Search papers, labs, and topics across Lattice.
This paper explores the use of reasoning-capable LLMs for extracting structured Social Determinants of Health (SDOH) events from unstructured clinical notes. They employ a four-module approach involving prompt engineering, few-shot learning, self-consistency, and post-processing. The proposed method achieves a micro-F1 score of 0.866, demonstrating competitive performance with BERT-based models while offering implementation simplicity.
LLMs can extract structured social determinants of health from clinical notes with competitive performance compared to BERT-based models, but with significantly less implementation complexity.
Social Determinants of Health (SDOH) refer to environmental, behavioral, and social conditions that influence how individuals live, work, and age. SDOH have a significant impact on personal health outcomes, and their systematic identification and management can yield substantial improvements in patient care. However, SDOH information is predominantly captured in unstructured clinical notes within electronic health records, which limits its direct use as machine-readable entities. To address this issue, researchers have employed Natural Language Processing (NLP) techniques using pre-trained BERT-based models, demonstrating promising performance but requiring sophisticated implementation and extensive computational resources. In this study, we investigated prompt engineering strategies for extracting structured SDOH events utilizing LLMs with advanced reasoning capabilities. Our method consisted of four modules: 1) developing concise and descriptive prompts integrated with established guidelines, 2) applying few-shot learning with carefully curated examples, 3) using a self-consistency mechanism to ensure robust outputs, and 4) post-processing for quality control. Our approach achieved a micro-F1 score of 0.866, demonstrating competitive performance compared to the leading models. The results demonstrated that LLMs with reasoning capabilities are effective solutions for SDOH event extraction, offering both implementation simplicity and strong performance.
