A research team recently found a way to detect prostate cancer factors in urine, said the National Research Council of Science and Technology in an article at Phys.org. This method is said to have 100% diagnosis accuracy in only 20 minutes.
This technique uses a smart AI analysis method introduced to an ultrasensitive biosensor. This sensor is based on an electrical signal.
The non-invasive method was developed by researchers at the Korea Institute of Science and Technology (KIST) and the Biomaterials Research Center and professor In Gab Jeong from the Asan Medical Center.
Professor Jeong said, “For patients who need surgery and/or treatments, cancer will be diagnosed with high accuracy by using urine to minimize unnecessary biopsy and treatments, which can dramatically reduce medical costs and medical staff’s fatigue."
He added, “This research developed a smart biosensor that can rapidly diagnose prostate cancer with almost 100% accuracy only through a urine test, and it can be further used in the precise diagnoses of other cancers via a urine test.”
Dr. Kwan Hyi Lee, leader of the KIST team, is also optimistic about its potential to diagnose other types of the disease using urine samples.
The development of this technique is a great leap compared to previous prostate cancer detection methods using Prostate-Specific Antigen (PSA), which is a blood-based factor with only a 30% accuracy rate, said Study Finds.
With such a low prospect, patients are compelled to have invasive ways for diagnoses, which can lead to side-effects including bleeding or surgical pain.
Prior to the team’s progress, the urine-based diagnosis had a low precision rate because urine cancer factor levels are low in comparison to biopsies, which limited the technique to risk group classifications instead of precise diagnosis as of current developments.
The KIST team was able to elevate the accuracy level to 90% by implementing an ultrasensitive biosensor that uses electrical signals to detect only one factor.
To increase the accuracy rate of this technique, the team simultaneously used various factors associated with the diagnosis of cancer in order to reach 100%.
This technique was a success thanks to an AI trained by introducing correlations of four factors specifically for prostate cancer. The algorithm diagnoses the disease by evaluating complex patterns sent by electrical signals to the semiconductor system.
The researchers used 76 urine samples to test this method, which gave an almost 100% accuracy with its diagnoses.
