An AI healthcare company has claimed that its software can more accurately assess the extent of prostate cancer compared to human doctors.
Avenda Health published a study last month involving ten physicians who each evaluated 50 prostate cancer cases. The findings revealed that Avenda’s Unfold AI software achieved an accuracy rate of 84.7% in detecting cancer, while the doctors’ manual assessments varied between 67.2% and 75.9%.
The research, conducted in collaboration with UCLA Health and featured in the Journal of Urology, also indicated that utilizing AI for cancer contouring resulted in predictions of tumor size being 45 times more accurate and consistent than traditional methods without AI assistance.
Dr. Shyam Natarajan, an assistant adjunct professor of urology, surgery, and bioengineering at UCLA and the study’s senior author, stated that the integration of AI assistance not only improved accuracy but also increased consistency among doctors in their evaluations.
While doctors typically rely on MRIs to determine tumor size, some tumors elude detection, making them “MRI-invisible,” noted Dr. Wayne Brisbane, an assistant professor of urology at the David Geffen School of Medicine at UCLA. He emphasized that AI has the potential to identify cancer in cases where MRI imaging is insufficient.
Dr. Brisbane added that the application of AI in cancer treatment may pave the way for more precise and personalized patient care, leading to enhanced treatment success rates tailored to individual needs.
Avenda Health’s CEO, Dr. Shyam Natarajan, expressed that witnessing innovations like this being validated through research and recognized by the American Medical Association is an empowering moment for physicians.
According to the American Cancer Society, approximately 1 in 8 men in the United States will be diagnosed with prostate cancer in their lifetime, and 1 in 44 will die from the disease. It is estimated that there will be 299,010 new prostate cancer cases in the U.S. this year, with 35,250 fatalities resulting from the condition.