(I-641) Multivariate Automated Prediction Algorithm Improves Accuracy of Intraoperative Neuromonitoring to Predict Nerve Root Injury after Adult Deformity Surgery
Assistant Professor Oklahoma University San Francisco, California, United States
Introduction: Intraoperative neuromonitoring (IONM) utilizing transcranial motor evoked potentials (TCMEP) has limited ability to detect neurological deficit in nerve roots after adult spinal deformity (ASD) surgery. We hypothesize that, multivariate decision algorithms should improve the ability of IONM to detect postoperative neurological changes.
Methods: A pilot set of thirty-four ASD cases with complete neuromonitoring data were identified. Normalized changes in the motor evoked potential TCMEP were used to create a decision variable (DV), and a univariate and multivariate logistic regression (LR) classifier used the DV in combination with patient demographics and surgical variables to predict post-operative deficits. The sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of human alerts and the multivariate LR were compared. The correlation was found using Pearson’s linear correlation coefficient and the quality of the prediction was tested by calculating the area under the curve (AUC) using a receiver operating characteristic (ROC) analysis.
Results: Of the 34 cases in this pilot series, 11 patients (32.3%) had a new post-operative neurological deficit at least 6 weeks follow-up. For patients who developed motor weakness post-operatively, the average drop in motor score was 4.45 points (MRC grading system). The DV was significantly higher for patients with neurological deficit (p < 0.05) and correlated with the degree of post-operative weakness (r=0.44, p< 0.001). Regarding prediction, there was an improvement for the multivariate classifier compared to the neuro-monitoring staff alerts (sensitivity: 0.36, specificity: 0.65, PPV: 0.33, NPV: 0.68). The AUC of the multivariate classifier to predict neurological deficit was 0.83.
Conclusion : These data highlight how predictive analytics, in combination with IONM, can significantly improve the ability to predict post operative deficits after spinal surgery.
