The rapid growth of healthcare data necessitates advanced analytical techniques to enhance the prediction and management of cardiological diseases. Traditional methods like Logistic Regression, Support Vector Machine, Random Forest, and Decision Tree often fall short, relying on basic statistical analyses that overlook complex data relationships, resulting in reduced predictive accuracy and inadequate decision-making support. This research presents a robust model utilizing Convolutional Neural Networks and Long Short-Term Memory (CNN-LSTM) networks with attention mechanism for cardiological disease prediction. By leveraging CNNs for feature extraction from spatial data and LSTMs for sequential data analysis, the proposed model effectively captures intricate patterns in large healthcare datasets, significantly improving prediction capabilities. The significance of this approach lies in its ability to provide timely and accurate predictions, facilitating proactive clinical interventions. Performance evaluation metrics, including accuracy, precision, recall, and F1-score, indicate substantial improvements over traditional methods. The CNN-LSTM model is particularly applicable in real-time monitoring systems and telehealth applications, offering healthcare providers valuable insights for early diagnosis and optimized patient management in cardiology. © 2025 Elsevier B.V., All rights reserved.