BACKGROUND
Spinal cord injury is complicated and varied conditions that receive a lot of attention. However, the prognosis of patients with spinal cord injury is increasingly being predicted using machine learning techniques.
OBJECTIVE
The purpose of this study is to evaluate the efficacy and caliber of machine learning models in forecasting the consequences of spinal cord injury.
METHODS
Literature searches were conducted in PubMed, Web of Science, Embase, PROSPERO, Scopus, Cochrane Library, CNKI, CBM, and Wanfang databases. Meta-analysis of the area under the receiver operating characteristic curve (AUC) of machine learning models was performed to comprehensively evaluate their performance.
RESULTS
A total of 1254 articles were retrieved, and 13 eligible studies were included. Predictive outcomes included spinal cord function prognosis, postoperative complications, independent living ability, and walking ability. For spinal cord function prognosis, the AUC of the Random Forest (RF) algorithm was 0.832, the AUC of the Logistic Regression (LR) algorithm was 0.813 (95% CI: 0.805, 0.883), the AUC of the Decision Tree (DT) algorithm was 0.747 (95% CI: 0.677, 0.802), and the AUC of the XGBoost algorithm was 0.867. For postoperative complications, the AUC of the RF algorithm was 0.627 (95% CI: 0.441, 0.812), the AUC of the LR algorithm was 0.747 (95% CI: 0.597, 0.896), and the AUC of the DT algorithm was 0.688. For independent living ability, the AUC of the CART model was 0.813. For walking ability, the model based on the VM algorithm was the most effective, with an AUC of 0.780.
CONCLUSIONS
Machine learning models predict spinal cord injury outcomes with relative accuracy, particularly in spinal cord function prognosis. They are expected to become important tools for clinicians in assessing the prognosis of spinal cord injury patients, with the XGBoost algorithm showing the best performance. Prediction models should continue to advance as large data is used and machine learning algorithms develop.