Researchers at the Korean Institute of Science and Technology (KIST) recently developed a machine to detect prostate cancer that needs just 20 minutes of your time and a few grams of your pee to reach almost 100% accuracy. Human oncologists are only about 30% accurate when it comes to detecting the disease. This is a big deal.
Bottom: Detecting prostate cancer is literally a pain in the ass. In the current paradigm, the disease is confirmed through a combination of laboratory work and invasive diagnoses. This involves a painful biopsy procedure in which surgeons remove a sample of tissue from the prostate.
Unfortunately, a large number of patients who undergo this procedure do not need it. These healthy people are at risk for nosocomial infection, surgical death and persistent side effects, including discomfort, pain and internal bleeding.
How it works: The KIST team decided to focus on urine because it contains traces of what the researchers call “cancer factors”. Normally, humans cannot diagnose prostate cancer using urine because the concentration of these cancer factors is simply not high enough to support standard test methods.
[Read: How Netflix shapes mainstream culture, explained by data]
To overcome this obstacle, the team used a special semiconductor-based sensor, sensitive enough to detect enough data for the team’s algorithms to analyze and correlate.
According to a press release from the National Science and Technology Council of Korea:
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.
Quick take: Wow!! This is amazing. Assuming that everything in the research is successful when scaled to the general population, it could save many lives. On average, about 1 in 41 men will die from prostate cancer, which is the second leading cause of cancer-related death among men worldwide.
Best of all, the team believes that this work can be adapted for other types of cancer.
You can read the team’s research article here.
Published on January 21, 2021 – 18:48 UTC