Predicting the Early Risk of Heart Disease using MABC with Self-Adaptive Bayesian Technique based on Lifestyle Factors

A heart attack occurs when the veins and arteries that provide blood to muscle get blocked. The hazards and obligations of modern life are shared equally by people of both sexes. When people have a heart attack, they often don't know what to do, so they put off getting help, which can make the injury worse and, in most cases, proves fatal. Medical diagnosis using data mining techniques has been explored by a number of researchers with promising outcomes. Different approaches can either predict a single disease or a large range of diseases. Improved health prediction is possible as well. This article discussed in depth the many methods of data categorization that are currently in use. In the field of IT, data categorization is common yet computationally demanding. In order to solve optimisation problems, metaheuristics are widely used. Metaheuristic methods can be used to increase a model's precision in computation. Artificial intelligence is widely used for early illness detection, severity appraisal, and prediction. To address this issue, our IoT platform employs an Optimised Self-Adaptive Bayesian algorithm (OSABA) to deliver more accurate diagnoses of HD. The MSABA is applied to the collected sensor data in order to ascertain its normalcy or abnormality. Patients, health care budgets, and disease progression can all benefit from this strategy. This research makes an effort to categorise and forecast human cardiac disease by using machine learning and metaheuristics. We may summarise the usefulness of the proposed OSABA by comparing it to already-existing models. Results metrics demonstrate the superiority of the proposed OSABA-based prediction system. Following the recommended procedure, we show that the OSABA outperforms state-of-the-art classifiers on the fullest datasets.