A healthcare technology company has announced that its software can identify the extent of prostate cancer with greater accuracy than medical professionals.
Avenda Health conducted a study involving ten physicians who evaluated 50 different prostate cancer cases. Their AI software, called Unfold AI, demonstrated an accuracy rate of 84.7% in detecting cancer, which surpassed the accuracy of doctors who achieved rates between 67.2% and 75.9% during manual assessments.
The research, which collaborated with UCLA Health and appeared in the Journal of Urology, found that AI-assisted cancer contouring resulted in predictions of cancer size being 45 times more accurate and consistent compared to traditional methods.
Shyam Natarajan, an assistant adjunct professor of urology, surgery, and bioengineering at UCLA and the study’s senior author, noted that AI assistance improved both the accuracy and consistency of doctors’ assessments, leading to increased agreement among them when utilizing AI.
Doctors typically rely on MRI scans to determine tumor size; however, some tumors are not detectable on MRIs. Dr. Wayne Brisbane, an assistant professor of urology at the David Geffen School of Medicine at UCLA, stated that AI fills the gaps where MRIs are ineffective.
Brisbane explained that the integration of AI in cancer care could result in more effective and personalized treatments, tailored to individual patient needs and enhancing the success of combating the disease. He emphasized that AI has the potential to exceed human capabilities.
Dr. Shyam Natarajan, CEO of Avenda Health, expressed the significance of validating such innovations through research and receiving recognition from the American Medical Association.
Current data from the American Cancer Society indicates that approximately 1 in 8 men will receive a prostate cancer diagnosis in their lifetime, with a 1 in 44 chance of mortality from the disease. This year, it is projected that there will be 299,010 new prostate cancer cases in the US, with an estimated 35,250 fatalities resulting from the condition.