An AI healthcare company claims that its software can more accurately assess the extent of prostate cancer than traditional methods used by doctors.
Avenda Health conducted a study in collaboration with UCLA Health, which was published in the Journal of Urology, involving ten physicians who evaluated 50 prostate cancer cases each. The company’s Unfold AI software identified cancer with an accuracy rate of 84.7%, while the doctors’ manual assessments yielded accuracy rates ranging between 67.2% and 75.9%.
The study emphasized that the integration of AI for cancer contouring improved the accuracy and consistency of predictions regarding cancer size by a remarkable factor of 45 when compared to traditional methods.
“AI assistance has been shown to enhance both the accuracy and consistency of doctors’ assessments, resulting in greater agreement among them,” said Shyam Natarajan, an assistant adjunct professor of urology, surgery, and bioengineering at UCLA and the study’s senior author.
While physicians typically use MRI scans to gauge tumor sizes, certain tumors remain “MRI-invisible,” explained Dr. Wayne Brisbane, an assistant professor of urology at the David Geffen School of Medicine at UCLA. He noted that AI technology fills the gaps where MRI cannot provide clarity.
Brisbane added that leveraging AI in cancer treatment could significantly improve patient care, tailoring treatments to individual needs and increasing the chances of successful outcomes. He remarked that AI has the potential to exceed human capabilities.
Dr. Shyam Natarajan, CEO of Avenda Health, expressed that it is encouraging for clinicians to see such innovations validated through research and acknowledged by organizations like the AMA.
According to the American Cancer Society, approximately 1 in 8 men in the U.S. will be diagnosed with prostate cancer in their lifetime, and 1 in 44 will succumb to the disease. It is anticipated that in 2023, there will be about 299,010 new cases of prostate cancer in the United States, with 35,250 fatalities attributed to the disease.