{
  "abstract": "Introduction Non-communicable diseases (NCDs) are increasingly contributing to morbidity and mortality in Africa. Existing NCD surveillance systems are often fragmented and rely on routine health data, population surveys or environmental metrics collected independently. Emerging applications in machine learning and geospatial analytics create new opportunities for integrated predictive modelling of NCDs, yet there is limited evidence of feasibility as well as methodological performance and policy relevance in African settings.The objective of this systematic review is to synthesise evidence from studies that combine NCD prediction with routine health data, survey data and environmental exposures in Africa. The review will examine methodological approaches, predictive performance, interoperability and implications for surveillance systems.Methods and analysis This systematic review protocol was prospectively registered with the International Prospective Register of Systematic Reviews (PROSPERO) under registration number CRD420251116003. We will search PubMed, Scopus, Web of Science, Cochrane Library, WHO Global Index Medicus and grey literature under sources such as Google Scholar; WHO, Africa CDC repositories and University of Zambia library resources from 2000 to 2025. Screening will be conducted independently by two reviewers using Rayyan for study selection and conflict resolution in accordance with Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. The risk of bias will be evaluated using the Prediction Model Risk of Bias Assessment Tool for predictive modelling. The results will be synthesised narratively as heterogeneity in methods and outcomes is anticipated.Ethics and dissemination Ethical approval is not required because this review will use data from published studies and will not involve human participants or primary data collection. Findings will be disseminated through peer-reviewed publication, conference presentations and sharing with relevant public health stakeholders.PROSPERO registration number CRD420251116003.",
  "authors": [
    {
      "affiliations": [
        "Public Health, University of Zambia, Lusaka, Zambia",
        "Workforce Development, Zambia National Public Health Institute, Lusaka, Zambia"
      ],
      "name": "Nyambe Sinyange"
    },
    {
      "affiliations": [
        "Mathematics & Statistics, University of Wyoming, Wyoming, Laramie, USA"
      ],
      "name": "Timothy Robinson"
    },
    {
      "affiliations": [
        "Natural and Applied Sciences, University of Zambia, Lusaka, Zambia"
      ],
      "name": "Jackson Phiri"
    },
    {
      "affiliations": [
        "Global Health, Stellenbosch University, Stellenbosch, South Africa"
      ],
      "name": "Veranyuy Ngah"
    },
    {
      "affiliations": [
        "School of Medicine, University of Zambia, Lusaka, Zambia"
      ],
      "name": "Allan Mayaba Mwiinde"
    },
    {
      "affiliations": [
        "School of Medicine, University of Zambia, Lusaka, Zambia"
      ],
      "name": "Isaac Fwemba"
    }
  ],
  "title": "Integration of routine health information, population surveys and environmental data for predictive modelling of non-communicable diseases in Africa: a systematic review protocol",
  "uid": "fdc81b43-48c5-5d5b-9374-dbe9064e2624"
}