Tartibian B, Fasihi L, Eslami R, Fasihi A. Comparing and Predicting Hepatic Encephalopathy Complications Using Random Forest Algorithm in Active Men. PTJ 2025; 15 (1) :81-90
URL:
http://ptj.uswr.ac.ir/article-1-663-en.html
1- Department of Exercise Physiology, Faculty of Physical Education and Sport Sciences, Allameh Tabataba’i University, Tehran, Iran.
2- Department of Physical Education and Sport Sciences, Faculty of Humanities, Tarbiat Modares University, Tehran, Iran.
3- Department of Physical Education and Sport Sciences, Faculty of Literature and Humanities, Malayer University, Malayer, Iran.
Abstract: (1741 Views)
Purpose: Liver diseases are among the most common disorders worldwide. For liver transplant patients, the presence of postoperative problems increases the complexity of postoperative nursing. Patients’ hospitalization is prolonged, and the costs of hospitalization increase. Data mining has become an easy way to predict diseases in recent years. Accordingly, this study compares and predicts the complications of hepatic encephalopathy in active and inactive men after liver transplantation.
Methods: The statistical population of this study was 852 people. Among them, 350 active men (162 healthy people and 188 people with encephalopathy symptoms) and 402 inactive men (210 healthy people and 192 people with encephalopathy symptoms) were selected as study subjects. These people underwent a liver transplant in the hospital between 2010 and 2011. The random forest algorithm and 14 features from laboratory records were used to predict encephalopathy complications after liver transplantation. Meanwhile, MATLAB software, version 2023, was used for data analysis.
Results: There was no significant difference in predicting encephalopathy complications by random forest algorithm between active and inactive men. Also, this study showed that the random forest algorithm using 14 features is 76.2% and 75.5% accurate for diagnosing hepatic encephalopathy after liver transplantation in active and inactive men, respectively.
Conclusion: Computer-based decision support systems can help to reduce poor healthcare decisions and the expenses associated with unneeded clinical trials in both active and inactive populations. Based on the accuracy of the random forest algorithm on the data, this system can assist clinicians in forecasting the risk of hepatic encephalopathy following transplantation with high accuracy and at a cheap cost.
Type of Study:
Research |
Subject:
General Received: 2024/07/29 | Accepted: 2024/09/1 | Published: 2024/01/13