Real-Time Cloud-Based Patient-Centric Monitoring Using Computational Health Systems

• Published in: IEEE transactions on computational social systems Vol. 9; no. 6; pp. 1613 - 1623
• Main Authors: Chakraborty, Chinmay, Kishor, Amit
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.12.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Artificial intelligence (AI); Cardiovascular disease; Classification; Cloud computing; Computational modeling; Diseases; fog computing; health; Health care; Health services; Heart; Heart diseases; Internet of Medical Things (IoMT); Internet of Things; Machine learning; machine learning (ML); Medical diagnostic imaging; Medical electronics; Medical services; Monitoring; Real time; Remote monitoring; Telemedicine; User satisfaction; Wearable technology
• ISSN: 2329-924X; 2373-7476
• DOI: 10.1109/TCSS.2022.3170375

In many sectors, including healthcare services, Internet of Things (IoT) systems are growing rapidly, providing promising technological, economical, and social potential. Healthcare services can be improved with IoT capabilities, including remote patient monitoring, diagnosis of medical issues in real-time, and more, all of which improves both the quality and the satisfaction of human users. The Internet of Medical Things (IoMT) is gaining momentum as wearable devices, and their numerous health monitoring applications increase popularity. The IoMT plays a significant role in reducing death rates by detecting diseases early. Prediction of heart disease is an essential challenge in clinical dataset analysis. The proposed research aim is to employ machine learning (ML) classification algorithms to predict heart disease. The IoMT-based cloud-fog diagnostics for heart disease have been proposed. Fog layer is used to quickly analyze patient data using ML classification techniques. The performance of the healthcare model is evaluated with different simulations and achieves 97.32% accuracy, 97.58% recall, 97.16% precision, 97.37% <inline-formula> <tex-math notation="LaTeX">F1 </tex-math></inline-formula>-measure, 96.87% specificity, and 97.22% <inline-formula> <tex-math notation="LaTeX">G </tex-math></inline-formula>-mean, which has significant improvement as compared with previous models.