article · Expert Systems
Real-time patient monitoring has expanded through advancements in information technology, connected devices, and miniaturised medical equipment, enabling remote healthcare delivery. Accurate detection of cardiac abnormalities remains a challenge, prompting the design of an effective arrhythmia classification framework. The described setup gathers electrocardiogram data from individuals across an Internet of Things network, transferring it to a hospital server where medical professionals can access it on demand. To classify the signals, a deep convolutional neural network is tuned using a custom optimisation algorithm inspired by predator hunting tactics and the herding behaviour of dogs to achieve better global convergence. When evaluated, the optimised deep learning model delivered reliable classification results, achieving an accuracy of 95.33 percent, a sensitivity of 94.92 percent, and a specificity of 97.57 percent.
Remote health tracking enables medical practitioners to monitor patients and deliver care without requiring continuous hospital stays. Reliable automated detection of heart arrhythmias ensures that doctors can quickly spot irregular cardiac activity. Improving the accuracy and sensitivity of such diagnostic algorithms reduces the likelihood of false alarms or missed conditions, supporting safer and more dependable tele-healthcare delivery.
The method is relevant to digital health providers, connected medical device manufacturers, and hospital IT services seeking automated cardiac diagnostics. It could enable real-time alert systems for remote patient care. The technology appears to be applied and tested at an algorithmic validation stage, meaning commercial deployment would require embedding the pipeline into approved medical software and demonstrating performance on diverse, real-time patient streams.
AI-generated from the published abstract. Always read the original work before citing.
Abstract The advancement of information technology, the Internet of Things (IoT), and several miniaturize equipment's enhances the healthcare field that provides real‐time patient monitoring, which helps to provide medication anywhere and anytime. However, accurate detection is still a challenging task for which an effective classification model is introduced in this research. The proposed method is the Enhanced Hunt optimization based Deep convolutional neural network (Enhanced Hunt based‐Deep CNN), in which the Enhanced Hunt optimization algorithm (EHOA) is developed by fusing the hunting habit of the predator and the herding characteristics of herding dog for enhancing the global optimal convergence. Here, the ECG signal from the individuals is collected using the IoT network and stored in the Hospital server, which is accessed by the doctor when requested, the classification is performed using the Enhanced Hunt based‐Deep CNN and the performance revealed the effectiveness with the accuracy, sensitivity, and specificity of 95.33%, 94.92%, and 97.57%.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1111/exsy.13298
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
