When doctors and AI medical opinions diverge, humans must question the difference, according to experts
The human doctor and the artificial intelligence (AI) tool they are using more and more frequently are not always going to agree.
When doctors and artificial intelligence (AI) medical opinions diverge, the human must question the difference, according to experts. A new paper published in the journal npj Digital Medicine suggests that carefully setting up a process of parallel assessments from the beginning of data collection can help maximize the benefits of both human and machine when diagnosis and prognosis do not align.
The lead author, Dr. Charles E. Binkley, emphasizes the importance of recognizing and reconciling these divergence events in clinical human-AI interactions. Experts argue that treating divergence moments as insightful interactions between two kinds of knowledge, rather than just adjudications between two outputs, can lead to safer clinical decisions and enable both the clinician and AI system to learn from each other.
Written by urgent.news from Medical Xpress's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
