Proactive Polypharmacy Management Using Large Language Models: Opportunities to Enhance Geriatric Care

Arya Rao; John Kim; Winston Lie; Michael Pang; Lanting Fuh; Keith J Dreyer; Marc D Succi

doi:10.1007/s10916-024-02058-y

Proactive Polypharmacy Management Using Large Language Models: Opportunities to Enhance Geriatric Care

J Med Syst. 2024 Apr 18;48(1):41. doi: 10.1007/s10916-024-02058-y.

Authors

Arya Rao^{1

2

3}, John Kim^{1

2

3}, Winston Lie^{1

2

3}, Michael Pang^{1

2

3}, Lanting Fuh³, Keith J Dreyer^{1

4}, Marc D Succi^{5

6

7}

Affiliations

¹ Harvard Medical School, Boston, MA, USA.
² Medically Engineered Solutions in Healthcare Incubator, Innovation in Operations Research Center (MESH IO), Massachusetts General Hospital, Boston, MA, USA.
³ Massachusetts General Hospital, Department of Radiology, 55 Fruit Street, Boston, MA, 02114, USA.
⁴ Data Science Office, Mass General Brigham, Boston, MA, USA.
⁵ Harvard Medical School, Boston, MA, USA. msucci@mgh.harvard.edu.
⁶ Medically Engineered Solutions in Healthcare Incubator, Innovation in Operations Research Center (MESH IO), Massachusetts General Hospital, Boston, MA, USA. msucci@mgh.harvard.edu.
⁷ Massachusetts General Hospital, Department of Radiology, 55 Fruit Street, Boston, MA, 02114, USA. msucci@mgh.harvard.edu.

PMID: 38632172
DOI: 10.1007/s10916-024-02058-y

Abstract

Polypharmacy remains an important challenge for patients with extensive medical complexity. Given the primary care shortage and the increasing aging population, effective polypharmacy management is crucial to manage the increasing burden of care. The capacity of large language model (LLM)-based artificial intelligence to aid in polypharmacy management has yet to be evaluated. Here, we evaluate ChatGPT's performance in polypharmacy management via its deprescribing decisions in standardized clinical vignettes. We inputted several clinical vignettes originally from a study of general practicioners' deprescribing decisions into ChatGPT 3.5, a publicly available LLM, and evaluated its capacity for yes/no binary deprescribing decisions as well as list-based prompts in which the model was prompted to choose which of several medications to deprescribe. We recorded ChatGPT responses to yes/no binary deprescribing prompts and the number and types of medications deprescribed. In yes/no binary deprescribing decisions, ChatGPT universally recommended deprescribing medications regardless of ADL status in patients with no overlying CVD history; in patients with CVD history, ChatGPT's 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, ChatGPT preferentially deprescribed pain medications. 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. These results indicate that specifically trained LLMs may provide useful clinical support in polypharmacy management for primary care physicians.

Keywords: Artificial intelligence; Large language models; Polypharmacy; Primary care.

MeSH terms

Aged
Artificial Intelligence
Cardiovascular Diseases*
Deprescriptions*
General Practitioners*
Humans
Polypharmacy

Abstract

MeSH terms

Grants and funding