sensor.

Once trained, the algorithm identified patients with prostate cancer by analyzing complex patterns of the detected signals.

The system detected the presence of prostate cancer in 76 urinary samples with almost 100 percent accuracy.

Reduction in surgery, cost, and medical staff fatigue

“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 at Asan Medical Center said.

“This research developed a smart biosensor that can rapidly diagnose prostate cancer with almost 100 percent accuracy only through a urine test, and it can be further utilized in the precise diagnoses of other cancers using a urine test,” Dr. Lee at the KIST said.

Related Story:  An AI Program Identifies Prostate Cancer With Almost 100% Accuracy