Systematic Literature Review on Secured Electronic Health Monitoring System Using Edge Computing and Machine Learning

Abstract

This systematic literature review (SLR) looks at improvements in secure electronic health monitoring systems (EHMS) in Nigerian healthcare, with a focus on the integration of edge computing and machine learning (ML) between 2020 and 2025. Following the PRISMA paradigm, 57 peer-reviewed studies were analysed from Google Scholar, Scopus, IEEE Xplore, PubMed, and other reliable databases. The findings show that edge computing improves latency reduction, scalability, and data privacy by allowing for localised processing, whilst ML improves predictive analytics, anomaly detection, and decision support. Encryption, federated learning, intrusion detection, and compliance with Nigeria’s data protection policies (NDPR/NDPA) have all been cited as critical security procedures. Despite these developments, Nigeria still faces obstacles such as insufficient ICT infrastructure, a lack of clinical pilots, weak interoperability standards, and gaps in regulatory enforcement. The review finds that edge-ML-enabled EHMS can improve Nigeria’s healthcare system by allowing for resilient, privacy-preserving, and locally adaptive solutions. Future research should prioritise pilot deployments, energy-efficient machine learning, dataset building specific to Nigerian populations, and improved alignment with the Nigeria Data Protection Regulation/Nigeria Data Protection Acts (NDPR/NDPA) frameworks.