An AI healthcare company has claimed that its software can detect prostate cancer more accurately than human doctors. Avenda Health recently published a study involving ten physicians who examined 50 different cases of prostate cancer. The findings revealed that Avenda’s Unfold AI software achieved an accuracy rate of 84.7% in detecting cancer, while the accuracy of the physicians ranged from 67.2% to 75.9%.
Conducted in collaboration with UCLA Health and featured in the Journal of Urology, the study also demonstrated that when AI was utilized for cancer contouring, predictions regarding the size of tumors were 45 times more accurate and consistent compared to traditional methods.
Shyam Natarajan, an assistant adjunct professor of urology, surgery, and bioengineering at UCLA and the senior author of the study, highlighted that the use of AI assistance improved both the accuracy and consistency of doctors’ assessments. This, he noted, resulted in greater agreement among physicians when aided by AI.
Typically, doctors rely on MRIs to gauge tumor size, but some tumors are “MRI-invisible,” according to Dr. Wayne Brisbane, an assistant professor of urology at the David Geffen School of Medicine at UCLA. He emphasized that AI provides valuable support where MRIs may fail.
Brisbane added that incorporating AI into cancer care could enhance treatment effectiveness and personalize care, leading to more tailored and successful interventions for patients. He asserted that AI has the potential to exceed human capabilities.
Dr. Shyam Natarajan, CEO of Avenda Health, expressed his enthusiasm for seeing such innovations being validated through research and acknowledged by the American Medical Association (AMA).
According to the American Cancer Society, approximately 1 in 8 men in the United States will receive a prostate cancer diagnosis during their lifetime, and 1 in 44 men will die from the illness. This year alone, it is estimated that there will be 299,010 new cases of prostate cancer in the U.S., with 35,250 expected fatalities.