Real-Time Coronary Heart Disease Prediction using Various Machine Learning Techniques and Internet of Things

Coronary heart disease (CHD) is the major cause of death worldwide and can be responsible for approximately 17.6 million deaths, equivalent to 32% of deaths in the whole world. Certain heart conditions, like arrhythmias and coronary artery disease, continue to cause deaths in the world in a significant manner. Accurately predicting the likelihood of a patient developing heart disease is the major challenge in data analysis in the medical field. This project aims to utilize various methods to design an effective machine learning (ML) approach for earlystage coronary heart disease prediction. Initially, the physiological data can be collected by the biometric sensors. A Microcontroller receives the collected data from the sensors, either signals or data. Collected information received through a sensory system is processed in the input to a controller, and then it will be output through the IEEE 802.11a Wi-Fi connectivity module to the IoT analysis platform. Machine learning (ML) offers a promising solution by improving diagnostic accuracy and enabling datadriven predictions. The cloud server connects with the processing platform, which applies machine learning techniques to analyze the data. These include organizing the data into a dataset, applying pre-processing and feature extraction techniques to clean and refine the data, and using classification and algorithms for predicting the probability of heart disease. The results can be validated by comparing predictions with a trained machinelearning model to ensure accuracy and continuous improvement for the patients. Finally, the output is transmitted to the user's device, such as a smartphone, providing a clear prediction of heart disease risk, and a dataset of patient bodily statistics was collected in compliance with ethical guidelines, including obtaining prior consent from both the doctor and patients.