A healthcare technology company has introduced software that claims to detect prostate cancer more accurately than human doctors. Avenda Health published a study last month featuring ten doctors who evaluated 50 prostate cancer cases each. The results indicated that Avenda’s Unfold AI software achieved an accuracy rate of 84.7%, while the physicians’ manual assessments ranged between 67.2% and 75.9%.
The research, conducted in collaboration with UCLA Health and reported in the Journal of Urology, showed that AI-assisted cancer contouring improved predictions of tumor size by 45 times compared to methods without AI.
According to Shyam Natarajan, an assistant adjunct professor of urology, surgery, and bioengineering at UCLA and the study’s senior author, using AI made doctors both more accurate and more consistent in their evaluations, leading to better agreement among them.
Doctors typically rely on MRIs to assess tumor sizes, but some tumors remain “MRI-invisible,” noted Dr. Wayne Brisbane, an assistant professor of urology at UCLA’s David Geffen School of Medicine. He explained that AI can provide valuable insights where MRI technology falls short.
Brisbane remarked that incorporating AI into cancer treatment could enable more effective and personalized patient care, allowing for better-tailored treatments that effectively combat the disease. He emphasized that AI has the potential to surpass human capabilities in certain areas.
Avenda Health’s CEO, Dr. Shyam Natarajan, expressed enthusiasm about the validation of their innovation through scholarly research and recognition from the American Medical Association.
In the United States, statistics indicate that approximately one in eight men will be diagnosed with prostate cancer in their lifetime, with one in 44 men succumbing to the illness, as reported by the American Cancer Society. This year alone, it is projected that there will be 299,010 new prostate cancer cases in the U.S., with 35,250 resulting in fatalities.