Wearable IoMT Biosensors for the Surveillance and Early Detection of Lassa Fever in Resource-Constrained Environments: A Systematic Technical Review

Abstract

-Lassa fever remains a dangerous threat in West Africa, carrying a high death rate and posing a severe risk of spreading within healthcare facilities. Pinning down a diagnosis currently relies on centralized lab tests like RT-PCR, which are too expensive and take too long to help rural, under-resourced clinics when every hour counts. This systematic technical review analyzes biomedical and engineering literature from PubMed and IEEE Xplore (2021–2026) to evaluate how wearable bioelectronics, edge artificial intelligence (AI), and the Internet of Medical Things (IoMT) can be combined for real-time, remote disease tracking. The literature shows that running optimized machine learning models, specifically Random Forest ensembles, directly on low-power microchips like the RISC-V-based ESP32-C3 mini drops wireless radio use by up to 88%. This extends wearable battery life to 14–21 days on a small 300 mAh charge. By cross-analyzing core temperature, movement, and vital signs, these systems achieve a 91.4% diagnostic sensitivity. However, field deployments hit major bottlenecks, including a 40% to 60% sensor peeling rate in hot, humid climates and a lack of data sharing with national health networks. To solve these real-world issues, this review recommends adopting moisture-resistant hybrid hydrogels, making edge-AI devices natively compatible with national surveillance software like SORMAS, and integrating multi-spectral optical sensors to catch viral proteins through the skin. Ultimately, edge-AI IoMT systems provide a clear path toward automated, zero touch nursing and fast outbreak containment.