Date of Award

12-2012

Embargo Period

8-21-2013

Degree Type

Dissertation

Degree Name

Doctor of Philosophy (PhD)

Department

Biomedical Engineering

Advisor(s)

Takeo Kanade, Jessica Hodgins

Abstract

Advances in technology and research have been employed in recent years to develop efficient mechanisms to deliver home-based exercise therapy to patients suffering from knee osteoarthritis, a degenerative disease associated with aging. Essential to the success of a therapeutic home-exercise program is the quality of the motion performed by the patient. The unsupervised nature of home-based exercise may lead to incorrect exercise performance by patients; however, current home-based exercise programs do not provide mechanisms for monitoring the quality of motion performed or for providing feedback to the patient. This lack of support has been found to be a factor in patient non-compliance to home exercise programs.

Our goal is to provide a motion sensor-based system that can evaluate the quality of exercise to support home rehabilitation. We introduce the Quality Assessment Framework (QAF) that uses low-cost motion sensors with data processing and machine learning techniques to assess the quality of human motion performed during therapeutic exercises. Data from fifteen persons with knee osteoarthritis were collected in a laboratory environment, and a classifier was trained using multi-label learning methods to detect descriptive characteristics of the patient's motion. These characteristics represent errors in the exercise performance as well as variables, such as speed, that are regularly monitored by the patient's therapist.

Results from multi-label learning are presented and recommendations are made on requirements for an in-home therapeutic exercise system. A classifier, using Ensembles of Classifier Chains with a Support Vector Machine base classifier, provides the best method for assessing human motion quality in the QAF. Leave-one-out and leave-half-out testing provided us with information on the achievable level of generalizability for new patients whose motion is not contained in the training set. We found that a small amount of new patient data is required for good recognition of characteristics in exercise performances. The QAF can be adapted to the home therapy needs of conditions other than knee OA. We present a preliminary design of the InForm Exercise System that utilizes the QAF and has the potential to present feedback to patients completing home exercise programs.

Share

COinS