Multimodal Late Fusion for Obstructive Sleep Apnea Phenotyping and Risk Stratification
作者
Itunuoluwa Ayo-Durojaiye,Aijuan Dong,Sophia Isabel P. Ferrer,Silvia N. Crivelli,Daniel Coblentz,Qian Cheng
出处
期刊:日期:2026-02-02卷期号:: 148-154
标识
DOI:10.1109/icsc67292.2026.00028
摘要
Obstructive sleep apnea (OSA) is a sleep disorder associated with elevated cardiovascular and metabolic risks. This study presents a multimodal late-fusion framework to identify OSA patients most at risk using data from the MIMIC-IV database. Structured electronic health record data were encoded with an autoencoder trained through a joint reconstruction and classification loss, while unstructured discharge notes were represented by topic distributions extracted with BERTopic using BioClinicalBERT embeddings. The fused data were combined, reduced with UMAP, and clustered using HDBSCAN. Results show that multimodal fusion outperformed single-modality approaches, achieving a Silhouette Score of 0.8186 and an Adjusted Rand Index of 0.2802, compared with 0.8025/0.2797 for structured data and 0.4878 / -0.0012 for unstructured data. These findings highlight the synergistic value of multimodal data and its potential to advance precision medicine.