Abstract

Background Obstructive sleep apnea (OSA) is a common sleep breathing disorder and timely diagnosis helps to avoid the serious medical expenses caused by related complications. Existing deep learning (DL)-based methods primarily focus on single-modal models, which cannot fully mine task-related representations.

Methods This paper develops a modality fusion representation enhancement (MFRE) framework adaptable to flexible modality fusion types with the objective of improving OSA diagnostic performance, and providing quantitative evidence for clinical diagnostic modality selection.

Results he proposed parallel information bottleneck modality fusion network (IPCT-Net) can extract local-global multi-view representations and eliminate redundant information in modality fusion representations through branch sharing mechanisms. We utilize large-scale real-world home sleep apnea test (HSAT) multimodal data to comprehensively evaluate relevant modality fusion types. Extensive experiments demonstrate that the proposed method significantly outperforms existing methods in terms of participant numbers and OSA diagnostic performance

Conclusions The proposed MFRE framework delves into modality fusion in OSA diagnosis and contributes to enhancing the screening performance of artificial intelligence (AI)-assisted diagnosis for OSA.

IPCT-Net: Parallel information bottleneck modality fusion network for obstructive sleep apnea diagnosis

Recommended citation: Hu Shuaicong, Yanan Wang, Liu Jian, Zhaoqiang Cui, Cuiwei Yang, Zhifeng Yao, and Junbo Ge. "IPCT-Net: Parallel information bottleneck modality fusion network for obstructive sleep apnea diagnosis." Neural Networks (2024): 106836.
Download Paper