Purpose: The objective of this study was to create and validate a novel prediction model that incorporated both multi-modal radiomics features and multi-clinical features, with the aim of accurately identifying acute ischemic stroke (AIS) patients who faced a higher risk of poor outcomes.Methods: A cohort of 461 patients diagnosed with AIS from four centers was divided into a training cohort and a validation cohort. Radiomics features were extracted and selected from diffusion-weighted imaging (DWI) and apparent diffusion coefficient (ADC) images to create a radiomic signature. Prediction models were developed using multi-clinical and selected radiomics features from DWI and ADC.Results: A total of 49 radiomics features were selected from DWI and ADC images by the least absolute shrinkage and selection operator (LASSO). Additionally, 20 variables were collected as multi-clinical features. In terms of predicting poor outcomes in validation set, the area under the curve (AUC) was 0.727 for the DWI radiomics model, 0.821 for the ADC radiomics model, 0.825 for the DWI + ADC radiomics model, and 0.808 for the multi-clinical model. Furthermore, a prediction model was built using all selected features, the AUC for predicting poor outcomes increased to 0.86.Conclusion: Radiomics features extracted from DWI and ADC images can serve as valuable biomarkers for predicting poor clinical outcomes in patients with AIS. Furthermore, when these radiomics features were combined with multi-clinical features, the predictive performance was enhanced. The prediction model has the potential to provide guidance for tailoring rehabilitation therapies based on individual patient risks for poor outcomes.

Purpose: Accurate prediction of the progression to severe stroke in initially diagnosed nonsevere patients with acute–subacute anterior circulation nonlacuna ischemic infarction (ASACNLII) is important in making clinical decision. This study aimed to apply a machine learning method to predict if the initially diagnosed nonsevere patients with ASACNLII would progress to severe stroke by using diffusion-weighted images and clinical information on admission.Methods: This retrospective study enrolled 344 patients with ASACNLII from June 2017 to August 2020 on admission, and 108 cases progressed to severe stroke during hospitalization within 3–21 days. The entire data were randomized into a training set (n = 271) and an independent test set (n = 73). A U-Net neural network was employed for automatic segmentation and volume measurement of the ischemic lesions. Predictive models were developed and used for evaluating the progression to severe stroke using different feature sets (the volume data, the clinical data, and the combination) and machine learning methods (random forest, support vector machine, and logistic regression).Results: The U-Net showed high correlation with manual segmentation in terms of Dice coefficient of 0.806 and R² value of the volume measurements of 0.960 in the test set. The random forest classifier of the volume + clinical combination achieved the best area under the receiver operating characteristic curve of 0.8358 (95% CI 0.7321–0.9269), and the accuracy, sensitivity, and specificity were 0.7780 (0.7397–0.7945), 0.7695 (0.6102–0.9074), and 0.8686 (0.6923–1.0), respectively. The Shapley additive explanation diagram showed the volume variable as the most important predictor.Conclusion: The U-Net was fully automatic and showed a high correlation with manual segmentation. An integrated approach combining clinical variables and stroke lesion volumes that were derived from the advanced machine learning algorithms had high accuracy in predicting the progression to severe stroke in ASACNLII patients.

This study aimed to develop novel nomogram models capable of predicting early neurological deterioration (END) and 90-day prognosis outcomes in acute ischemic stroke (AIS) patients treated with IV thrombolysis. A retrospective derivation cohort comprising 298 AIS patients was enrolled from January 2021 to March 2024. A separate validation cohort of 94 patients was retrospectively enrolled between April 2024 and December 2024. END was defined as a sustained NIHSS increase of ≥ 2 points within 24 h, and poor prognosis outcome a mRS score of 3-6 at 90 days. Multivariate logistic regression analysis was employed to construct nomogram models for the prediction of outcomes. In the derivation cohort, 23.83% patients with END experienced a poor 90-day outcome, as compared to 12.42% of those from NO-END group. Independent risk factors for END included a lower initial NIHSS score, a delayed DNT, a reduced ASPECTS score, and incomplete Willis Artery. END patients were found to be at a significantly increased risk of poor 90-day prognosis (odds ratio 0.163, p < 0.001). In addition, elevated initial NIHSS and glucose levels, the presence of nonlacunar infarction, and history of hypertension were predictive of poor prognosis. Two separate nomogram models, developed based on the previously identified risk factors to predict the occurrence of END and a poor 90-day prognosis, demonstrated AUC values of 0.740 (95% CI 0.686-0.789) and 0.859 (95% CI 0.814-0.896). These models also exhibited good discriminatory capacity in the validation cohort, with corresponding AUC values of 0.716 (95% CI 0.541-0.892) and 0.795 (95% CI 0.689-0.900). This study has successfully constructed reliable nomogram models for forecasting END and poor 90-day outcomes in AIS patients treated with IV thrombolysis; thereby, facilitating personalized prediction of adverse outcomes and adjustment of treatment strategy.

