Comparing performances of intelligent classifier algorithms for predicting type of pain in patients with spinal cord injury
Journal Title: Electronic Physician - Year 2017, Vol 9, Issue 7
Abstract
BACKGROUND AND AIM: In this study, performances of classification techniques were compared in order to predict type of pain in patients with spinal cord injury. Pain is one of the main problems in people with spinal cord injury. Identifying the optimal classification technique will help improve decision support systems in clinical settings. METHODS: A descriptive retrospective analysis was performed in 253 patients. We compared performances of "Bayesian Networks", "Decision Tree", neural networks: "Multi-Layer Perceptron" (MLP), and "Support Vector Machines" (SVM). Predictor variables were collected in data set in SCI patients referred to Shefa Neuroscience Research Center, Tehran, Iran from 2010 through 2016. Performances of classification techniques were compared using "Accuracy", "Sensitivity or True Positive Rate" (TPR), "Specificity or True Negative Rate" (SPC), "Positive Predictive Value" (PPV), "Negative Predictive Value" (NPV). RESULTS: MLP with Boosting technique was found to have the best accuracy (91%), best sensitivity (89%), best specificity (95%) best PPV (91%), and best NPV (96%) to predict spinal cord injury in this data set, given its good classificatory performance. CONCLUSION: Computer-aided decision support systems (CAD) are dependent on a wide range of classification methods such as statistical methods, Bayesian methods, deductive classifiers based on the state or case, decision-making trees and neural networks: Multi-Layer Perceptron. Neural network classifiers especially, are very popular choices for medical decision-making, with proven effectiveness in the clinical field
Authors and Affiliations
Nasrolah Nasr HeidarAbadi, Laleh Hakemi, Pirhossein Kolivand, Reza Safdari, Marjan Ghazi Saeidi
Keywords
Related Articles
- EP ID EP323603
- DOI 10.19082/4847
- Views 85
- Downloads 0
Analysis of the reasons for nurses’ confusion in relation to the concept of brain death from clinical and legal points of view
BACKGROUND: Nurses in intensive care units (ICU) play a key role in taking care of brain dead patients and they are often in contact with such patients given the high rate of brain deaths. Consequently, they are in a cha...
Investigating Knowledge Management Status among Faculty Members of Kerman University of Medical Sciences based on the Nonaka Model in 2015
INTRODUCTION: Education and research are two major functions of universities, which require proper and systematic exploitation of available knowledge and information. Therefore, it is necessary to investigate the knowled...
The effects of vitamin D supplementation on adiponectin level and insulin resistance in first-degree relatives of subjects with type 2 diabetes: a randomized double-blinded controlled trial
BACKGROUND: Despite the certain role of both vitamin D and adiponectin in the regulation of insulin sensitivity, the interaction between these two agents has remained uncertain. OBJECTIVE: The present study aimed to det...
Environmental interventions based on the Health Belief Model and the Ecological-social model in the continuation of consumption of rice, free from toxic metals
BACKGROUND AND AIM: Continuation of healthy nutritional behaviors is one of the important factors in effectiveness of educational intervention programs. The aim of this research is to compare the Health Belief Model and...
Impact of a Computerized Hospital Information System on the Staff workload in an Iranian Hospital Medical Records Department
Introduction: A hospital information system (HIS) is a comprehensive, integrated information system designed to manage the administrative, financial and clinical aspects of a hospital. As an area of medical informa...