Title: Heart Failure Prediction Using Artificial Neural Networks and JustNN
Authors: Qutaiba Jomah Mohammed Alnajjar, Samy S. Abu-Naser
Volume: 10
Issue: 7
Pages: 66-76
Publication Date: 2026/07/28
Abstract:
Artificial Neural Networks (ANNs) are important machine learning techniques used for classification and prediction problems. In healthcare, early prediction of heart failure may support clinical decision-making and help identify high-risk patients. This research presents the application of a feedforward Artificial Neural Network to predict heart failure events using the Heart Failure Clinical Records dataset from the UCI Machine Learning Repository. The dataset was prepared, imported into JustNN software, divided into training and validation subsets, and used to train a neural network model. The model demonstrated the ability to learn patterns from structured clinical data and showed promising potential for heart failure prediction. However, further quantitative evaluation using accuracy, precision, recall, F1-score, validation error, and confusion matrix analysis is required before the model can be considered reliable for real clinical use.