Early-Stage Risk Prediction of Non-Communicable Disease Using Machine Learning in Health CPS

Abstract

Cyber-Physical Systems (CPS) embed computation and communication capability into its core to regulate physical processes and seamlessly mediate between the cyber and the physical world for various control and monitoring tasks. Health CPS, a variant of CPS in the healthcare sector, acts as a health monitoring system to dynamically capture, process, and analyze health sensor data through integrated internet of things (IoT)-enabled cyber-physical processes. These systems can suitably support patients suffering from non-communicable diseases (NCDs) or who are at risk of suffering from those. Identifying the risk of NCDs, such as heart disease and diabetes, requires artificial intelligence (AI) techniques into the core of health CPS. Recently, there has been growing interest to incorporate machine learning into CPS, which can facilitate the disease classification, detection, monitoring, and prediction of several NCDs. However, there is a shortage of visible work that focus on early-stage risk prediction of these diseases. In this work, we propose a novel machine learning based health CPS framework that addresses the challenge of effectively processing the wearable IoT sensor data for early risk prediction of diabetes as an example of NCDs. In the experiment, a verified diabetic dataset has been used for training, while the testing has been performed on an artificially generated data collection from sensors. The experiment with several machine learning algorithms shows the effectiveness of the proposed approach in achieving the maximum precision from the Random Tree algorithm, which requires a minimum time of 0.01s to construct a model and obtains 94% accuracy to predict the probability of diabetes at an early point.

Empowering Healthcare With Cyber-Physical System—A Systematic Literature Review

“…In [118], a Fog-Cloud medical cyber-physical system called FCMCPS-COVID is proposed, utilizing AI techniques to enable early detection, prevention, and control of the Covid-19 pandemic. The system adopts a Fog-Cloud architecture to process and analyze heterogeneous data collected from the medical sensors and R. Ferdousi et al [119] introduce a closed-loop, machine learning-driven HCPS for early prediction of diabetes risk. This approach leverages the novel concept of using a validated training dataset and a dynamic testing dataset, enabling the application of machine learning to real-time data obtained from the sensors.…”

Machine Learning for Cardiovascular Disease Risk Assessment: A Systematic Review

“…The institution's commitment to high-quality evidence-based research is evident in this study. ASHIR JAVEED et-al (2019) [35] The RSA-RF learning system for heart failure prediction that was proposed in this research successfully combines the advantages of the random search and random forest algorithms to improve prediction accuracy. According to the study, the RSA-RF system surpasses 11 current approaches for detecting heart failure and other wellknown machine learning models, leading to an increase in prediction accuracy of 3.3%.…”

Survey Paper Artificial and Computational Intelligence in the Internet of Things and Wireless Sensor Network

“…Another example was proposed by Yu et al The processing is use LSTM (long short-term memory) deep learning network methods to process all IoT data and provide semantic services such as New York City temperature forecasting [222]. Besides those two computational intelligence methods, there are a lot of other methods to process and provide semantic services such as KNN [223], DTMC (Discrete-time Markov chain) [224], SNN [225], CNN [226], Random Tree [227], and more. We can summarize Computational Intelligence in IoT WSN Functionality in Table 2.…”