Ensemble Machine Learning Model Validated at Three Centers for Predicting One-Year Functional Outcomes After Traumatic Cervical Spinal Cord Injury

An ensemble machine learning model integrating clinical and MRI features achieved an area under the curve of at least 0.85 for predicting one-year ASIA Impairment Scale grades after traumatic cervical spinal cord injury in an external test set of 98 patients. The model also pred…

• The two-layer Stacking ensemble model was externally validated using data from three medical centers (n=340 after exclusions; 242 training, 98 test).
• SHAP analysis identified baseline Upper Extremity Motor Score, ASIA Impairment Scale grade, and maximum spinal cord compression on MRI as the most influential predictors of functional recovery.
• The study is retrospective, and the source does not report prospective validation.

Automated summary

RadPigeon summaries are original and for information only. They are not clinical advice.