From fragmented to integrated surveillance in LMICs: digital pathways for outbreak detection and vaccine intelligence

Abstract

Background Low- and middle-income countries (LMICs) often rely on fragmented, disease-specific surveillance systems that produce delayed and incomplete data. Recent outbreaks, including COVID-19, have highlighted the urgent need for integrated, real-time digital surveillance to improve early outbreak detection and optimize vaccine deployment. Methods A structured narrative review was conducted following SANRA recommendations on the literature published between 2019 and 2025 on digital health, artificial intelligence (AI), genomic surveillance, and vaccine-information systems in LMIC infectious disease surveillance. PubMed, Scopus, WHO IRIS, and regional CDC repositories were searched using pre-specified Boolean strings. Over 312 records were screened; 46 unique references were selected for final synthesis. Results Traditional indicator-based systems in LMICs suffer from siloed reporting, poor connectivity, and workforce shortages. Digital platforms (DHIS2, mobile reporting, cloud dashboards) can unify multi-sector data and accelerate outbreak signals. AI tools offer predictive capabilities, though LMIC-specific external validation remains limited in only 14% of published models. Electronic immunization registries demonstrate measurable improvements: stockout reductions of up to 76%, coverage gains of 12.3%, and median reporting delays cut from 28 to 3 days. Key barriers include non-standardized data formats, intermittent connectivity, algorithmic bias, and data governance gaps. Conclusions Achieving integrated surveillance in LMICs requires adherence to interoperability standards, robust digital infrastructure, One Health data integration, and equitable data governance. A four-layer conceptual framework is presented. Investment in local capacity, supportive policy, and ethical AI frameworks is critical for sustainable innovation.