A new diagnostic test powered by artificial intelligence has been found to detect prostate cancer markers in urine samples with close to 100% accuracy. This noninvasive method sidesteps the need for biopsies or physical examinations, making it far more practical to incorporate into routine health check-ups for men.
At the core of the technology is an ultrasensitive biosensor, capable of picking up minute amounts of molecules linked to the presence of malignancies within a urine sample. The data is analyzed using a machine-learning algorithm, trained to identify patterns in the levels of the biomarkers detected, providing a cancer diagnosis in around 20 minutes.
"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," said In Gab Jeong from Korea’s Asan Medical Center.
Jeong and team tested the analytical software in urine samples collected from a cohort of 76 men, which was found to be incredibly sensitive, detecting cancer biomarkers with almost 100 percent accuracy.
At present, screening patients for prostate cancer relies on a routine blood test for detecting prostate-specific antigen. This test is far from perfect, however, yielding an 80 percent rate of false positives. Consequently, patients who are cancer-negative end up having to undergo painful biopsies to confirm the results.
"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 used in the precise diagnoses of other cancers via a urine test," said study co-author Kwan Hyi Lee from the Biomaterials Research Center.