Predicting 30-Day Postoperative Mortality and American Society of Anesthesiologists Physical Status Using Retrieval-Augmented Large Language Models: Development and Validation Study

This study introduces a novel clinical AI framework integrating Large Language Models (LLMs) with Retrieval-Augmented Generation (RAG) to predict 30-day postoperative mortality and ASA physical status classifications based on unstructured preoperative clinical notes.

We conducted a retrospective cohort study using 24,491 medical records from a tertiary medical center.

To extract clinical insights from free-text data, we used the LLaMA 3.1-8B language model with RAG, using MedEmbed for text embedding and Miller's Anesthesia as the primary retrieval source.

The LLaMA-RAG model significantly improved the prediction of postoperative mortality and ASA classification, especially for rare high-risk cases.

By grounding outputs in domain knowledge, retrieval-augmented generation enhanced both accuracy and prompt-driven interpretability over ML and ablation models—highlighting its promise for real-world clinical decision support.