Artificial Intelligence Helps Diagnose Prostate Cancer

Prostate cancer is the second leading cause of cancer death for men in the U.S. It is primarily determined using PSA (Prostate-Specific Antigen) test, a cancer factor in the blood. But the diagnostic accuracy is as low as 30%, and additional invasive biopsies are required to confirm the diagnosis causing bleeding and pain in patients. Prostate cancer can now be diagnosed from the urine within twenty minutes with almost 100% accuracy, using a smart Artificial Intelligence (AI) analysis method and an electrical-signal-based ultrasensitive biosensor, as per the research team at The Korea Institute of Science and Technology (KIST).

This non-invasive diagnostic method makes it convenient for prostate cancer patients as it utilizes urine thus, minimizing the need for invasive biopsy and side effects. But as the concentration of cancer factors (a cancer-related biological index) remains low in urine, the urine-based biosensor is so far used to classify the risk groups than accurately diagnosing the patients.

Artificial Intelligence in Prostate Cancer Diagnosis

The research team deployed different types of cancer factors using the electrical-signal-based ultrasensitive biosensor rather than employing only one factor to enhance the diagnostic accuracy innovatively to over 90%.

This ultrasensitive semiconductor sensor system can simultaneously measure trace amounts of four selected cancer factors in the urine and provide a diagnosis for prostate cancer.

"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," says Professor Jeong at Asan Medical Center

The team trained an AI algorithm for identifying the correlation between the four cancer factors and analyzing their complex patterns of the detected signals to provide the diagnosis from the developed sensor. The AI analysis was able to detect 76 urinary samples successfully with almost 100 percent accuracy.

"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," says Dr. Lee at the KIST.

Top AI Applications in Healthcare

The top applications of artificial intelligence that could change healthcare include:

• Robot-assisted surgery
• Virtual nursing assistants Fraud detection
• Dosage error reduction
• Clinical trial participation
• Cybersecurity

Reference:

1. Hojun Kim et al, Noninvasive Precision Screening of Prostate Cancer by Urinary Multimarker Sensor and Artificial Intelligence Analysis, ACS Nano (2020). DOI:10.1021/acsnano.0c06946

Advertisement

Source-Medindia