CPLLM: Clinical prediction with large language models.

Abstract

We present Clinical Prediction with Large Language Models (CPLLM), a method that involves fine-tuning a pre-trained Large Language Model (LLM) for predicting clinical disease and readmission. We utilized quantization and fine-tuned the LLM using prompts. For diagnostic predictions, we predicted whether patients would be diagnosed with a target disease during their next visit or in the subsequent diagnosis, leveraging their historical medical records. We compared our results to various baselines, including Retain and Med-BERT, the latter of which is the current state-of-the-art model for disease prediction using temporal structured EHR data. In addition, we also evaluated CPLLM's utility in predicting hospital readmission and compared our method's performance with benchmark baselines. Our experiments ultimately revealed that our proposed method, CPLLM, surpasses all the tested models in terms of PR-AUC and ROC-AUC metrics, providing state-of-the-art performance as a tool for predicting disease diagnosis and patient hospital readmission without requiring pre-training on medical data. Such a method can be easily implemented and integrated into the clinical workflow to help care providers plan next steps for their patients.