Cardiovascular Health Monitoring with IoMT, ML, and FBG Sensors in Operation

Abstract

In today's healthcare industry, it is essential to continuously monitor cardiac parameters and Heart Rate Variability (HRV), necessitating systems that function effectively around the clock. Therefore, the emergence of the Internet of Medical Things (IoMT) technology provides a useful approach by employing various kinds of sensors for remote monitoring and analysis. This study presents a passive optical Fiber Bragg Gratings (FBG) sensor as a promising new technology for continuous monitoring of HRV and vital sign parameters. It also incorporates machine learning techniques to forecast heart conditions, improving the efficacy of remote monitoring systems.

Method: The study methodology utilizes an in-depth structural analysis approach employing finite element analysis to examine a specialized FBG sensor. This fabricated sensor demonstrates its ability to record cardiac signals in real-time. The key cardiac parameters such as Root Mean Square of Successive Differences (RMSSD), Heart Rate (HR), Standard Deviation of Normal-to-Normal (SDNN) intervals, percentage of successive NN intervals differing by more than 50 ms (pNN50), and real-time Body Temperature are extracted from the acquired FBG signal using sophisticated signal processing algorithms. Integrating machine learning models like the Radial Basic Function Neural Network (RBF) and Partial Least Square Regression (PLSR) offers valuable insights for early detection and management of heart disease.

Findings: The outcomes of various HRV parameters, including SDNN, HR, the percentage of consecutive NN intervals that are more than 50 ms apart, and RMSSD, obtained from the proposed FBG-based sensing system compared to a Standard Heart Variability monitor, result below 10% error. Moreover, among the RBF and PLSR models, RBF stands out for its significant success, delivering clinically acceptable metrics such as R-squared error and RMSE.

Novelty: Due to its passive nature, the FBG sensor can be vulnerable to various hazardous environments such as electromagnetic radiation and corrosive atmospheres. However, FBG sensors transmit signals through optical fibers; they can be employed for remote sensing in challenging conditions where conventional electrical sensors might fail. This approach is also innovative due to the fusion of state-of-the-art FBG sensors with an IoT-based decision support system, enabling seamless 24/7 continuous monitoring of cardiac parameters and HRV in real-time scenarios.