J Med Syst
Can large language models help in polypharmacy management?
April 29, 2024
Researchers evaluated ChatGPT's performance in polypharmacy management via its deprescribing decisions in standardized clinical vignettes. Findings suggest that trained large language models (LLM) like ChatGPT 3.5 may provide useful clinical support in polypharmacy management for PCPs.
- ChatGPT universally recommended deprescribing medications regardless of activities of daily living (ADL) status in patients with no overlying CVD history; in patients with CVD history, answers varied by technical replicate.
- Total number of medications deprescribed ranged from 2.67 to 3.67 (out of 7) and did not vary with CVD status but increased linearly with severity of ADL impairment.
- Among medication types, pain medications were preferentially deprescribed.
- ChatGPT's deprescribing decisions vary along the axes of ADL status, CVD history, and medication type, indicating some concordance of internal logic between general practitioners and the model.
Source:
Rao A, et al. (2024, April 18). J Med Syst. Proactive Polypharmacy Management Using Large Language Models: Opportunities to Enhance Geriatric Care. https://pubmed.ncbi.nlm.nih.gov/38632172/
TRENDING THIS WEEK