ARTIFICIAL INTELLIGENCE FOR RESPIRATORY DISEASE DIAGNOSIS: A PRISMA 2020 SYSTEMATIC REVIEW OF CURRENT CLINICAL APPLICATIONS AND FUTURE DIRECTIONS

Abstract

Respiratory diseases remain among the leading causes of morbidity and mortality worldwide, imposing a substantial clinical and economic burden. Early and accurate diagnosis is essential for improving patient outcomes, yet conventional diagnostic approaches often depend on expert interpretation, are resource intensive, and may be limited by interobserver variability. Reviews in pulmonary medicine also emphasize that successful implementation requires rigorous validation, regulatory oversight, and clinically meaningful evaluation beyond algorithmic accuracy. To systematically evaluate current evidence regarding the diagnostic applications, clinical performance, advantages, limitations, and future directions of artificial intelligence technologies in respiratory disease diagnosis. This systematic review will be conducted according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA 2020) guidelines. Eligible studies will be identified through comprehensive searches of PubMed/MEDLINE, Embase, Scopus, Web of Science, IEEE Xplore, and the Cochrane Library. Studies evaluating AI-based diagnostic models for respiratory diseases in human populations will be considered. Two reviewers will independently perform study selection, data extraction, and quality assessment. This review aims to provide clinicians, researchers, and policymakers with a comprehensive synthesis of current evidence regarding AI-assisted respiratory disease diagnosis and to identify priorities for future research and clinical translation.