An AI healthcare company claims its software can more accurately assess the extent of prostate cancer compared to traditional methods.
Avenda Health recently published a study involving ten doctors who evaluated 50 prostate cancer cases each. The study found that Avenda’s Unfold AI software identified cancer with an accuracy of 84.7%, while the manual assessments by physicians varied between 67.2% and 75.9%.
Conducted in collaboration with UCLA Health and published in the Journal of Urology, the study also revealed that AI-assisted cancer contouring improved predictions of tumor size, making them 45 times more accurate and consistent than assessments without AI support.
Shyam Natarajan, an assistant adjunct professor of urology, surgery, and bioengineering at UCLA and the study’s senior author, noted that AI assistance enhanced both the accuracy and consistency of physicians’ diagnoses, leading to greater agreement among doctors when using the technology.
While doctors typically rely on MRIs to determine tumor size, some tumors can be “MRI-invisible,” according to Dr. Wayne Brisbane, an assistant professor of urology at the David Geffen School of Medicine at UCLA. He emphasized that AI can address limitations where MRIs might fall short.
Dr. Brisbane stated that leveraging AI in cancer treatment could enable more effective and personalized patient care, ultimately leading to better-tailored treatments that enhance success rates against the disease. He highlighted AI’s potential to surpass human capabilities.
Avenda Health CEO Dr. Shyam Natarajan expressed enthusiasm over the validation of this innovative technology through research, noting that it has gained recognition from the American Medical Association (AMA).
According to the American Cancer Society, approximately 1 in 8 men will be diagnosed with prostate cancer in their lifetime, and 1 in 44 will succumb to the disease. The organization projects there will be 299,010 new prostate cancer cases and 35,250 deaths from the illness in the United States this year.