What question did this study set out to answer?

The study aims to assess the effectiveness of ChatGPT in providing clinical decision support throughout clinical workflows.

February 26, 2023Open Access

Assessing the Utility of ChatGPT Throughout the Entire Clinical Workflow

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial evaluates ChatGPT's accuracy in clinical decision support, suggesting its potential in clinical practice.

The study aims to assess the effectiveness of ChatGPT in providing clinical decision support throughout clinical workflows.
Input all 36 clinical vignettes from the MSD Clinical Manual into ChatGPT.
Evaluated accuracy on differential diagnoses, diagnostic testing, final diagnosis, and management.
Comparative analysis based on patient demographics and case acuity.
ChatGPT achieved overall accuracy of 71.7% (95% CI, 69.3% to 74.1%).
Best performance was in final diagnosis with 76.9% accuracy (95% CI, 67.8% to 86.1%).
Lowest performance in initial differential diagnoses at 60.3% accuracy (95% CI, 54.2% to 66.6%).

Rao et al. (2023) studied this question.

View Full Paper

Ask AI

Bookmark