An AI healthcare company asserts that its software can more accurately detect the extent of prostate cancer than doctors.
Avenda Health recently released a study involving ten doctors who each evaluated 50 separate prostate cancer cases. The study demonstrated that Avenda’s Unfold AI software detected cancer with 84.7% accuracy, whereas manual detection by physicians ranged between 67.2% and 75.9%.
The study, conducted in collaboration with UCLA Health and published in the Journal of Urology, also found that AI-assisted cancer contouring improved prediction accuracy and consistency by 45 times compared to non-AI methods.
Assistant adjunct professor of urology, surgery, and bioengineering at UCLA and senior author of the study, Shyam Natarajan, stated, “We observed that AI assistance made doctors more accurate and consistent, meaning they tended to agree more when using AI.”
Doctors typically use MRIs to gauge tumor size, but some tumors remain “MRI-invisible,” according to Dr. Wayne Brisbane, assistant professor of urology at the David Geffen School of Medicine at UCLA. AI can assist in these challenging detections.
Dr. Brisbane added, “Overall, AI in cancer treatment could result in more effective and personalized care for patients, offering treatments better suited to their individual needs and more successful in combating the disease. AI has the potential to surpass human abilities in these areas.”
Avenda Health CEO Dr. Shyam Natarajan remarked that it’s encouraging for physicians to see such innovation validated through research and recognized by the AMA.
According to the American Cancer Society, about 1 in 8 men in the US will be diagnosed with prostate cancer during their lifetimes, and 1 in 44 men will die from the disease. It is projected that there will be 299,010 new cases of prostate cancer this year in the US and that 35,250 will die from it.