Review Article
Published: 30 September, 2026 | Volume 9 - Issue 1 | Pages: 61-79
The COVID-19 pandemic accelerated the development and application of artificial intelligence (AI) across disease surveillance, epidemiological forecasting, medical imaging, prognosis, drug discovery, vaccine research, contact tracing, and public-health decision support. This review synthesizes the literature on these applications while critically examining the evidence needed for translation into clinical and public-health practice. A structured literature-search and selection framework was used to organize evidence published from the emergence of COVID-19 through the contemporary literature, with emphasis on peer-reviewed studies and recent reviews. The evidence was synthesized according to the pandemic-response pathway: early warning and surveillance; diagnosis and differential diagnosis; severity and prognosis; clinical and resource decision support; therapeutic and vaccine discovery; genomic surveillance; and privacy-preserving and responsible AI. Across these domains, AI demonstrates potential to process heterogeneous data and support time-sensitive decisions, but reported performance does not by itself establish clinical utility. Recurring limitations include small or non-representative datasets, dataset shift, limited external validation, class imbalance, information leakage, insufficient calibration and interpretability, privacy and security risks, and uncertainty about workflow integration and regulatory accountability. Recent systematic reviews also indicate that multimodal, federated, and privacy-preserving approaches remain less developed than conventional centralized models. The principal contribution of this review is a unified critical framework that links technical performance with data quality, external validation, clinical relevance, fairness, privacy, interpretability, and implementation readiness. The review therefore identifies not only where AI has been applied to COVID-19, but also the conditions required for responsible translation to clinical practice and future pandemic preparedness.
Read Full Article HTML DOI: 10.29328/journal.ijcmbt.1001042 Cite this Article Read Full Article PDF
COVID-19; SARS-CoV-2; Artificial intelligence; Machine learning; Deep learning; Diagnosis, prognosis; Epidemiological forecasting, drug discovery; Responsible AI
If you are already a member of our network and need to keep track of any developments regarding a question you have already submitted, click "take me to my Query."