Machine learning–based surveillance and forecasting of infectious diseases: a systematic review of modeling approaches and multi-source data integration
Year: 2026
Type: article
Study design: Systematic Review
Abstract: Background Enteric infections, including rotavirus gastroenteritis, place a heavy burden on children and low-resource health systems. Surveillance still depends on laboratory-confirmed case reporting that moves slowly through hospital information systems (HIS), electronic medical records (EMR), and laboratory information systems (LIS), offering little predictive lead time. Digital health infrastructure and artificial intelligence (AI) now offer a way to rebuild surveillance around combined, near-real-time data. Methods Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020, we searched PubMed and IEEE Xplore (through July 2026, with a supplementary PubMed search in September 2026) for studies using statistical, machine learning, deep learning, or multi-source AI-driven methods for infectious disease surveillance or forecasting, with attention to enteric infections and methodologically transferable work. Additional studies were identified through reference citation searching. Two reviewers screened records, extracted data, and assessed risk of bias (PROBAST for 23 prediction-model studies; narrative appraisal for 5 ecological association studies; contextual studies were not formally appraised). Results Thirty-three studies were included: 28 formal studies — statistical models ( n = 5), machine learning approaches ( n = 8), deep learning approaches ( n = 4), and multi-source digital surveillance ( n = 11) — and five contextual studies (environmental monitoring, virus–host association, simulation, surveillance-signal, and network studies) analyzed separately. Data sources broadened over time from meteorological and clinical records to EMR, telehealth, wastewater, internet-search, social-media, water-quality, and genomic streams. Machine learning and deep learning approaches were increasingly applied alongside conventional methods to model nonlinear and lagged exposure–response patterns and to integrate heterogeneous data streams, and multi-source systems—including wastewater-based and syndromic designs—reported earlier signal detection than single-source designs. Most evidence, however, is retrospective in design—spanning single-site to national and multinational datasets—and external validation and prospective deployment were largely absent. Conclusions The reviewed evidence suggests that AI-supported approaches may improve infectious disease surveillance by enabling earlier detection of epidemiological changes and supporting more timely public health responses. Operational use will depend less on retrospective accuracy than on external validation, interpretability, and integration with existing surveillance infrastructure.
Source: BMC Infectious Diseases
Institution: Kunming Medical University
Language: English
Subfield: Epidemiology
Field: Medicine
Domain: Health Sciences
Keywords: infectious disease surveillance, disease prediction, machine learning, deep learning, multi-source data fusion, gastrointestinal infections, rotavirus gastroenteritis, electronic health records, wastewater-based epidemiology, syndromic surveillance, internet search data, social media, environmental monitoring, exposure-response modeling, external validation, artificial intelligence in public health
Open Access status: gold
Estimated APC paid: $3,090
OpenAlex ID: W7236354246
