Automated heart disease prediction using improved explainable learning-based technique

• Published in: Neural computing & applications Vol. 36; no. 26; pp. 16289 - 16318
• Main Authors: Bizimana, Pierre Claver, Zhang, Zuping, Hounye, Alphonse Houssou, Asim, Muhammad, Hammad, Mohamed, El-Latif, Ahmed A. Abd
• Format: Journal Article
• Language: English
• Published: London Springer London 01.09.2024; Springer Nature B.V
• Subjects: Accuracy; Algorithms; Artificial Intelligence; Cardiovascular disease; Computational Biology/Bioinformatics; Computational Science and Engineering; Computer Science; Data Mining and Knowledge Discovery; Diagnosis; Harnesses; Heart diseases; Image Processing and Computer Vision; Machine learning; Original Article; Parameterization; Performance prediction; Probability and Statistics in Computer Science; Public health; Support vector machines; Venn diagrams; Cardiovascular disease; Feature selection; Venn diagram; Heart disease; Machine learning
• ISSN: 0941-0643; 1433-3058
• DOI: 10.1007/s00521-024-09967-6

Heart disease (HD) stands as a major global health challenge, being a predominant cause of death and demanding intricate and costly detection methods. The widespread impact of heart failure, contributing to increased rates of morbidity and mortality, underscores the urgency for accurate and timely prediction and diagnosis. This is crucial for effective prevention, early detection, and treatment, thereby reducing the threat to individual health. However, the early and precise prediction of HD remains a significant challenge. The complexity of medical data poses a considerable challenge for healthcare professionals, who are required to interpret and utilize this information swiftly for effective intervention. Addressing this gap, our study introduces a novel Improved Explainable Learning-Based Technique (IELBT) for HD prediction. This technique harnesses a strategic combination of feature selection, Venn diagrams, data normalization methods, optimized parameters, and machine learning algorithms, specifically tailored for predicting HD. We evaluated the performance of our model using the Alizadeh Sani HD dataset, aiming to accurately detect the presence or absence of the condition. Our results demonstrate that the IELBT, employing a support vector machine with a robust scaling approach, optimal parameterization, and a data split ratio of 70:30, achieves an impressive accuracy rate of 96.00%. Beyond achieving high accuracy, the IELBT outperforms similar models in existing literature and provides significant interpretability and explanation, essential elements in the field of medical diagnosis.