Context: Heart disease is considered to be the leading cause of death around the world. Accurately predicting heart disease early is one of the most challenging tasks of the 21st century. Not only is accurate prediction important, but taking necessary precautions is also crucial. In this era, heart disease is regarded as the most prominent source of illness and death globally.

Objectives: The objective of this article is to predict heart disease early using IoT sensory data and an XAI framework. In this article, we have developed a framework that includes the integration of IoT sensors for real-time monitoring of patient data. The machine learning models used to analyze the sensory data utilize XAI to ensure the interpretability and transparency of these models' predictions.

Materials/Methods: This article aims to predict heart disease early using IoT sensory data and an XAI framework. We developed a framework integrating IoT sensors for real-time patient data monitoring. To analyze and predict these data, we used machine learning and deep learning algorithms. XAI techniques such as SHAP and LIME were applied to ensure model prediction interpretability and transparency.

Results: In this article, we employed machine learning and deep learning algorithms to predict heart disease early. The ML algorithms used were LOGR and SVM, while the DL algorithms were RNN and LSTM. It was observed that Support Vector Machine achieved a high accuracy rate of 97%, compared to other classifiers.