Development of an unsupervised machine learning algorithm for the prognostication of walking ability in spinal cord injury patients.

Journal: The spine journal : official journal of the North American Spine Society
PMID:

Abstract

BACKGROUND CONTEXT: Traumatic spinal cord injury can have a dramatic effect on a patient's life. The degree of neurologic recovery greatly influences a patient's treatment and expected quality of life. This has resulted in the development of machine learning algorithms (MLA) that use acute demographic and neurologic information to prognosticate recovery. The van Middendorp et al. (2011) (vM) logistic regression (LR) model has been established as a reference model for the prediction of walking recovery following spinal cord injury as it has been validated within many different countries. However, an examination of the way in which these prediction models are evaluated is warranted. The area under the receiver operators curve (AUROC) has been consistently used when evaluating model performance, but it has been shown that AUROC overemphasizes the most common event resulting in an inaccurate assessment when the data are imbalanced. Furthermore, there is evidence that the use of more advanced MLA, such as an unsupervised k-means model, may show superior performance compared to LR as they can handle a larger number of features.

Authors

  • Zachary DeVries
    Ottawa Spine Collaborative Analytics Network, The Ottawa Hospital, Ottawa, ON K1Y 4E9, Canada.
  • Mohamad Hoda
    Ottawa Spine Collaborative Analytics Network, The Ottawa Hospital, Ottawa, ON K1Y 4E9, Canada.
  • Carly S Rivers
    Rick Hansen Institute, Blusson Spinal Cord Centre, 6400-818 W. 10th Ave, Vancouver, BC V5Z 1M9, Canada.
  • Audrey Maher
    Ottawa Spine Collaborative Analytics Network, The Ottawa Hospital, Ottawa, ON K1Y 4E9, Canada.
  • Eugene Wai
    Ottawa Spine Collaborative Analytics Network, The Ottawa Hospital, Ottawa, ON K1Y 4E9, Canada; Division of Orthopaedic Surgery, Department of Surgery, Faculty of Medicine, University of Ottawa, The Ottawa Hospital, 1053 Caroling Ave, Ottawa, ON K1Y 4E9, Canada; Clinical Epidemiology Program, The Ottawa Hospital, Ottawa, ON K1Y 4E9, Canada.
  • Dita Moravek
    Ottawa Spine Collaborative Analytics Network, The Ottawa Hospital, Ottawa, ON K1Y 4E9, Canada; Ottawa Hospital Research Institute, Ottawa, ON K1Y 4E9, Canada.
  • Alexandra Stratton
    Ottawa Spine Collaborative Analytics Network, The Ottawa Hospital, Ottawa, ON K1Y 4E9, Canada; Division of Orthopaedic Surgery, Department of Surgery, Faculty of Medicine, University of Ottawa, The Ottawa Hospital, 1053 Caroling Ave, Ottawa, ON K1Y 4E9, Canada.
  • Stephen Kingwell
    Division of Orthopedic Surgery, The Ottawa Hospital, Ottawa, Canada.
  • Nader Fallah
    Praxis Spinal Cord Institute, Vancouver, BC, Canada.
  • Jérôme Paquet
    Département Sciences Neurologiques, Pavillon Enfant-Jésus, CHU de Québec, 1401 18e rue, Quebec, QC G1J 1Z4, Canada.
  • Philippe Phan
    Ottawa Spine Collaborative Analytics Network, The Ottawa Hospital, Ottawa, ON K1Y 4E9, Canada; Division of Orthopaedic Surgery, Department of Surgery, Faculty of Medicine, University of Ottawa, The Ottawa Hospital, 1053 Caroling Ave, Ottawa, ON K1Y 4E9, Canada; Clinical Epidemiology Program, The Ottawa Hospital, Ottawa, ON K1Y 4E9, Canada. Electronic address: pphan@toh.ca.