German-based PRAIM Study Demonstrates that AI Significantly Enhances Breast Cancer Detection

A groundbreaking new study has demonstrated that artificial intelligence (AI) can improve breast cancer detection rates by approximately 18% with no increase in false positives. The study was conducted by the University of Luebeck and the University Medical Center Schleswig-Holstein (UKSH), Campus Luebeck, in collaboration with the company Vara. The findings were reported in Nature Medicine.

The study, called PRAIM, assessed the data of over 460,000 women who participated in Germany’s Mammography Screening Program (MSP) between 2021 and 2023. Approximately half of all mammograms were assessed using AI, while the other half were analyzed by radiologists.

According to the findings, AI identified 6.7 cases of breast cancer per 1,000 women screened, compared to 5.7 cases per 1,000 detected using traditional methods. The results equated to one additional cancer case detected per 1,000 women screened. Notably, the findings showed that the rate of women referred for further testing remained stable, with 37.4 per 1,000 for AI assessments compared to 38.3 per 1,000 for traditional double readings.

“Our initial aim was to demonstrate that AI-based evaluations are equivalent to human assessments,” explained Prof. Dr. Alexander Katalinic, principal investigator and Director of the Institute of Social Medicine and Epidemiology at the University of Luebeck and UKSH, Campus Luebeck via a press release. “However, the findings exceeded our expectations: AI significantly improves breast cancer detection rates.”