Deep Phenotyping of Obstructive Sleep Apnea Using Multimodal Representation Learning

Obstructive sleep apnea (OSA) is linked to elevated cardiovascular and metabolic risks. We developed a multimodal framework integrating structured clinical data and unstructured discharge summaries using TabNet and ClinicalBERT with late fusion to generate unified patient embeddings. After UMAP dimensionality reduction, multimodal clustering outperformed single-modality approaches (Silhouette Score: 0. 74 vs. 0. 49) and revealed two OSA subgroups with marked differences in hypertension prevalence (1 0 0 \% vs. 0. 6 \%) and survival (p 0. 0 5). Multimodal classification achieved a higher AUROC for phenotype prediction with Random Forest (0. 884 vs. 0. 878 structured; 0. 713 unstructured) and comparable performance with Logistic Regression (0. 886 vs. 0. 890 structured; 0. 721 unstructured). These results demonstrate that integrating heterogeneous data improves OSA patient stratification and phenotype prediction.