Cancer can be accurately diagnosed using an artificial intelligence urine test

Prostate cancer is one of the most common cancers among men. It was determined that patients have prostate cancer primarily based on * PSA, a blood cancer factor. However, as the diagnostic accuracy is as low as 30%, a considerable number of patients undergo additional invasive biopsy and therefore suffer from the resulting side effects, such as bleeding and pain.

* Prostate specific antigen (PSA): a prostate specific antigen (a cancer factor) used as an index for screening for prostate cancer.

The Korean Institute of Science and Technology (KIST) announced that the collaborative research team led by Dr. Kwan Hyi Lee of the Biomaterials Research Center and Professor In Gab Jeong of Asan Medical Center have developed a technique to diagnose prostate cancer from urine in just twenty minutes with almost 100% accuracy. The research team developed this technique by introducing a method of intelligent AI analysis in an ultrasensitive biosensor based on electrical signals.

As it is a non-invasive method, a diagnostic test using urine is convenient for patients and does not require invasive biopsy, thus diagnosing cancer without side effects. However, as the concentration of cancer factors ** is low in the urine, a urine-based biosensor has been used to classify risk groups rather than for an accurate diagnosis so far.

** Cancer factor: a biological index related to cancer that can measure and evaluate the reactivity of the drug objectively for a normal biological process, disease progress and a treatment method.

Dr. Lee’s team at KIST has been working to develop a technique for diagnosing diseases from urine using the ultrasensitive biosensor based on an electrical signal. An approach that uses a single cancer factor associated with a cancer diagnosis has been limited to increasing the accuracy of the diagnosis to more than 90%. However, to overcome this limitation, the team simultaneously used different types of cancer factors instead of using just one to increase the accuracy of the diagnosis in an innovative way.

The team developed an ultrasensitive semiconductor sensor system capable of simultaneously measuring traces of four selected cancer factors in the urine for the diagnosis of prostate cancer. They trained AI using the correlation between the four cancer factors, which were obtained from the developed sensor. The trained AI algorithm was then used to identify those with prostate cancer, analyzing complex patterns of the detected signals. The diagnosis of prostate cancer using AI analysis has successfully detected 76 urinary samples with almost 100 percent accuracy.

“For patients who need surgery and / or treatments, cancer will be diagnosed with high precision, using urine to minimize biopsies and unnecessary treatments, which can dramatically reduce medical costs and fatigue for medical staff,” said Professor Jeong , from Asan Medical Center. “This research has developed an intelligent biosensor that can quickly diagnose prostate cancer with almost 100 percent accuracy just by using a urine test, and can later be used to accurately diagnose other cancers using a urine test,” he said. Dr. Lee at KIST. .

###

This research was supported by the Korean National Research Foundation’s Midcare Researcher Grant program, government departments (the Ministry of Science and ICT, the Ministry of Commerce and Industry, the Ministry of Health and Welfare and the Ministry of Food and Drug Safety) and Korea Medical Device Development Fund, funded by the Ministry of Science and ICT (MSIT). The research results were published in the latest edition of ACS Nano, one of the leading international academic journals in the nano field.