A study conducted by Avenda Health has revealed that its AI software can more accurately detect the extent of prostate cancer compared to human doctors. The research, which involved ten doctors each evaluating 50 prostate cancer cases, found that Avenda’s Unfold AI achieved an accuracy of 84.7%. In contrast, the physicians’ manual assessments ranged from 67.2% to 75.9% accuracy.
Published in the Journal of Urology and conducted in collaboration with UCLA Health, the study highlighted that AI-assisted cancer contouring resulted in predictions of tumor size that were 45 times more accurate and consistent than those made without AI support.
Shyam Natarajan, an assistant adjunct professor of urology, surgery, and bioengineering at UCLA and the study’s senior author, noted that the integration of AI assistance led to improved accuracy and consistency among doctors, making their assessments more aligned.
Traditionally, doctors rely on MRIs to evaluate tumor size, but some tumors are not visible via MRI. Dr. Wayne Brisbane, an assistant professor of urology at UCLA’s David Geffen School of Medicine, explained that AI can provide crucial insight where MRIs fall short. He emphasized that the incorporation of AI into cancer treatment could result in more personalized and effective care, allowing for treatments that better meet patients’ unique needs.
Avenda Health’s CEO, Dr. Shyam Natarajan, expressed that it is encouraging for physicians to witness such innovative technology being validated through research and gaining recognition from the American Medical Association (AMA).
According to the American Cancer Society, in the United States, approximately 1 in 8 men will receive a prostate cancer diagnosis in their lifetime, and 1 in 44 will succumb to the disease. For the current year, it is estimated that there will be 299,010 new prostate cancer cases in the U.S., with 35,250 resulting in death.