Development of a Machine Learning Algorithm for Predicting In-hospital and 1-year Mortality After Traumatic Spinal Cord Injury

Nader Fallah, Vanessa K. Noonan, Zeina Waheed, Carly S. Rivers, Tova Plashkes, Manekta Bedi, Mahyar Etminan, Nancy P. Thorogood, Tamir Ailon, Elaine Chan, Nicolas Dea, Charles Fisher, Raphaele Charest-Morin, Scott Paquette, SoEyun Park, John T. Street, Brian K. Kwon, Marcel F. Dvorak

[published online August 19, 2021] Spine J. 2021. doi: https://doi.org/10.1016/j.spinee.2021.08.003

Summary

Current prognostic tools such as the Injury Severity Score (ISS) that predict mortality following trauma do not adequately consider the unique characteristics of traumatic spinal cord injury (tSCI).

Using machine learning techniques, the aim of the research team was to develop and validate a prognostic tool that can predict mortality following a tSCI. The study found that the tool — the Spinal Cord Injury Risk Score (SCIRS) — predicted in-hospital and 1-year mortality following tSCI more accurately than ISS. Further validation using larger sample sizes and independent datasets is needed to assess its reliability and to evaluate using it as an assessment tool to guide clinical decision-making and discussions with patients and families.

Data from the Rick Hansen SCI Registry was used to support this study.

View the open access article here.

Acknowledgment

The authors would like to thank the Vancouver Spine Research Program team at Vancouver General Hospital for their help in data collection and Jeffrey Shum for his help with data analysis. The Rick Hansen Spinal Cord Injury Registry and this work are supported by funding from the Praxis Spinal Cord Institute, Health Canada, Western Economic Diversification Canada and the Government of BC.