Ultrasound for the evaluation of stenosis after flow diversion

Machine learning to predict in-stent stenosis after Pipeline embolization device placement

Background

The Pipeline embolization device (PED) is a flow diverter used to treat intracranial aneurysms. In-stent stenosis (ISS) is a common complication of PED placement that can affect long-term outcome. This study aimed to establish a feasible, effective, and reliable model to predict ISS using machine learning methodology.

Methods

We retrospectively examined clinical, laboratory, and imaging data obtained from 435 patients with intracranial aneurysms who underwent PED placement in our center. Aneurysm morphological measurements were manually measured on pre- and posttreatment imaging studies by three experienced neurointerventionalists. ISS was defined as stenosis rate >50% within the PED. We compared the performance of five machine learning algorithms (elastic net (ENT), support vector machine, Xgboost, Gaussian Naïve Bayes, and random forest) in predicting ISS. Shapley additive explanation was applied to provide an explanation for the predictions.

Results

A total of 69 ISS cases (15.2%) were identified. Six predictors of ISS (age, obesity, balloon angioplasty, internal carotid artery location, neck ratio, and coefficient of variation of red cell volume distribution width) were identified. The ENT model had the best predictive performance with a mean area under the receiver operating characteristic curve of 0.709 (95% confidence interval [CI], 0.697–0.721), mean sensitivity of 77.9% (95% CI, 75.1–80.6%), and mean specificity of 63.4% (95% CI, 60.8–65.9%) in Monte Carlo cross-validation. Shapley additive explanation analysis showed that internal carotid artery location was the most important predictor of ISS.

Conclusion

Our machine learning model can predict ISS after PED placement for treatment of intracranial aneurysms and has the potential to improve patient outcomes.

Role of transcranial Doppler ultrasonography in assessing stenosis after flow diversion

INTRODUCTION

Patients after implantation of flow diverters (FD) due to intracranial aneurysms require radiological and clinical follow-up in view of in-stent stenosis. The aim of the study was to evaluate transcranial Doppler ultrasonography (TCD) as an alternative to more invasive digital subtraction angiography in monitoring patients with FD.

PATIENTS AND METHODS

Twenty-five patients after FD deployment due to internal carotid artery (ICA) aneurysms were reviewed. The degree stenosis found on TCD was compared with the results of catheter angiography. The TCD examinations were recorded from two sides at the extracranial ICA and the most proximal and distal segment of intracranial ICA. Analyzed TCD factors included: peak systolic blood flow velocity, end diastolic velocity, mean velocity, pulsatility index, and resistivity index. The side-to-side differences and ratios between particular TCD indices were calculated.

RESULTS

The cumulative frequency of angiographic in-stent stenosis was 5 of 25 (20 %). The analysis showed that pulsatility index measured on the most proximal intracranial segment of ICA is a predictor for angiographic instent stenosis (AUC = 0.854; p = 0.04; 95 % CI 0.59-1.00). The threshold of pulsatility index separating stenosis and non-stenosis groups was 1.05 with a sensitivity of 50 % and a specificity of 100 %. As the cut-off threshold of PI was set 0.75 the sensitivity and specificity was 100 % and 16.7 %, respectively.

CONCLUSIONS

The increased TCD-derived pulsatility index measured on the most proximal intracranial segment of ICA is associated with in-stent stenosis demonstrated on angiograms.