LLMs-based Few-Shot Disease Predictions using EHR: A Novel Approach Combining Predictive Agent Reasoning and Critical Agent Instruction

arXiv:2403.15464v1 Announce Type: cross
Abstract: Electronic health records (EHRs) contain valuable patient data for health-related prediction tasks, such as disease prediction. Traditional approaches rely on supervised learning methods that require large labeled datasets, which can be expensive and challenging to obtain. In this study, we investigate the feasibility of applying Large Language Models (LLMs) to convert structured patient visit data (e.g., diagnoses, labs, prescriptions) into natural language narratives. We evaluate the zero-shot and few-shot performance of LLMs using various EHR-prediction-oriented …

abstract agent arxiv cs.ai cs.cl cs.lg cs.ma data datasets disease ehr electronic electronic health records few-shot health llms novel patient prediction predictions predictive reasoning records supervised learning tasks type