Heart Failure Prediction Using LabVIEW-Based Support Vector Machine Model

Abstract

Heart failure (HF) is a grave medical condition that poses a significant threat to the global population, marked by high morbidity and mortality rates. Timely prediction of HF is crucial in enhancing diagnostic accuracy and improving treatment outcomes. In this context, various machine learning models have been developed to enable early HF prediction and assist physicians in diagnosis. The main objective of this study was to develop machine learning approaches to facilitate the diagnosis of chronic HF. The study employed models based on various combinations of feature categories, such as clinical features, echocardiographic data, and laboratory findings, to simulate the diagnostic process employed in clinical practice. To achieve precise HF prediction, a LabVIEW-based expert system employing support vector machine (SVM) models was proposed. The proposed method is both reliable and efficient, utilizing SVM models to accurately identify and classify individuals with HF. The effectiveness of the proposed method was evaluated using performance metrics such as accuracy, sensitivity, and specificity. The results of this study underscore the significance of using machine learning models in predicting HF and the need for further research to enhance early detection and treatment of HF. This research makes an important contribution to the field of predicting HF and has the potential to improve outcomes for patients. The results of the HF diagnosis were highly satisfactory, achieving high accuracy (83.57%), precision (85.23%), recall (84.36%), and F1 score (85.47%) when features from all categories were utilized.