A healthcare technology company, Avenda Health, claims that its AI software can identify the extent of prostate cancer more accurately than human doctors.
In a recent study involving ten doctors who evaluated 50 prostate cancer cases each, Avenda’s Unfold AI software achieved an accuracy rate of 84.7%. In contrast, the physicians’ manual assessments varied, with accuracy rates ranging from 67.2% to 75.9%.
Conducted in collaboration with UCLA Health and published in the Journal of Urology, the study also highlighted that AI-assisted cancer contouring yielded predictions about cancer size that were 45 times more accurate and consistent compared to assessments made without AI assistance.
Dr. Shyam Natarajan, a senior author of the study and assistant adjunct professor of urology, surgery, and bioengineering at UCLA, noted that AI not only improves accuracy but also enhances consistency among doctors, leading to greater agreement in their assessments.
Dr. Wayne Brisbane, an assistant professor of urology at the David Geffen School of Medicine at UCLA, explained that while doctors typically rely on MRIs to determine tumor size, some tumors are not visible through MRI scans. In such cases, AI can provide critical assistance where traditional imaging fails.
Brisbane emphasized that AI’s application in cancer treatment could enable more effective and personalized care, tailoring treatments to individual patient needs and improving success rates against the disease. He remarked that AI has the capacity to surpass human capabilities.
Dr. Natarajan, the CEO of Avenda Health, expressed optimism about the validation of such innovations through studies and the acknowledgment from the American Medical Association (AMA).
According to the American Cancer Society, approximately 1 in 8 men in the U.S. will be diagnosed with prostate cancer in their lifetime, and 1 in 44 men will die from the illness. It is projected that there will be 299,010 new cases of prostate cancer in the U.S. this year, resulting in an estimated 35,250 deaths from the disease.