The use of classification and regression tree analysis to identify the optimal surgical timing for improving neurological outcomes following motor-complete thoracolumbar traumatic spinal cord injury

Does Improvement in American Spinal Injury Association Impairment Scale Grade Correlate With Functional Recovery in All Patients With a Traumatic Spinal Cord Injury?

OBJECTIVE

The aim of the study is to determine what improvement on the American Spinal Injury Impairment Scale correlates with functional status after a traumatic spinal cord injury.

DESIGN

We performed an observational cohort study, analyzing prospective data from 168 patients with traumatic spinal cord injury admitted to a single level 1 trauma center. A multivariable analysis was performed to assess the relationship between functional status (from the Spinal Cord Independence Measure) at 1-year follow-up and American Spinal Injury Impairment Scale grade (baseline and 1-yr follow-up), while taking into account covariables describing the sociodemographic status, trauma severity, and level of neurological injury.

RESULTS

Individuals improving to at least American Spinal Injury Impairment Scale grade D had significantly higher Spinal Cord Independence Measure score compared with those not reaching American Spinal Injury Impairment Scale D (89.3 ± 15.2 vs. 52.1 ± 20.4) and were more likely to reach functional independence (68.5% vs. 3.6%), regardless of the baseline American Spinal Injury Impairment Scale grade. Higher final Spinal Cord Independence Measure was more likely with an initial American Spinal Injury Impairment Scale grade D (β = 1.504; 95% confidence interval = 0.46-2.55), and a final American Spinal Injury Impairment Scale grade D (β = 3.716; 95% CI = 2.77-4.66) or E (β = 4.422; 95% CI = 2.91-5.93).

CONCLUSIONS

Our results suggest that reaching American Spinal Injury Impairment Scale grade D or better 1 yr after traumatic spinal cord injury is highly predictive of significant functional recovery, more so than the actual improvement in American Spinal Injury Impairment Scale grade from the injury to the 1-yr follow-up.

Predictors of spinal trauma care and outcomes in a resource-constrained environment: a decision tree analysis of spinal trauma surgery and outcomes in Tanzania

OBJECTIVE

The burden of spinal trauma in low- and middle-income countries (LMICs) is immense, and its management is made complex in such resource-restricted settings. Algorithmic evidence-based management is cost-prohibitive, especially with respect to spinal implants, while perioperative care is work-intensive, making overall care dependent on multiple constraints. The objective of this study was to identify determinants of decision-making for surgical intervention, improvement in function, and in-hospital mortality among patients experiencing acute spinal trauma in resource-constrained settings.

METHODS

This study was a retrospective analysis of prospectively collected data in a cohort of patients with spinal trauma admitted to a tertiary referral hospital center in Dar es Salam, Tanzania. Data on demographic, clinical, and treatment characteristics were collected as part of a quality improvement neurotrauma registry. Outcome measures were surgical intervention, American Spinal Injury Association (ASIA) Impairment Scale (AIS) grade improvement, and in-hospital mortality, based on existing treatment protocols. Univariate analyses of demographic and clinical characteristics were performed for each outcome of interest. Using the variables associated with each outcome, a machine learning algorithm-based regression nonparametric decision tree model utilizing a bootstrapping method was created and the accuracy of the three models was estimated.

RESULTS

Two hundred eighty-four consecutively admitted patients with acute spinal trauma were included over a period of 33 months. The median age was 34 (IQR 26-43) years, 83.8% were male, and 50.7% had experienced injury in a motor vehicle accident. The median time to hospital admission after injury was 2 (IQR 1-6) days; surgery was performed after a further median delay of 22 (IQR 13-39) days. Cervical spine injury comprised 38.4% of the injuries. Admission AIS grades were A in 48.9%, B in 16.2%, C in 8.5%, D in 9.5%, and E in 16.6%. Nearly half (45.1%) of the patients underwent surgery, 12% had at least one functional improvement in AIS grade, and 11.6% died in the hospital. Determinants of surgical intervention were age ≤ 30 years, spinal injury level, admission AIS grade, delay in arrival to the referral hospital, undergoing MRI, and type of insurance; admission AIS grade, delay to arrival to the hospital, and injury level for functional improvement; and delay to arrival, injury level, delay to surgery, and admission AIS grade for in-hospital mortality. The best accuracies for the decision tree models were 0.62, 0.34, and 0.93 for surgery, AIS grade improvement, and in-hospital mortality, respectively.

