An AI healthcare company claims that its software offers a more accurate detection of prostate cancer compared to traditional methods used by doctors.
Avenda Health published a study last month involving ten physicians who evaluated 50 different cases of prostate cancer. The study revealed that the company’s Unfold AI software identified cancer with an accuracy rate of 84.7%, whereas the doctors using manual detection achieved accuracy rates between 67.2% and 75.9%.
Conducted in collaboration with UCLA Health and presented in the Journal of Urology, the research highlighted that employing AI for cancer contouring resulted in size predictions that were 45 times more precise and consistent compared to those made without AI assistance.
Shyam Natarajan, an assistant adjunct professor of urology, surgery, and bioengineering at UCLA and the study’s senior author, noted, “We observed that AI assistance improved both the accuracy and consistency of doctors’ assessments, leading to a greater agreement among them.”
Doctors typically utilize MRI scans to gauge tumor size; however, some tumors are not visible on these scans. Dr. Wayne Brisbane, an assistant professor of urology at the David Geffen School of Medicine at UCLA, explained that AI can assist in situations where MRI fails.
Brisbane stated, “The incorporation of AI in cancer treatment has the potential to enable more effective and personalized patient care, with treatments that are better tailored to individual needs and more successful in combating the disease.” He emphasized that AI can surpass human diagnostic capabilities.
Dr. Shyam Natarajan, CEO of Avenda Health, expressed that seeing such innovations validated through research and acknowledged by the American Medical Association is empowering for doctors.
According to the American Cancer Society, approximately one in eight men will be diagnosed with prostate cancer in their lifetime, and one in 44 will succumb to the disease. The projections for this year indicate 299,010 new prostate cancer cases in the US, with an estimated 35,250 deaths attributed to the illness.