Feature Selection and Classification in Supporting Report-Based Self-Management for People with Chronic Pain
| Autor: | Yan Huang, Norman D. Black, Paul McCullagh, Kevin E. Vowles, Huiru Zheng, Chris D. Nugent, Lance M. McCracken |
|---|---|
| Rok vydání: | 2011 |
| Předmět: |
Biopsychosocial model
Feature extraction Feature selection Machine learning computer.software_genre User-Computer Interface Artificial Intelligence Surveys and Questionnaires Humans Pain Management Medicine Medical Informatics Applications Electrical and Electronic Engineering Analysis of Variance Chi-Square Distribution business.industry Supervised learning General Medicine Computer Science Applications Self Care Support vector machine Statistical classification Ranking Area Under Curve Chronic Disease Artificial intelligence business computer Classifier (UML) Algorithms Biotechnology |
| Zdroj: | IEEE Transactions on Information Technology in Biomedicine. 15:54-61 |
| ISSN: | 1558-0032 1089-7771 |
| DOI: | 10.1109/titb.2010.2091510 |
| Popis: | Chronic pain is a common long-term condition that affects a person's physical and emotional functioning. Currently, the integrated biopsychosocial approach is the mainstay treatment for people with chronic pain. Self-reporting (the use of questionnaires) is one of the most common methods to evaluate treatment outcome. The questionnaires can consist of more than 300 questions, which is tedious for people to complete at home. This paper presents a machine learning approach to analyze self-reporting data collected from the integrated biopsychosocial treatment, in order to identify an optimal set of features for supporting self-management. In addition, a classification model is proposed to differentiate the treatment stages. Four different feature selection methods were applied to rank the questions. In addition, four supervised learning classifiers were used to investigate the relationships between the numbers of questions and classification performance. There were no significant differences between the feature ranking methods for each classifier in overall classification accuracy or AUC (p >; 0.05); however, there were significant differences between the classifiers for each ranking method (p |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|