The Crimson has an interesting piece on AI and Medical Imaging. They note:
Harvard Medical School researchers and affiliates have discovered that the use of artificial intelligence in radiology is not universally beneficial, contrary to existing research. The study — released last Tuesday by researchers at MIT, Stanford, and the Rajpurkar Lab of Harvard Medical School — was a re-analysis of a previous study by the same researchers. Published in Nature, it centered on a high-performing AI model and studied its effectiveness in diagnosing patients based on chest X-rays. Pranav Rajpurkar, a Harvard Medical School professor who co-authored the study, emphasized the need for a more detailed understanding of AI in medicine. “While previous studies have shown the potential for AI to improve overall diagnostic accuracy, there was limited understanding of the individual-level impact on clinicians and what factors influence the effectiveness of AI assistance for each radiologist,” he wrote in an emailed statement. The study found that AI use in radiology “did not uniformly improve diagnostic accuracy, and could even hurt performance for some cases,” according to Kathy Yu, a researcher who was a member of the Rajpurkar Lab when the study was conducted.
This is not at all surprising. When I first started to learn radiology one went through steps. Say one is looking at the lung. Start at the periphery, any fluids, compressions, nodules, then work in to see heart mediastinumn vasculature. Is there honeycombing, nodules etc. Namely there was a methodology developed over years of reading images.
In the days of pattern recognition, images were approached in a similar structured manner. However with AI one uses learning sets and then "trusts in the kindness of strangers" with some neural network.
Thus one is hardly surprised.
Posts
