An AI healthcare company claims its software can determine the extent of prostate cancer more accurately than doctors.
Avenda Health recently released a study involving ten doctors who assessed 50 different prostate cancer cases each. The Unfold AI software from Avenda detected cancer with an accuracy of 84.7%, while doctors who detected cancer manually showed accuracy rates between 67.2% and 75.9%.
Conducted in partnership with UCLA Health and published in the Journal of Urology, the study also revealed that using AI for cancer contouring made predictions of cancer size 45 times more accurate and consistent compared to assessments without AI.
“We observed that AI assistance made doctors both more accurate and more consistent, meaning there was more agreement among doctors when AI was used,” stated Shyam Natarajan, an assistant adjunct professor of urology, surgery, and bioengineering at UCLA and senior author of the study.
Doctors often rely on MRIs to determine tumor size, but some tumors are “MRI-invisible,” explained Dr. Wayne Brisbane, an assistant professor of urology at the David Geffen School of Medicine at UCLA. AI can assist where MRIs fail.
“Overall, the use of AI in cancer treatment could result in more effective and personalized care for patients, with treatments better tailored to their individual needs and more successful in combating the disease,” Brisbane said. He added that AI can “go beyond human ability.”
Avenda Health CEO Dr. Shyam Natarajan emphasized that it is “empowering for physicians to see this kind of innovation being validated through studies and recognized by the AMA.”
In the US, approximately 1 in 8 men will be diagnosed with prostate cancer during their lifetimes, and 1 in 44 men will die from the disease, according to the American Cancer Society. It is estimated that there will be 299,010 new cases of prostate cancer this year in the US, with 35,250 deaths expected from the disease.