Machine Learning Algorithms for Individual-Level Infectious Disease Risk Prediction: A Scoping Review and Bibliometric Analysis

Background: Infectious diseases remain a leading cause of morbidity and mortality worldwide. Early identification of individuals at high risk of infection can guide preventive interventions. Machine learning (ML) offers powerful tools for building predictive models that capture complex, non-linear relationships in large datasets. While many ML-based infection risk models have been developed, the landscape of algorithms, target diseases, and methodological quality has not been systematically mapped at the individual level. Objective: This scoping review aims to map the supervised ML algorithms used to predict individual-level risk of acquiring infectious diseases, describing the targeted diseases, populations, data sources, performance metrics, and identified research gaps. A parallel bibliometric analysis will examine publication trends, thematic clusters, and collaboration networks. Methods: The review will follow the Joanna Briggs Institute (JBI) methodology and the PRISMA Extension for Scoping Reviews (PRISMA-ScR). We will search PubMed, Scopus, Cochrane, Science Direct, and Institute of Electrical and Electronics Engineers from inception to May 2026. Studies will be included if they (a) involve human populations, (b) address an infectious disease, (c) apply at least one supervised ML algorithm, (d) predict individual-level risk of infection (not diagnosis or prognosis), and (e) report discrimination metrics (accuracy, sensitivity, or AUC). Two reviewers will independently screen titles/abstracts and full texts. Data will be charted on a piloted form. Results will be synthesised narratively and supplemented by bibliometric mapping of term co-occurrence, country collaboration, and publication trends using VOSviewer.