Empowering large language models for automated clinical assessment with generation-augmented retrieval and hierarchical chain-of-thought.

Journal: Artificial intelligence in medicine
PMID: 39978047

Abstract

BACKGROUND: Understanding and extracting valuable information from electronic health records (EHRs) is important for improving healthcare delivery and health outcomes. Large language models (LLMs) have demonstrated significant proficiency in natural language understanding and processing, offering promises for automating the typically labor-intensive and time-consuming analytical tasks with EHRs. Despite the active application of LLMs in the healthcare setting, many foundation models lack real-world healthcare relevance. Applying LLMs to EHRs is still in its early stage. To advance this field, in this study, we pioneer a generation-augmented prompting paradigm "GAPrompt" to empower generic LLMs for automated clinical assessment, in particular, quantitative stroke severity assessment, using data extracted from EHRs.

Authors

  • Zhanzhong Gu
    School of Electrical and Data Engineering, University of Technology Sydney, NSW, 2007, Australia. Electronic address: zhanzhong.gu@student.uts.edu.au.
  • Wenjing Jia
    School of Electrical and Data Engineering (SEDE), University of Technology Sydney, 2007, Sydney, Australia.
  • Massimo Piccardi
    University of Technology Sydney (UTS), Australia.
  • Ping Yu
    Beijing National Laboratory for Molecular Sciences, Key Laboratory of Analytical Chemistry for Living Biosystems, Institute of Chemistry, the Chinese Academy of Sciences (CAS), Beijing 100190, China.

Keywords

External Resources

Popular Topics
Recent Journals