Heart Risk Failure Prediction Using a Novel Feature Selection Method for Feature Refinement and Neural Network for Classification

Abstract

Diagnosis of heart disease is a difficult job, and researchers have designed various intelligent diagnostic systems for improved heart disease diagnosis. However, low heart disease prediction accuracy is still a problem in these systems. For better heart risk prediction accuracy, we propose a feature selection method that uses a floating window with adaptive size for feature elimination (FWAFE). After the feature elimination, two kinds of classification frameworks are utilized, i.e., artificial neural network (ANN) and deep neural network (DNN). Thus, two types of hybrid diagnostic systems are proposed in this paper, i.e., FWAFE-ANN and FWAFE-DNN. Experiments are performed to assess the effectiveness of the proposed methods on a dataset collected from Cleveland online heart disease database. The strength of the proposed methods is appraised against accuracy, sensitivity, specificity, Matthews correlation coefficient (MCC), and receiver operating characteristics (ROC) curve. Experimental outcomes confirm that the proposed models outperformed eighteen other proposed methods in the past, which attained accuracies in the range of 50.00–91.83%. Moreover, the performance of the proposed models is impressive as compared with that of the other state-of-the-art machine learning techniques for heart disease diagnosis. Furthermore, the proposed systems can help the physicians to make accurate decisions while diagnosing heart disease.

The Value of Python Programming in General Education and Comprehensive Quality Improvement of Medical Students Based on a Retrospective Cohort Study

“…Therefore, the construction of the Python course teaching model of computational thinking should be closely linked with the activity learning theory, and the teaching activities should be designed from the perspective of computational thinking so as to achieve the purpose of improving the comprehensive quality of students [ 28 ]. The same idea can be found in the diagnostic model proposed by Ashir Javeed et al [ 29 ], who have applied new methods to help doctors make accurate decisions in the diagnosis of heart disease.…”

Effect of Uterine Artery Ligation and Uterine Artery Embolization on Postpartum Hemorrhage Due to Uterine Asthenia after Cesarean Section and Its Effect on Blood Flow and Function of Uterine and Ovarian Arteries

“…Cesarean section is an effective measure to rescue puerpera, fetal life and solve dystocia, and the risk of postoperative PPH is significantly higher than that of vaginal delivery [ 4 ]. At present, PPH patients are mainly treated by drugs and surgery, and for those whose hemostatic effect is not obvious, surgery is used for treatment [ 5 ]. As an effective and rapid treatment for PPH, hysterectomy is suitable for all kinds of PPH that have failed to be rescued.…”

Effectiveness of Artificial Intelligence Models for Cardiovascular Disease Prediction: Network Meta-Analysis

“…Furthermore, 10 ML studies reported a total of 94,714 patients with heart failure. Of these, two prospective cohort studies [ 16 , 30 ] and one experimental study [ 11 ] used SVM for the prediction of heart failure, and two experimental studies [ 25 , 32 ] used ANN; two retrospective cohort studies [ 9 , 10 ] used LogR, and three studies [ 12 – 14 ] used GBM. The prediction of heart failure was associated with the result, which shows that GBM models achieved an average prediction accuracy of 91.10%, which is 4.40% higher than other models (e.g., ANN, SVM, and LogR).…”