On the application of multi-class classification in physical therapy recommendation
- Jing Zhang
- Peng Cao
- Douglas P. Gross
- Osmar R. Zaiane, University of Alberta (Database)
Recommending optimal rehabilitation intervention for injured workers that would lead to successful return-to-work (RTW) is a challenge for clinicians. Currently, the clinicians are unable to identify with complete confidence which intervention is best for a patient and the referral is often made in trial and error fashion. Only 58% recommendations are successful in our dataset. We aim to develop an interpretable decision support system using machine learning to assist the clinicians. We proposed an alternate ripper (ARIPPER) combined with a hybrid re-sampling technique, and a balanced weighted random forests (BWRF) ensemble method respectively, in order to tackle the multi-class imbalance, class overlap and noise problem in real world application data. The final models have shown promising potential in classification compared to human baseline and has been integrated into a web-based decision-support tool that requires additional validation in a clinical sample.
Citation
J. Zhang, P. Cao, D. Gross, O. Zaiane. "On the application of multi-class classification in physical therapy recommendation". Health Information Science and Systems, 1(15), December 2013.Keywords: | Random Forest, Injured Worker, Minority Class, Class Imbalance, Imbalanced Data |
Category: | In Journal |
Web Links: | Springer Link |
BibTeX
@article{Zhang+al:13, author = {Jing Zhang and Peng Cao and Douglas P. Gross and Osmar R. Zaiane}, title = {On the application of multi-class classification in physical therapy recommendation}, Volume = "1", Number = "15", journal = {Health Information Science and Systems}, year = 2013, }Last Updated: October 29, 2019
Submitted by Sabina P