Integrated Empowered AI and IoT Approach for Heart Prediction

Abstract

The application of Internet of Things (IoT) technology has transformed the healthcare sector. Using IoT monitored data with AI, especially ML algorithms and statistical methodologies, we provide a study on the prediction of heart conditions. This study aims to create a precise and trustworthy predictive model that can efficiently analyse and understand the enormous quantity of data gathered from Internet of Things devices for monitoring heart health. The proposed methodology involves collecting real-time physiological data, such as systolic and diastolic blood pressure, heart rate, and BMI readings, from an IOT health monitoring device with different machine learning (ML) algorithms (random forest, decision tree, gradient booster classifier, and logistic regression) and statistical techniques (correlational analysis, data visualisation, ANOVA, and t-test) used to analyse and forecast heart conditions. Further, cross-validation techniques are used to evaluate the generalizability and robustness of the model. The performance of the predictive model is assessed using several criteria, including accuracy, precision, recall, and F1-score. The Gradient Boosting classifier worked well on the dataset for cardiac conditions, with an accuracy of almost 98%. Approximately 88% accuracy was attained. Naive Bayes functioned admirably, although it wasn't as effective as the Gradient Boost. Around 86% accuracy was attained. Overall, among the models, the Gradient Booster demonstrated the best accuracy, demonstrating its superior performance on the heart condition dataset. The outcomes of our tests and model building show good accuracy rates and reliable predictions for the prediction of heart conditions. In conclusion, the suggested method demonstrates the potential for early identification and prevention of cardiac illnesses using IoT-monitored data in conjunction with AI, improving patient outcomes and lowering healthcare expenditures.