Related Experiment Video
Updated: Oct 26, 2025
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
Published on: August 16, 2020
Construction data mining methods in the prediction of death in hemodialysis patients using support vector machine,
Salman Khazaei1, Somayeh Najafi-GhOBADI2, Vajihe Ramezani-Doroh3,4
1Research Center for Health Sciences, Hamadan University of Medical Sciences, Hamadan, Iran.
Insights
Logistic regression best predicts death in hemodialysis patients. Key survival factors include female gender, older age, addiction, low iron, C-reactive protein, and low urea reduction ratio.
Area of Science:
- Nephrology
- Data Science
- Biostatistics
Background:
- Chronic kidney disease (CKD) significantly contributes to global morbidity and mortality.
- Identifying modifiable factors is crucial for managing hemodialysis patients and informing treatment decisions.
Purpose of the Study:
- To develop an optimal predictive model for mortality in hemodialysis patients using data mining.
- To identify key predictors of death in this patient population.
Main Methods:
- Analysis of a dataset comprising 857 hemodialysis patients.
- Evaluation of 31 potential risk factors associated with mortality.
- Comparison of four machine learning classifiers: support vector machine, neural network, logistic regression, and decision tree.
Main Results:
- Logistic regression achieved the highest overall accuracy (0.71), sensitivity (0.69), and specificity (0.72).
- Logistic regression also demonstrated the highest positive likelihood ratio (2.48) and the lowest negative likelihood ratio (0.43).
Conclusions:
- Logistic regression outperformed other models in predicting mortality among hemodialysis patients.
- Significant predictors of death identified include female gender, advanced age at diagnosis, addiction, low iron levels, positive C-reactive protein, and a low urea reduction ratio (URR).
Objectives:
Chronic kidney disease (CKD) is one of the main causes of morbidity and mortality worldwide. Detecting survival modifiable factors could help in prioritizing the clinical care and offers a treatment decision-making for hemodialysis patients. The aim of this study was to develop the best predictive model to explain the predictors of death in Hemodialysis patients by data mining techniques.
Methods:
In this study, we used a dataset included records of 857 dialysis patients. Thirty-one potential risk factors, that might be associated with death in dialysis patients, were selected. The performances of four classifiers of support vector machine, neural network, logistic regression and decision tree were compared in terms of sensitivity, specificity, total accuracy, positive likelihood ratio and negative likelihood ratio.
Results:
The average total accuracy of all methods was over 61%; the greatest total accuracy belonged to logistic regression (0.71). Also, logistic regression produced the greatest specificity (0.72), sensitivity (0.69), positive likelihood ratio (2.48) and the lowest negative likelihood ratio (0.43).
Conclusions:
Logistic regression had the best performance in comparison to other methods for predicting death among hemodialysis patients. According to this model female gender, increasing age at diagnosis, addiction, low Iron level, C-reactive protein positive and low urea reduction ratio (URR) were the main predictors of death in these patients.
Related Concept Videos
01:19Survival Tree
Building a Survival Tree
Constructing a...
01:27Dialysis
Acute kidney injury develops suddenly and can be caused by pre-renal causes (e.g., hypovolemia, shock), intrinsic renal causes (e.g., acute tubular necrosis), or post-renal causes (e.g., urinary obstruction). In contrast, chronic renal failure progresses gradually over time and is often...
01:25Hemodialysis I: Introduction
01:24Kaplan-Meier Approach
01:25Hemodialysis III: Nursing Management
01:30Extracorporeal Removal of Drugs: Peritoneal Dialysis and Hemodialysis