Risk of Recurrent Stroke: The Critical Need for Continued Efforts in Secondary Prevention

Quantitative Analysis of White Matter Hyperintensities as a Predictor of 1-Year Risk for Ischemic Stroke Recurrence

INTRODUCTION

This study evaluates the role of quantitative characteristics of white matter hyperintensities (WMHs) in predicting the 1-year recurrence risk of ischemic stroke.

METHODS

We conducted a retrospective analysis of 1061 patients with ischemic stroke from January 2018 to April 2021. WMHs were automatically segmented using a cluster-based method to quantify their volume and number of clusters (NoC). Additionally, two radiologists independently rated periventricular and deep WMHs using the Fazekas scale. The cohort was divided into a training set (70%) and a testing set (30%). We employed Cox proportional hazards models to develop predictors based on quantitative WMH characteristics, Fazekas scores, and clinical factors, and compared their performance using the concordance index (C-index).

RESULTS

A total of 180 quantitative variables related to WMHs were extracted. A higher NoC in deep white matter and brainstem, advanced age (> 90 years old), specific stroke subtypes, and absence of discharge antiplatelets showed stronger associations with the risk of ischemic stroke recurrence within 1 year. The nomogram incorporating quantitative WMHs data showed superior discrimination compared to those based on the Fazekas scale or clinical factors alone, with C-index values of 0.709 versus 0.647 and 0.648, respectively, in the testing set. Notably, a combined model including both WMHs and clinical factors achieved the highest predictive accuracy, with a C-index of 0.735 in the testing set.

CONCLUSION

Quantitative assessment of WMHs provides a valuable neuro-imaging tool for enhancing the prediction of ischemic stroke recurrence risk.

Diffusion-weighted imaging-based radiomics for predicting 1-year ischemic stroke recurrence

Purpose

To investigate radiomics based on DWI (diffusion-weighted imaging) for predicting 1-year ischemic stroke recurrence.

Methods

A total of 1,580 ischemic stroke patients were enrolled in this retrospective study conducted from January 2018 to April 2021. Demographic and clinical characteristics were compared between recurrence and non-recurrence groups. On DWI, lesions were segmented using a 2D U-Net automatic segmentation network. Further, radiomics feature extraction was done using the segmented mask matrix on DWI and the corresponding ADC map. Additionally, radiomics features were extracted. The study participants were divided into a training cohort (n = 157, 57 recurrence patients, and 100 non-recurrence patients) and a test cohort (n = 846, 28 recurrence patients, 818 non-recurrence patients). A sparse representation feature selection model was performed to select features. Further classification was accomplished using a recurrent neural network (RNN). The area under the receiver operating characteristic curve values was obtained for model performance.

Results

A total of 1,003 ischemic stroke patients (682 men and 321 women; mean age: 65.90 ± 12.44 years) were included in the final analysis. About 85 patients (8.5%) recurred in 1 year, and patients in the recurrence group were older than the non-recurrence group (P = 0.003). The stroke subtype was significantly different between recurrence and non-recurrence groups, and cardioembolic stroke (11.3%) and large artery atherosclerosis patients (10.3%) showed a higher recurrence percentage (P = 0.005). Secondary prevention after discharge (statins, antiplatelets, and anticoagulants) was found significantly different between the two groups (P = 0.004). The area under the curve (AUC) of clinical-based model and radiomics-based model were 0.675 (95% CI: 0.643–0.707) and 0.779 (95% CI: 0.750–0.807), respectively. With an AUC of 0.847 (95% CI: 0.821–0.870), the model that combined clinical and radiomic characteristics performed better.

Conclusion

DWI-based radiomics could help to predict 1-year ischemic stroke recurrence.