What question did this study set out to answer?

The review aims to summarize advancements in multimodal deep learning for lung disease classification and detection, identifying key architectures and challenges.

June 26, 2026Open Access

Multimodal Deep Learning Approaches for Lung Disease Detection: A Review

Key Points

The review aims to summarize advancements in multimodal deep learning for lung disease classification and detection, identifying key architectures and challenges.
Conducted a structured narrative review using databases such as PubMed, Scopus, IEEE Xplore, and Web of Science.
Reviewed studies from 2019 to 2024 focusing on multimodal deep learning in lung disease.
Extracted performance metrics, dataset characteristics, and limitations from peer-reviewed articles.
Convolutional neural networks (CNNs) and Transformer models showed high performance in chest X-ray classification.
Acoustic approaches leveraging spectrograms and self-supervised learning exhibit promising results but are dependent on specific datasets.
Integration of imaging and EHR modalities reveals translational barriers in clinical applications.

Abstract

Lung diseases are among the leading global causes of morbidity and mortality, and existing reviews on deep learning (DL) for pulmonary diagnosis rarely integrate imaging, acoustic, and electronic health record (EHR) modalities within a single framework. We aimed to synthesize the state of the art (2019–2024) in multimodal DL for lung disease detection and classification, identifying dominant architectures, performance benchmarks, and translational barriers across chest X-rays, CT scans, respiratory sounds, and EHRs. A structured narrative review was conducted using PubMed, Scopus, IEEE Xplore, and Web of Science, applying explicit inclusion criteria for peer-reviewed studies; performance metrics, dataset characteristics, and reported limitations were extracted. Research involving convolutional neural networks (CNNs) and more recent models such as Transformers have reported high performance in chest X-ray classification, whereas acoustic approaches based on spectrograms and self-supervised representations (e.g., Wav2Vec 2.0) show promising but dataset-dependent results.

Mark Helpful

Bookmark

Relay

View Full Paper