Exploring the value of ChatGPT in selecting antidiabetic agents for type 2 diabetes
Authors' conclusion
ChatGPT shows potential as a decision-support tool for selecting anti-diabetic medications, particularly for treatment-naive individuals. Few-shot learning demonstrated improvements in recommendation accuracy, especially for simpler regimens. However, accuracy was notably limited in complex regimens such as triple therapy, highlighting the need for further refinement before clinical use.
Study context
- Population
- Adults with T2D visiting the Endocrine Department, Yongin Severance Hospital
- Participants
- 85 adults
- Exposure
- ChatGPT 4.0 treatment recommendations vs clinician prescriptions
- Outcome
- Concordance between ChatGPT's recommendations and clinician prescriptions for monotherapy, dual therapy and triple therapy (agree, partially agree, disagree)
Methodological detailssingle-centre
- Single-centre
Main finding
As reported in the abstract
Monotherapy (1st, 2nd, 3rd)
69.2%, 69.2%, 84.6%
Dual therapy (1st, 2nd, 3rd)
12.5%, 20.8%, 0%
Triple therapy (all three assessment points)
0%
Observational data: associations, not effects.
Further findings
Concordance in individuals with prior treatment history
- Concordance rate lower for individuals with prior treatment history
Few-shot vs zero-shot prompting
- Few-shot prompting improved agreement vs zero-shot, particularly for monotherapy and dual therapy
Original publication
Composed by AI from the published abstract and checked against it. How Briefs are made →