Eric Topol 1/28/24: Toward the eradication of medical diagnostic error
Key points/excerpts:
- There is little evidence that we are reducing diagnostic errors despite more lab testing and more imaging. “One of the important reasons for these errors is failure to consider the diagnosis when evaluating the patient.” This, in turn, may be related to brief office visits.
- There are a few ways that artificial intelligence (AI) is emerging to make a difference to diagnostic accuracy. ..A systematic analysis of 33 randomized trials of colonoscopy, with or without real-time AI machine vision, indicated there was more than a 50% reduction in missing polyps and adenomas, and the inspection time added by AI to achieve this enhanced accuracy averaged only 10 s.
- AI support to radiologists for a large mammography study “showed improvement in accuracy with a considerable 44% reduction of screen-reading workload.” The cancer detection rate was 6.1 per 1000 compared to 5.1 per 1000 in the control group.
- In difficult NEJM CPC cases, large language AI model (LLM) outperformed clinicians (see slide below).” The LLM was nearly twice as accurate as physicians for accuracy of diagnosis, 59.1 versus 33.6%, respectively.”
- “Likewise, the cofounder of OpenAI, Ilya Sutskever, was emphatic about AI’s future medical superintelligence: ‘If you have an intelligent computer, an AGI [artificial general intelligence], that is built to be a doctor, it will have complete and exhaustive knowledge of all medical literature, it will have billions of hours of clinical experience.’ “
My take (borrowed from Dr. Topol): “We are certainly not there yet. But in the years ahead, …it will become increasingly likely that AI will play an invaluable role in providing second opinions with automated, System 2 machine-thinking, to help us move toward the unattainable but worthy goal of eradicating diagnostic errors.”
Related blog posts:
gutsandgrowth 