Data science applications for non-communicable disease prevention and control in Africa: a systematic review protocol

Akinkunmi Paul Okekunle, Muideen Tunbosun Olaiya, Paul Olowoyo, Grace Ajuwon, Alison Annet Kinengyere, Judit Kumuthini, Osahon Jeffery Asowata, Onoja Matthew Akpa, Adekunle Fakunle, Shakuntala Baichoo, Folakemi Odedina, Yosr Hamdi, Charles Agyemang, Bruce Ovbiagele, Mayowa Owolabi

Abstract

Aim: This systematic review protocol describes the proposed method for evaluating evidence from original articles to understand the benefits, opportunities, and challenges of using data science for non-communicable disease (NCD) prevention and control in Africa.
Methods: Literature searches will be implemented in five scientific databases and one search engine using predefined keywords/MeSH terms to identify relevant articles. At least two reviewers will independently screen, appraise, extract, and summarise data from eligible articles using predefined inclusion criteria.
Results: This systematic review will consider primary studies from articles that applied data science methods (such as artificial intelligence, machine learning, and risk or prognosis model algorithms, among others) to address NCD prevention and control exclusively among Indigenous Africans.
Conclusion: Findings from this systematic review could serve as a roadmap to guide future initiatives to apply data science methods to revolutionise NCD prevention and control in Africa.