On the Application of Multi-Class Classification in Physical Therapy Recommendation

• Author / Creator

  Zhang, Jing

• Selecting appropriate rehabilitation treatments for injured workers has been a challenging task for clinicians and health care funders. Currently, clinicians are unable to identify the optimal treatment for a patient with absolute confidence and are looking for assistance from other research fields, such as Machine Learning.
  This thesis aims at building a knowledge-based clinical decision support system using machine learning algorithms. We have found that with proper data preprocessing, the RIPPER algorithm can extract meaningful, editable and interpretable decision rules from a severely imbalanced multi-class clinical dataset.
  Moreover, the extracted rule set is integrated into our prototype Work Assessment Triage Tool (WATT), a web-based online decision support system. It has an easy-to-use interface and provides useful recommendations to help clinicians make better decisions.

• Subjects / Keywords

  • Class Imbalance
  • Recommendation System
  • Physical Therapy
  • Multi-Class Classification

• Graduation date

  Fall 2012

• Type of Item

  Thesis

• Degree

  Master of Science

• DOI

  https://doi.org/10.7939/R3GD9R

• License

  This thesis is made available by the University of Alberta Libraries with permission of the copyright owner solely for non-commercial purposes. This thesis, or any portion thereof, may not otherwise be copied or reproduced without the written consent of the copyright owner, except to the extent permitted by Canadian copyright law.