An algorithm capable of assessing the risk that a particular patient will develop prostate cancer over the next five years will be used in a national screening program in the UK.
According to the charity Prostate Cancer UK, one in eight men in the United Kingdom will be diagnosed with prostate cancer in their lifetime. The disease is diagnosed in more than 47,500 men each year, and more than 11,500 people die from it. At the same time, prostate cancer is one of the most curable forms of cancer if it is diagnosed at an early stage.
The most common form of screening is a regular blood test. Doctors are looking for prostate-specific antigen (PSA), a protein produced by prostate cells. Its elevated levels may mean that the cells are cancerous. Patients in such cases are usually given a biopsy to confirm whether they have cancer or not.
However, PSA tests are not always reliable and tend to produce false positives, leading to overdiagnosis.
Alternatively, screening for PSA can be done, as well as human kallikrein peptidase (hK2), another cancer biomarker. Although hK2 is a weak marker, it can help improve the accuracy of PSA measurements.
Scientists led by University College London combined this two-marker approach and an algorithm that takes into account the age of the patient to ultimately determine the risk of developing prostate cancer.
The researchers analyzed blood samples from more than 21,000 men, identifying 571 who died of prostate cancer and 2,169 who were healthy. Then took the PSA and hK2 levels from these samples, as well as the age of the men, and used this information to develop a standard algorithm capable of automatically estimating men's prostate cancer risk based on their age and hK2 levels.
The team said this screening approachieve a 90 percent detection rate for prostate cancer, with a false-positive rate of 1.2 percent, for regularly tested men aged 55 and over.
The PSA test alone was able to detect the disease in 86% of cases with a false positive rate of 2%. Scaling the algorithm approach yielded 0.5% false positives. According to the scientists, this allows them to claim that their dual-marker software method can reduce false positives by three-quarters while maintaining the same detection rate as today's PSA analysis.
“Our study shows that a different screening approach can reduce false positives by three-quarters,” said Sir Nicholas Wald, lead author of the paper and professor at the UCL Institute for Medical Informatics. “This would make prostate cancer screening safer and more accurate, reducing overdiagnosis and treatment.”
Sir Nicholas wants to test the algorithm on more patients to see if it can be used in a real clinical setting.
“The next step is to test the feasibility of this approach in practice through a pilot project in which healthy men are invited for screening. If the project is successful, we believe this approach should be considered as part of a national screening program for all men,” he concluded.
Earlier, the Korea Institute of Science and Technology (KAIST) announced the development of a urinalysis method for diagnosing prostate cancer in just twenty minutes with almost 100% accuracy. The team has developed an ultra-sensitive semiconductor sensor system capable of simultaneously detecting traces of selected four cancer factors in urine. They trained the AI using the correlation between the four cancer factors provided by the developed sensor.
bbabo.Net