Optimized Cardiac and Circulatory Disorders Prediction: A High-Accuracy Model Selection Approach that utilizes Machine Learning and Deep Learning.

Abstract

Cardiac and Circulatory Disorders are among the primary causes of death globally, making early detection crucial for successful treatment and prevention, This research presents an advanced predictive cardiac and circulatory Disorders risk assessment model using machine learning and deep learning techniques. Three different datasets were analyzed, and the most accurate dataset was selected to train the models. Various algorithms, including Decision Tree, XGBoost(Extreme Gradient Boosting), Ada-Boost, Multi-Layer Perceptron (MLP), and Tabnet were implemented and compared. The MLP model attained the highest accuracy of 98% among all evaluated approaches, surpassing traditional machine learning models. The proposed system is designed to support healthcare professionals in identifying at-risk patients early, enabling timely intervention and improved healthcare results.

Introduction

Cardiac and circulatory disorders are leading causes of global mortality, with stress as a major risk factor. Early prediction and intervention are crucial to reduce fatalities. This research focuses on developing a robust predictive system for cardiovascular disease (CVD) by analyzing three different datasets with machine learning (ML) and deep learning (DL) models.

Prior studies have explored various ML/DL techniques such as Multi-Layer Perceptron (MLP), Recurrent Neural Networks (RNN) with Long Short-Term Memory (LSTM), Radial Basis Function Networks (RBFN), and ensemble models, achieving varying degrees of accuracy in CVD detection. Challenges include handling static tabular data, avoiding false positives, and improving prediction precision.

The methodology involves dataset collection, preprocessing, splitting, and training with algorithms like Random Forest, Decision Trees, Support Vector Machines, XGBoost, Naïve Bayes, MLP, and Tabnet. The MLP model achieved the highest accuracy (98%) on the best-performing dataset and was selected for deployment. A Flask web application was developed for real-time CVD risk prediction, demonstrating the practical utility of the approach.

Overall, the study highlights the effectiveness of advanced ML and DL techniques, particularly MLP, in early and accurate cardiovascular disease prediction, which can assist timely medical intervention and improve patient outcomes.

Conclusion

The integration of machine learning and deep learning methodologies has significantly transformed the accuracy and efficiency of predictive models in cardiovascular disease (CVD) risk assessment. These advanced computational approaches have pioneered new possibilities in analysing complex medical data, enabling earlier detection and more personalized strategies for managing heart-related conditions. By leveraging patterns within large datasets, these technologies enhance clinical decision-making and contribute to proactive healthcare interventions. enabling early diagnosis and risk assessment with high accuracy. The MLP Neural Network, achieving 98% accuracy, was selected as the optimal model and deployed via a Flask web application on the Render platform. Subsequent studies ought to prioritize on enhancing model interpretability, scalability, and real-world applicability to further improve patient outcomes.

References

v

Copyright

Copyright © 2025 A. Munipriya, Amjad Khan Patan. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.