Related Experiment Video
Updated: Sep 20, 2025
Constructing and Visualizing Models using Mime-based Machine-learning Framework
Published on: July 22, 2025
Design of an artificial neural network to predict mortality among COVID-19 patients
Mostafa Shanbehzadeh1, Raoof Nopour2, Hadi Kazemi-Arpanahi3,4
1Department of Health Information Technology, School of Paramedical, Ilam University of Medical Sciences, Ilam, Iran.
Insights
Artificial neural networks (ANNs) effectively predict mortality risk in hospitalized COVID-19 patients. The back-propagation ANN model demonstrated superior performance, offering potential for improved clinical decision support and patient outcomes.
Area of Science:
- Medical Informatics
- Computational Biology
- Epidemiology
Background:
- The COVID-19 pandemic presents significant clinical challenges due to uncertainties in disease outcomes.
- Accurate prediction of mortality risk is crucial for managing hospitalized patients.
Purpose of the Study:
- To develop and evaluate artificial neural networks (ANNs) for predicting mortality risk in hospitalized COVID-19 patients.
- To identify key factors influencing COVID-19 mortality.
Main Methods:
- Retrospective analysis of 1710 hospitalized COVID-19 patients.
- Feature selection using Chi-square, Eta coefficient, and binary logistic regression (P < 0.05).
- Training and evaluation of feed-forward ANNs (back-propagation and distributed time delay) using MSE, EH, and AUC-ROC metrics.
Main Results:
- 13 significant variables were identified for predicting COVID-19 mortality.
- The back-propagation ANN (BP-ANN) model showed the best performance with a validation error of 0.067 and AUC-ROC of 0.888.
- BP-ANN achieved low error rates for most classified samples (0.049 and 0.05).
Conclusions:
- ANNs demonstrate acceptable performance in predicting mortality risk for hospitalized COVID-19 patients.
- The developed ANN-based clinical decision support system (CDSS) has the potential to enhance patient safety.
- Implementation of ANN models can aid in reducing disease severity and mortality.
Introduction:
The fast pandemic of coronavirus disease 2019 (COVID-19) has challenged clinicians with many uncertainties and ambiguities regarding disease outcomes and complications. To deal with these uncertainties, our study aimed to develop and evaluate several artificial neural networks (ANNs) to predict the mortality risk in hospitalized COVID-19 patients.
Material And Methods:
The data of 1710 hospitalized COVID-19 patients were used in this retrospective and developmental study. First, a Chi-square test (P < 0.05), Eta coefficient (η > 0.4), and binary logistics regression (BLR) analysis were performed to determine the factors affecting COVID-19 mortality. Then, using the selected variables, two types of feed-forward (FF) models, including the back-propagation (BP) and distributed time delay (DTD) were trained. The models' performance was assessed using mean squared error (MSE), error histogram (EH), and area under the ROC curve (AUC-ROC) metrics.
Results:
After applying the univariate and multivariate analysis, 13 variables were selected as important features in predicting COVID-19 mortality at P < 0.05. A comparison of the two ANN architectures using the MSE showed that the BP-ANN (validation error: 0.067, most of the classified samples having 0.049 and 0.05 error rates, and AUC-ROC: 0.888) was the best model.
Conclusions:
Our findings show the acceptable performance of ANN for predicting the risk of mortality in hospitalized COVID-19 patients. Application of the developed ANN-based CDSS in a real clinical environment will improve patient safety and reduce disease severity and mortality.