Purpose: This study aimed to evaluate the influence of the triglyceride-glucose index (TyG index) on clinical outcomes and to develop nomogram models for predicting early neurological deterioration (END) and long-term prognosis in acute ischemic stroke (AIS) patients following intravenous thrombolytic (IVT) therapy. Methods: We conducted a multi-center retrospective cohort study involving 333 AIS patients treated with IVT. The short-term and long-term outcomes were defined as the occurrence of END and 90-day prognosis. Multivariate logistic regression was used to develop nomogram models for forecasting these clinical outcomes. Results: Patients in the high-TyG group exhibited significantly higher risks of END ( P = 0.0010) and poor 90-day outcomes ( P = 0.0012). Independent risk factors for END included a lower baseline NIHSS score, delayed door-to-needle time (DNT), reduced ASPECTS score, elevated TyG index, higher potassium (K+) levels, and incomplete Willis artery. Additionally, a higher initial NIHSS, increased TyG levels, presence of END, and a history of hypertension were predictors of poor prognosis. Based on the identified risk factors, two nomogram models yielded AUC values of 0.746 and 0.849 for predicting END and poor prognosis, respectively. NIHSS scores, TyG index, and admission glucose levels (Glu) emerged as prognostic indicators across all patients, while higher mean platelet volume (MPV) and history of stroke were identified as novel risk factors for poor prognosis in NO-END group. Conclusion: A higher TyG index correlates with poor clinical outcomes in AIS patients post-IVT. The nomograms combining the TyG index with various factors enhanced risk prediction for END and poor prognosis.

The purpose of this study was to develop and validate a deep learning framework for simultaneous automated quantification of diffusion-weighted imaging-the Alberta Stroke Programme early CT score (DWI-ASPECTS) and infarct core volume in middle cerebral artery acute ischaemic stroke (MCA-AIS) and to evaluate its clinical utility for severity stratification in multi-centre settings. A cohort of 738 patients diagnosed with MCA-AIS from four centres was divided into a train set (n = 408), a validation set (n = 116), an internal test set (n = 60) and an external test set (n = 154). A 3D U-Net architecture was trained for simultaneous infarct segmentation and the ASPECTS region analysis. Model performance was compared against expert neuroradiologists using intraclass correlation coefficients and the Spearman correlation coefficient. Furthermore, we investigated the correlation between ASPECTS deduction frequency, ASPECTS score, core volume and the severity of MCA-AIS. The 3D U-Net model showed a high correlation with manual segmentation, achieving a Dice coefficient of 0.801 and a Spearman correlation coefficient of 0.988 for volume measurements in the external test set. In both the internal and external test sets, the automated ASPECTS by the deep learning (DL) model (Automated), manual ASPECTS by raters (Raters) and manual ASPECTS by raters on DWI images registered with the template (Raters_template) exhibited a strong correlation and excellent agreement. The cortical regions (M1–M6) were particularly relevant in patients classified into the moderate–severe group. The threshold values for the mild group and moderate–severe group on receiver operating characteristic curve analysis for DWI-ASPECTS and Core volume, were 6 and 27.86 mL, respectively. The DL model demonstrated comparable performance to neuroradiologists’ evaluation, potentially serving as an ancillary tool for physicians in making urgent clinical decisions. The severity of MCA-AIS was significantly associated with the specific ASPETCS regions and core volume, which may aid in identifying moderate–severe MCA-AIS.