Artificial intelligence and big data applications in chronic disease management: clinical outcomes, challenges, and future directions

Abstract

Aim To synthesize applications of Artificial Intelligence (AI) and big data in chronic disease management, evaluate clinical and economic outcomes, challenges, and future directions. Methods A comprehensive search was conducted across PubMed, Scopus, Web of Science, IEEE Xplore, and CINAHL for studies published between 2015-2025, following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 guidelines. This review was registered in PROSPERO (CRD420251036828). Inclusion criteria encompassed peer-reviewed empirical, narrative, and systematic studies focusing on AI and big data in chronic disease care. Twelve studies were appraised using validated appraisal tools appropriate to each study design, which were conducted across clinical, technological and public health settings, reflecting application of AI and big data in hospital, digital health platform and disease management. Results AI models achieved predictive accuracies between 88-96% across diabetes, chronic kidney disease (CKD), chronic obstructive pulmonary disease (COPD), and cardiovascular conditions. Outcomes included a 25% reduction in readmissions, a 30% decrease in CKD progression, and a 25% improvement in treatment adherence. Technologies included machine learning, electronic health record integration, wearable devices, and multi-omics platforms. Major challenges identified were data fragmentation, bias, and regulatory gaps. Conclusion The Artificial intelligence and big data offer transformative potential for chronic disease management from early prediction to personalized treatment, but realizing this requires addressing data fragmentation, ethical and privacy concerns, and ensuring equity and accountability through transparent, explainable AI.