An artificial intelligence healthcare company has announced that its software can identify the extent of prostate cancer more accurately than human doctors.
Avenda Health conducted a study that involved ten physicians evaluating 50 separate prostate cancer cases. The company’s Unfold AI software achieved a detection accuracy of 84.7%, while the physicians’ manual assessments ranged from 67.2% to 75.9%.
The research, which was performed in collaboration with UCLA Health and published in the Journal of Urology, also revealed that with AI support in cancer contouring, predictions regarding cancer size were 45 times more accurate and consistent than traditional methods could achieve.
“Utilizing AI assistance improved both the accuracy and consistency amongst doctors; they reached more unanimous conclusions with AI help,” stated Dr. Shyam Natarajan, assistant adjunct professor of urology, surgery, and bioengineering at UCLA and senior author of the study.
Doctors typically rely on MRIs to evaluate tumor sizes; however, certain tumors are not detectable via MRI, according to Dr. Wayne Brisbane, an assistant professor of urology at the David Geffen School of Medicine at UCLA. He noted that AI proves beneficial in areas where MRIs struggle.
“Ultimately, integrating AI into cancer treatment could result in more effective and personalized care for patients, with therapies more specifically tailored to their needs, thereby improving outcomes in combating the disease,” Brisbane commented. He emphasized that AI has the potential to exceed human capabilities.
Dr. Shyam Natarajan, CEO of Avenda Health, expressed that seeing such innovative approaches validated through research and recognized by the American Medical Association is empowering for physicians.
According to the American Cancer Society, approximately 1 in 8 men will receive a prostate cancer diagnosis in their lifetime, and 1 in 44 will succumb to the disease. It is projected that in the U.S., there will be 299,010 new prostate cancer cases this year, with 35,250 fatalities attributed to the disease.