Synergizing Fusion Modeling for Accurate Cardiac Prediction Through Explainable Artificial Intelligence

Artificial Intelligence (AI) and Machine Learning (ML) play a crucial role in developing disruptive healthcare technologies since they address the needs of consumers by providing precise and effective diagnostic and decision-making capabilities. The influence of these factors on diagnosing and making decisions is especially noteworthy when collecting valuable information from healthcare data. This work offers “AC2” (Accurate Cardiac Classification), a hybrid deep learning model that correctly detects cardiovascular disease (CVD) and provides meaningful insights. Convolutional neural networks and the Light Gradient Boosting Model integrate well in the “AC2” model, simplifying feature learning and predictions. Using the CDC’s Behavioral Risk Factor Surveillance System (BRFSS) dataset, the proposed method outperforms current algorithms in accuracy, precision, recall, and F1 score. This dataset collects reliable, state-specific data on preventive health practices and risk behaviors related to chronic illnesses, injuries, and avoidable infections in adults, catering to the information needs of healthcare consumers. The “AC2” model’s outstanding forecast accuracy is further improved by integrating an explainable AI methodology, specifically emphasizing SHAP’s local and global explanations. These explanatory insights clarify the model’s decision-making process. With healthcare technology’s advancement and the requirement for efficient data analysis to gather information, the “AC2” model’s accuracy and comprehensibility may substantially improve healthcare professionals’ diagnosis and treatment skills, benefiting healthcare consumers.