ABSTRACT
Background: Timely intravenous thrombolysis (IVT) is crucial for improving outcomes in acute ischemic stroke (AIS) patients. This study evaluates the effectiveness of the Acute Stroke Care Map (ASCaM) initiative in Shenyang, aimed at reducing door-to-needle times (DNT) and thus improving the timeliness of care for AIS patients. Methods: An retrospective cohort study was conducted from April 2019 to December 2021 in 30 hospitals participating in the ASCaM initiative in Shenyang. The ASCaM bundle included strategies such as EMS prenotification, rapid stroke triage, on-call stroke neurologists, immediate neuroimaging interpretation, and the innovative Pre-hospital Emergency Call and Location Identification feature. An interrupted time series analysis (ITSA) was used to assess the impact of ASCaM on DNT, comparing 9 months pre-intervention with 24 months post-intervention. Results: Data from 9,680 IVT-treated ischemic stroke patients were analyzed, including 2,401 in the pre-intervention phase and 7,279 post-intervention. The ITSA revealed a significant reduction in monthly DNT by -1.12 min and a level change of -5.727 min post-ASCaM implementation. Conclusion: The ASCaM initiative significantly reduced in-hospital delays for AIS patients, demonstrating its effectiveness as a comprehensive stroke care improvement strategy in urban settings. These findings highlight the potential of coordinated care interventions to enhance timely access to reperfusion therapies and overall stroke prognosis.
ABSTRACT
Background: This study aimed to compare the performance of different machine learning models in predicting symptomatic intracranial hemorrhage (sICH) after thrombolysis treatment for ischemic stroke. Methods: This multicenter study utilized the Shenyang Stroke Emergency Map database, comprising 8,924 acute ischemic stroke patients from 29 comprehensive hospitals who underwent thrombolysis between January 2019 and December 2021. An independent testing cohort was further established, including 1,921 patients from the First People's Hospital of Shenyang. The structured dataset encompassed 15 variables, including clinical and therapeutic metrics. The primary outcome was the sICH occurrence post-thrombolysis. Models were developed using an 80/20 split for training and internal validation. Performance was assessed using machine learning classifiers, including logistic regression with lasso regularization, support vector machine (SVM), random forest, gradient-boosted decision tree (GBDT), and multilayer perceptron (MLP). The model boasting the highest area under the curve (AUC) was specifically employed to highlight feature importance. Results: Baseline characteristics were compared between the training cohort (n = 6,369) and the external validation cohort (n = 1,921), with the sICH incidence being slightly higher in the training cohort (1.6%) compared to the validation cohort (1.1%). Among the evaluated models, the logistic regression with lasso regularization achieved the highest AUC of 0.87 (95% confidence interval [CI]: 0.79-0.95; p < 0.001), followed by the MLP model with an AUC of 0.766 (95% CI: 0.637-0.894; p = 0.04). The reference model and SVM showed AUCs of 0.575 and 0.582, respectively, while the random forest and GBDT models performed less optimally with AUCs of 0.536 and 0.436, respectively. Decision curve analysis revealed net benefits primarily for the SVM and MLP models. Feature importance from the logistic regression model emphasized anticoagulation therapy as the most significant negative predictor (coefficient: -2.0833) and recombinant tissue plasminogen activator as the principal positive predictor (coefficient: 0.5082). Conclusion: After a comprehensive evaluation, the MLP model is recommended due to its superior ability to predict the risk of symptomatic hemorrhage post-thrombolysis in ischemic stroke patients. Based on decision curve analysis, the MLP-based model was chosen and demonstrated enhanced discriminative ability compared to the reference. This model serves as a valuable tool for clinicians, aiding in treatment planning and ensuring more precise forecasting of patient outcomes.
ABSTRACT
Background: Acute Ischemic Stroke (AIS) presents significant challenges in evaluating the effectiveness of Endovascular Treatment (EVT). This study develops a novel prognostic model to predict 6-month mortality post-EVT, aiding in identifying patients likely to benefit less from this intervention, thus enhancing therapeutic decision-making. Methods: We employed a cohort of AIS patients from Shenyang First People's Hospital, serving as the Validation set, to develop our model. LASSO regression was used for feature selection, followed by logistic regression to create a prognostic nomogram for predicting 6-month mortality post-EVT. The model's performance was validated using a dataset from PLA Northern Theater Command General Hospital, assessing discriminative ability (C-index), calibration (calibration plot), and clinical utility (decision curve analysis). Statistical significance was set at p < 0.05. Results: The development cohort consisted of 219 patients. Six key predictors of 6-month mortality were identified: "Lack of Exercise" (OR, 4.792; 95% CI, 1.731-13.269), "Initial TICI Score 1" (OR, 1.334; 95% CI, 0.628-2.836), "MRS Score 5" (OR, 1.688; 95% CI, 0.754-3.78), "Neutrophil Percentage" (OR, 1.08; 95% CI, 1.042-1.121), "Onset Blood Sugar" (OR, 1.119; 95% CI, 1.007-1.245), and "Onset NIHSS Score" (OR, 1.074; 95% CI, 1.029-1.121). The nomogram demonstrated a high predictive capability with a C-index of 0.872 (95% CI, 0.830-0.911) in the development set and 0.830 (95% CI, 0.726-0.920) in the validation set. Conclusion: Our nomogram, incorporating factors such as Lack of Exercise, Initial TICI Score 1, MRS Score 5, Neutrophil Percentage, Onset Blood Sugar, and Onset NIHSS Score, provides a valuable tool for predicting 6-month mortality in AIS patients post-EVT. It offers potential to refine early clinical decision-making and optimize patient outcomes, reflecting a shift toward more individualized patient care.
