Toward Intelligent Optimization of Brace Treatment for Adolescent Idiopathic Scoliosis

• Author / Creator

  Chalmers, David E.

• Electronic decision support systems have the potential to improve healthcare practices in many domains. This thesis investigates the use of data-driven decision support to help optimize brace treatment for children who have Adolescent Idiopathic Scoliosis (AIS).
  AIS is a spinal deformity affecting 2-3% of adolescents. If left untreated, AIS may progress (worsen), negatively affecting the adolescent’s emotional, social, and physical wellbeing and eventually necessitating surgical intervention. Brace treatment is the most common non-surgical treatment for AIS; in brace treatment a back brace applies corrective pressure to the torso, with the goal of preventing progression. Patients’ faithfulness in wearing the brace as long and as tightly as prescribed affects treatment outcome. But the outcome also depends on patient characteristics, the nature of the deformity, and many other factors in addition to compliance. The relationships between these factors and treatment outcome are complex and not perfectly understood; as a result, brace treatment outcome is difficult to predict. As technology improves our ability to predict treatment outcome, the ability to optimize treatment protocols for individual AIS patients should improve as well.
  This research envisions a complete system for collecting patient data and using it to generate treatment recommendations for new patients. In this system, electronic sensors collect information about patients’ brace-wear habits, machine-learning techniques use sensor and other data to train prediction models, and these models’ predictions of new patients’ outcomes are used to customize treatment protocols to those patients. This work developed the components of this system and implemented them in a scalable hardware/software platform. Data from 31 patients was collected and processed by the system. Simulations were used to provide an initial assessment of the system’s treatment recommendations.

• Subjects / Keywords

  • Brace Treatment
  • Machine Learning
  • Scoliosis
  • Decision support systems

• Graduation date

  Fall 2015

• Type of Item

  Thesis

• Degree

  Doctor of Philosophy

• DOI

  https://doi.org/10.7939/R3DF6KF1P

• 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.