Title: Heart Failure Prediction Using Artificial Neural Networks
Authors: Abdullah Osama Abu Salama , Samy S. Abu-Naser
Volume: 10
Issue: 7
Pages: 41-48
Publication Date: 2026/07/28
Abstract:
Heart failure is one of the serious medical conditions that may lead to death if it is not diagnosed and monitored properly. Artificial Neural Networks can be used to analyze medical data and support decision-making by predicting patient outcomes. In this research, the Heart Failure Clinical Records dataset was used to build a neural network model using JustNN software. The dataset was prepared and saved as a CSV file, then imported into JustNN. Twelve input features were used, including age, anaemia, diabetes, ejection fraction, serum creatinine, serum sodium, smoking, and time. The output variable was DEATH_EVENT, which indicates whether the patient died during the follow-up period. The dataset was divided into training and validation sets, and the neural network was trained to predict the output. The results showed that artificial neural networks can be used as a useful tool for predicting heart failure outcomes based on clinical records.