Smart Cardiac Care: Leveraging IoT, Healthcare 4.0, and Fiber Bragg Grating Sensors with Machine Learning Algorithms

Abstract

Recent developments in home-based monitoring, telerehabilitation, mobile health, and other aspects of the healthcare industry have led to the digitalization of cardiac parameter monitoring; including Heart Rate Variability (HRV) analysis. The Internet of Medical Things (IoMT) technology in conjunction with different sensors presents an acceptable solution towards the above advancements. Fiber Bragg grating (FBG) optical sensors are perfect for continuous cardiac monitoring if combined with machine learning (ML).The main goal of the study is to detect heart forces and vibrations in real time, which will result in the development of a novel FBG sensor. This sensitive sensor has been developed especially for the best possible detection of heart vibrations using PDMS polymer. Digital Signal Processing techniques enable the measurement of the mean Standard Deviation of Normal to the Normal intervals (SDNN), Heart Rate (HR) and the Root Mean Square of Successive Differences (RMSSD), apart from Body Temperature. The work also discusses about an IoMT-based recommendation system using HRV and statistical parameters to compare different models of ML such as RBF, PLSR, RF, FNN and DNN. The Random Forest algorithm's high precision is demonstrated by its values for R-squared error (1.000) and RMSE (0.5763). Finally, the study concludes with a comprehensive approach to cardiac monitoring and the early diagnosis of heart disease in healthcare settings using the Decision Support System (DSS) in conjunction with IoMT.