Avenda Health, an AI healthcare company, claims that its software can identify the extent of prostate cancer with greater accuracy than doctors. The company recently published a study that involved ten physicians who each evaluated 50 prostate cancer cases. According to the findings, Avenda’s Unfold AI software achieved an accuracy rate of 84.7% in detecting cancer, while the doctors’ manual assessments ranged from 67.2% to 75.9%.
Conducted in collaboration with UCLA Health and featured in the Journal of Urology, the study also revealed that AI-assisted cancer contouring resulted in predictions of tumor size that were 45 times more accurate compared to 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 AI assistance not only improved the accuracy of the doctors’ assessments but also enhanced consistency, leading to greater agreement among the physicians.
Dr. Wayne Brisbane, an assistant professor of urology at UCLA, explained that while doctors typically rely on MRIs to determine tumor size, some tumors are “MRI-invisible.” He emphasized the role of AI in complementing MRI capabilities.
Brisbane remarked that the integration of AI in cancer treatment could facilitate more personalized and effective care, with treatment plans tailored to meet individual patient needs and improving the chances against the disease. He highlighted that AI can surpass human capabilities in certain aspects.
Dr. Natarajan, CEO of Avenda Health, expressed that witnessing this kind of innovation being validated through research and acknowledged by the American Medical Association is empowering for physicians.
In the United States, approximately one in eight men is expected to be diagnosed with prostate cancer in their lifetime, and one in 44 may die from the disease, according to the American Cancer Society. This year, it is projected that there will be 299,010 new cases of prostate cancer in the US, with 35,250 fatalities attributed to the illness.