Practical Aspects of Using Large Language Models to Screen Abstracts for Cardiovascular Drug Development: Cross-Sectional Study

JMIR Med Inform. 2024 Sep 30:12:e64143. doi: 10.2196/64143.

Abstract

Cardiovascular drug development requires synthesizing relevant literature about indications, mechanisms, biomarkers, and outcomes. This short study investigates the performance, cost, and prompt engineering trade-offs of 3 large language models accelerating the literature screening process for cardiovascular drug development applications.

Keywords: AI; GPT; LLM; artificial intelligence; biomarker; biomedical; biomedical informatics; cardio; cardiology; cardiovascular; cross-sectional study; drug; drug development; large language model; screening optimization.

MeSH terms

  • Abstracting and Indexing
  • Cardiovascular Agents / therapeutic use
  • Cardiovascular Diseases / drug therapy
  • Cross-Sectional Studies
  • Drug Development* / methods
  • Humans
  • Natural Language Processing

Substances

  • Cardiovascular Agents