A healthcare technology company claims that its software can more accurately determine the extent of prostate cancer compared to traditional detection methods used by doctors.
Avenda Health conducted a study with ten doctors who evaluated 50 prostate cancer cases each. The company’s Unfold AI software achieved an accuracy rate of 84.7% in detecting cancer, while the physicians’ manual assessments ranged from 67.2% to 75.9% accuracy.
The research, conducted in collaboration with UCLA Health and published in the Journal of Urology, also highlighted that using AI for cancer contouring resulted in predictions of tumor size being 45 times more accurate and consistent than traditional methods.
According to Shyam Natarajan, an assistant adjunct professor of urology, surgery, and bioengineering at UCLA and the study’s senior author, AI assistance improved both the accuracy and the consistency of the doctors’ evaluations, leading to greater agreement among them.
While doctors typically use MRIs to measure tumor size, Dr. Wayne Brisbane, an assistant professor of urology at UCLA’s David Geffen School of Medicine, pointed out that certain tumors can be “MRI-invisible.” AI technology fills this gap where traditional imaging falls short.
Dr. Brisbane emphasized that incorporating AI in cancer treatment could result in more effective and personalized patient care, with approaches that are better suited to individual patient needs and more effective at combating the disease. He noted that AI’s capabilities can surpass human limitations.
Avenda Health’s CEO, Dr. Shyam Natarajan, expressed that it is encouraging for healthcare professionals to see such innovations validated through research and acknowledged by the American Medical Association.
In the United States, approximately 1 in 8 men will receive a prostate cancer diagnosis in their lifetime, with 1 in 44 men succumbing to the disease, according to the American Cancer Society. This year, it is estimated that there will be 299,010 new prostate cancer cases in the U.S., resulting in 35,250 fatalities.