Exploring explainable AI features in the vocal biomarkers of lung disease

• Published in: Computers in biology and medicine Vol. 179; p. 108844
• Main Authors: Chen, Zhao, Liang, Ning, Li, Haoyuan, Zhang, Haili, Li, Huizhen, Yan, Lijiao, Hu, Ziteng, Chen, Yaxin, Zhang, Yujing, Wang, Yanping, Ke, Dandan, Shi, Nannan
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.09.2024; Elsevier Limited
• Subjects: AI transparency; Artificial intelligence; Biomarkers; Biomedical signal processing; Clinical AI applications; Computational Pulmonology; Decision making; Explainable artificial intelligence; Heterogeneity; Lung disease detection; Lung diseases; Machine learning interpretability; Public health; Pulmonary diagnostics; Reviews; Software; Vocal biomarkers; Voice analysis; Pulmonary diagnostics; Vocal biomarkers; Lung disease detection; AI transparency; Clinical AI applications; Explainable artificial intelligence; Machine learning interpretability; Voice analysis; Computational Pulmonology; Biomedical signal processing
• ISSN: 0010-4825; 1879-0534; 1879-0534
• DOI: 10.1016/j.compbiomed.2024.108844

This review delves into the burgeoning field of explainable artificial intelligence (XAI) in the detection and analysis of lung diseases through vocal biomarkers. Lung diseases, often elusive in their early stages, pose a significant public health challenge. Recent advancements in AI have ushered in innovative methods for early detection, yet the black-box nature of many AI models limits their clinical applicability. XAI emerges as a pivotal tool, enhancing transparency and interpretability in AI-driven diagnostics. This review synthesizes current research on the application of XAI in analyzing vocal biomarkers for lung diseases, highlighting how these techniques elucidate the connections between specific vocal features and lung pathology. We critically examine the methodologies employed, the types of lung diseases studied, and the performance of various XAI models. The potential for XAI to aid in early detection, monitor disease progression, and personalize treatment strategies in pulmonary medicine is emphasized. Furthermore, this review identifies current challenges, including data heterogeneity and model generalizability, and proposes future directions for research. By offering a comprehensive analysis of explainable AI features in the context of lung disease detection, this review aims to bridge the gap between advanced computational approaches and clinical practice, paving the way for more transparent, reliable, and effective diagnostic tools. •The review presents groundbreaking applications of explainable artificial intelligence (XAI) in lung disease detection through vocal biomarkers, showcasing a novel approach in pulmonary diagnostics.•Highlights how XAI enhances transparency and interpretability in AI-driven lung disease diagnostics, bridging the gap between complex AI models and clinical application.•Provides a thorough examination of various methodologies used in XAI, detailing their effectiveness in identifying connections between vocal features and lung pathology.•Stresses the importance of ethical considerations and patient privacy in the deployment of AI-based diagnostics, emphasizing the need for responsible and trustworthy AI use in healthcare.•Offers insights into future directions for XAI in pulmonary medicine, including potential innovations and the integration with emerging technologies for enhanced patient care.