Real-time Chest X-Ray Distributed Decision Support for Resource-constrained Clinics
This system assists doctors in remote, resource-constrained clinics by enabling reliable real-time communication for medical diagnostics, though it is incremental as it applies existing methods to a new domain.
The paper tackled the problem of poor network infrastructure in remote healthcare by developing a real-time chest X-ray classification system using FastDDS middleware, achieving an accuracy of 88.61%, precision of 88.76%, recall of 88.49%, with an average throughput of 3.2 KB/s and latency of 65 ms.
Internet of Things (IoT) based healthcare systems offer significant potential for improving the delivery of healthcare services in humanitarian engineering, providing essential healthcare services to millions of underserved people in remote areas worldwide. However, these areas have poor network infrastructure, making communications difficult for traditional IoT. This paper presents a real-time chest X-ray classification system for hospitals in remote areas using FastDDS real-time middleware, offering reliable real-time communication. We fine-tuned a ResNet50 neural network to an accuracy of 88.61%, a precision of 88.76%, and a recall of 88.49\%. Our system results mark an average throughput of 3.2 KB/s and an average latency of 65 ms. The proposed system demonstrates how middleware-based systems can assist doctors in remote locations.