Evaluation of GPT-4 ability to identify and generate patient instructions for actionable incidental radiology findings.
Kar-Mun C WooGregory W SimonOlumide AkindutireYindalon AphinyanaphongsJonathan S AustrianJung G KimNicholas GenesJacob A GoldenringVincent J MajorChloé S ParienteEdwin G PinedaStella K KangPublished in: Journal of the American Medical Informatics Association : JAMIA (2024)
GPT-4 demonstrates proficiency in detecting actionable, incidental findings after refined instruction prompting. AI-generated patient instructions were most often appropriate, but rarely included inferred recommendations. While this technology shows promise to augment diagnostics, active clinician oversight via "human-in-the-loop" workflows remains critical for clinical implementation.