CONCLUSIONS

Operative intervention and functional improvement after acute spinal trauma in this tertiary referral hospital in an LMIC environment were low and inconsistent, which suggests that nonclinical factors exist within complex resource-driven decision-making frameworks. These nonclinical factors are highlighted by the authors' results showing clinical outcomes and in-hospital mortality were determined by natural history, as evidenced by the highest accuracy of the model predicting in-hospital mortality.

Early versus Late Surgical Decompression for Traumatic Spinal Cord Injury on Neurological Recovery: A Systematic Review and Meta-Analysis

This study aimed to investigate whether early surgical decompression was associated with favorable neurological recovery in patients with traumatic spinal cord injury (tSCI). We searched PubMed and Embase from the database inception through December 2020 and selected studies comparing the impact of early versus late surgical decompression on neurological recovery as assessed by American Spinal Injury Association Impairment Scale (AIS) for adult patients sustaining tSCI. We pooled the effect estimates in random-effects models and quantified the heterogeneity by the I2 statistics. Subgroup analysis and meta-regression analysis was conducted to identify significant outcome moderator. We included 26 studies involving 3574 patients in the meta-analysis. The pooled results demonstrated significant association between early surgical decompression and an improvement of at least one AIS grade (odds ratio [OR], 1.85; 95% confidence interval [CI], 1.41-2.41; I2, 48.06%). The benefits of early surgical decompression were consistently observed across different subgroups, including patients with cervical or thoracolumbar injury and patients with complete or incomplete injury. The meta-regression analysis indicated that cut-off timing defining early versus late decompression was a significant effect moderator, with early decompression performed before post-tSCI 8 or 12 h associated with greatest benefits (OR, 3.37; 95% CI, 1.74-6.50; I2, 53.52%). No obvious publication bias was detected by the funnel plot. In conclusion, early surgical decompression was associated with favorable neurological recovery for tSCI patients. However, there was a lack of high-quality evidence and the results need further examination.

XGBoost, a Machine Learning Method, Predicts Neurological Recovery in Patients with Cervical Spinal Cord Injury

The accurate prediction of neurological outcomes in patients with cervical spinal cord injury (SCI) is difficult because of heterogeneity in patient characteristics, treatment strategies, and radiographic findings. Although machine learning algorithms may increase the accuracy of outcome predictions in various fields, limited information is available on their efficacy in the management of SCI. We analyzed data from 165 patients with cervical SCI, and extracted important factors for predicting prognoses. Extreme gradient boosting (XGBoost) as a machine learning model was applied to assess the reliability of a machine learning algorithm to predict neurological outcomes compared with that of conventional methodology, such as a logistic regression or decision tree. We used regularly obtainable data as predictors, such as demographics, magnetic resonance variables, and treatment strategies. Predictive tools, including XGBoost, a logistic regression, and a decision tree, were applied to predict neurological improvements in the functional motor status (ASIA [American Spinal Injury Association] Impairment Scale [AIS] D and E) 6 months after injury. We evaluated predictive performance, including accuracy and the area under the receiver operating characteristic curve (AUC). Regarding predictions of neurological improvements in patients with cervical SCI, XGBoost had the highest accuracy (81.1%), followed by the logistic regression (80.6%) and the decision tree (78.8%). Regarding AUC, the logistic regression showed 0.877, followed by XGBoost (0.867) and the decision tree (0.753). XGBoost reliably predicted neurological alterations in patients with cervical SCI. The utilization of predictive machine learning algorithms may enhance personalized management choices through pre-treatment categorization of patients.