Related Experiment Videos
Functional outcome prediction after traumatic cervical spinal cord injury using ensemble machine learning: a
Zhenzhen Guan1, Bo Wang2, Tingting Wang2
1Department of Radiology, Sichuan Academy of Medical Sciences & Sichuan Provincial People's Hospital, Chengdu, 610072, China.
Acta Neurologica Belgica
|August 3, 2026
Summary
An ensemble model accurately predicts one-year functional recovery in traumatic cervical spinal cord injury (TCSCI) patients using clinical and MRI data. This aids in early prognosis and personalized rehabilitation planning for better outcomes.
Area of Science:
- Neurology
- Spinal Cord Injury Research
- Machine Learning in Medicine
Background:
- Traumatic cervical spinal cord injury (TCSCI) frequently results in significant neurological deficits.
- Predicting functional recovery is crucial for effective clinical management and rehabilitation strategies.
Purpose of the Study:
- To develop and validate an ensemble learning model for predicting one-year neurological and functional recovery in TCSCI patients.
- The model integrates baseline clinical data, neurological assessments, and cervical MRI features.
Main Methods:
- A two-layer Stacking ensemble model was developed using data from 410 TCSCI patients across three institutions.
- Predictors included demographic, clinical, and radiologic features; outcomes were AIS grade, UEMS, LEMS, TMS, and SCIM III.
- SHapley Additive exPlanations (SHAP) analysis was used for model interpretability.
Main Results:
- The model demonstrated high accuracy, with AUC ≥ 0.85 for AIS grades and R² values up to 0.9880 for motor and functional scores.
- Key predictors identified by SHAP analysis included baseline Upper Extremity Motor Score (UEMS) and ASIA Impairment Scale (AIS) grade.
- External validation confirmed the model's predictive performance.
Conclusions:
- The developed ensemble model provides accurate, externally validated predictions of one-year functional recovery in TCSCI patients.
- This tool can support early prognosis assessment and the development of individualized rehabilitation plans.