A Predictive Model for the Risk of Posterior Circulation Stroke in Patients with Intracranial Atherosclerosis Based on High Resolution MRI

A clinical comparative analysis between expanded NIHSS and original NIHSS in posterior circulation ischemic stroke

BACKGROUND

The NIHSS is used routinely but has drawbacks. One of them is its inefficiency in detecting all signs of posterior circulation strokes. Since its declaration as a possible substitute for NIHSS in posterior circulation strokes in 2016; the expanded NIHSS (e-NIHSS) has not been paid much attention. The current study assesses clinically the value of e-NIHSS over NIHSS in posterior circulation strokes as regards the percentage of cases with different/higher scores, the significance of such scoring on management decisions, the weight of baseline e-NIHSS as a prognostic tool on 90 days functional outcome and its cut off value.

METHODS

The current longitudinal observational study was conducted on 79 cases after formal written consent who presented with posterior circulation strokes and confirmed by brain imaging.

RESULTS

In Comparison to NIHSS; the e-NIHSS score was higher in 36 cases at baseline and in 30 cases on discharge. The e-NIHSS median was two points higher at baseline and 24 h and was one point higher on discharge P < 0.001. A baseline moderate/moderate-severe was more common with e-NIHSS (n 50, 63.3%). In terms of 90 days outcome; a less favorable outcome (>2) was evident in cases with different scoring (e-NIHSS > NIHSS) indicating more sensitivity of e-NIHSS in prognosing 90 days outcome. ROC curve showed 82% sensitivity and 81% specificity with a significant area under the curve (=0.858) on scoring ≥ 8 in e-NIHSS.

CONCLUSION

e-NIHSS is diagnostically and prognostically relevant tool in posterior circulation strokes and ought to be considered in future guidelines.

Predicting functional outcome in acute ischemic stroke patients after endovascular treatment by machine learning

Background

Endovascular therapy (EVT) was the standard treatment for acute ischemic stroke with large vessel occlusion. Prognosis after EVT is always a major concern. Here, we aimed to explore a predictive model for patients after EVT.

Method

A total of 156 patients were retrospectively enrolled. The primary outcome was functional dependence (defined as a 90-day modified Rankin Scale score ≤ 2). Least absolute shrinkage and selection operator and univariate logistic regression were used to select predictive factors. Various machine learning algorithms, including multivariate logistic regression, linear discriminant analysis, support vector machine, k-nearest neighbors, and decision tree algorithms, were applied to construct prognostic models.

Result

Six predictive factors were selected, namely, age, baseline National Institute of Health Stroke Scale (NIHSS) score, Alberta Stroke Program Early CT (ASPECT) score, modified thrombolysis in cerebral infarction score, symptomatic intracerebral hemorrhage (sICH), and complications (pulmonary infection, gastrointestinal bleeding, and cardiovascular events). Based on these variables, various models were constructed and showed good discrimination. Finally, a nomogram was constructed by multivariate logistic regression and showed a good performance.

Conclusion

Our nomogram, which was composed of age, baseline NIHSS score, ASPECT score, recanalization status, sICH, and complications, showed a very good performance in predicting outcome after EVT.