Predictive Modeling and Deep Phenotyping of Obstructive Sleep Apnea and Associated Comorbidities through Natural Language Processing and Large Language Models

Abstract Obstructive Sleep Apnea (OSA) is a prevalent sleep disorder associated with serious health conditions. This project utilized large language models (LLMs) to develop lexicons for OSA sub-phenotypes. Our study found that LLMs can identify informative lexicons for OSA sub-phenotyping in simple patient cohorts, achieving wAUC scores of 0.9 or slightly higher. Among the six models studied, BioClinical BERT and BlueBERT outperformed the rest. Additionally, the developed lexicons exhibited some utility in predicting mortality risk (wAUC score of 0.86) and hospital readmission (wAUC score of 0.72). This work demonstrates the potential benefits of incorporating LLMs into healthcare. Data and Code Availability This paper uses the MIMIC-IV dataset (Johnson et al., 2023a), which is available on the PhysioNet repository (Johnson et al., 2023b). We plan to make the source code publicly available in the future. Institutional Review Board (IRB) This research does not require IRB approval.