Unveiling a Cutting-Edge Living Style-Based AI Model for Early Heart Disease Prediction

Healthcare, agriculture, cybersecurity, and finance have all become increasingly dependent on machine learning models. The advancements in machine learning have been particularly beneficial to the medical field. As long as machine-learning techniques are properly trained, they are capable of detecting numerous diseases at an early stage. By timely diagnosis and effective health management, numerous deaths arising from severe heart diseases can be prevented. This paper aims to introduce NNXBoost, a machine-learning model capable of detecting heart disease at an early stage. SMOTE is applied to balance the dataset based on an open-source dataset provided by the National Government. We then combine XGBoost with an Artificial Neural Network (ANN), utilizing the features of the neural network. Compared with other machine learning algorithms, the proposed model is evaluated based on accuracy, precision, recall, F1Score, and AUCROC metrics. A 99% accuracy rate is achieved by the suggested model, which outperforms other models. NNXBoost has the potential to contribute significantly to the field of medical science by detecting early heart disease.