AI-Powered Urine Test Offers Accurate Prostate Cancer Diagnosis

A new urine-based diagnostic tool for prostate cancer has been developed using artificial intelligence and spatial gene expression analysis. The test identifies protein biomarkers in urine that reflect the presence and severity of prostate cancer, achieving diagnostic accuracy surpassing that of traditional blood tests.

According to principal investigator Mikael Benson, PhD, this method is noninvasive, painless, and can potentially be done at home. The sample is then analyzed using routine methods in clinical labs. In a study published in Cancer Research, researchers from Karolinska Institutet, Imperial College London, and Xiyuan Hospital at the China Academy of Chinese Medical Sciences found that the diagnostic models using these biomarkers achieved an area under the curve (AUC) of 0.92 in urine samples.

This is significantly higher than PSA-based diagnostics, which typically range from 0.56 to 0.6. Blood-based models using the same proteins achieved an AUC of 0.69. The findings suggest that proteins found in urine provide more accurate diagnostic signals than those found in blood.

Currently, screening for prostate cancer relies on PSA level tests, which lack specificity and sensitivity. Additional tests, such as the Prostate Health Index (PHI), have improved performance slightly, but still fall short in diagnostic reliability across patient populations.

The researchers analyzed samples from over 2,000 patients, including urine, blood, and prostate tissue. They found consistent patterns of overexpression in biomarkers such as SPON2, AMACR, and TMEFF2 across independent patient cohorts. The new tool has the potential to enhance personalized treatment in the future because some of the biomarkers are linked to known drug targets.

The research team is preparing for large-scale clinical trials and making all data and analytical tools publicly available. They believe that their framework, which combines spatial transcriptomics, pseudotime modeling, and machine learning, may be applicable across oncology.

Source: https://www.insideprecisionmedicine.com/topics/oncology/urine-test-detects-prostate-cancer-with-greater-precision-than-psa