Mediation effect of stroke recurrence in the association between post-stroke lactate dehydrogenase and functional disability.

Background: We aimed to use lactate dehydrogenase (LDH) as a marker of inflammation burden and quantify post-stroke inflammation's direct and indirect effect on functional disability. Methods: We analyzed 5,129 patients with acute ischemic stroke (AIS) admitted to Shenyang First People's Hospital. Stroke recurrence and functional outcome measured by the modified Rankin Scale (mRS) were assessed at 90 days. Functional disability was defined as mRS score > 2. Receiver operating characteristic curve and restricted cubic spline (RCS) analysis were conducted to illustrate the associations between LDH levels and 90-day functional outcomes in patients with AIS. Mediation analyses were performed to examine the potential causal chain in which stroke recurrence may mediate the relationship between LDH and functional outcome. Positive correlation between LDH and hs-CRP was found and mediation effects of stroke recurrence in the association between LDH or hs-CRP and functional disability were both less than 20%. Sensitivity analyses in different subgroups showed comparable results. Results: Among 5,129 included AIS patients, the median (IQR) level of LDH was 186 (161-204.4) U/L. Functional disability was seen in 1200 (23.4%) patients and recurrence was observed in 371(7.2%) patients at 90-day follow-up. Each standard deviation increase in the concentration of LDH was linked to an increased risk of functional disability (adjusted odds ratio[aOR], 1.07; 95%CI,1.04-1.09) and stroke recurrence (aOR,1.02; 95%CI, 1.01-1.04) within 90 days. The highest quartile of LDH (>204.2 U/L) had an elevated risk of suffering functional disability (aOR, 1.21; 95%CI, 1.00-1.47) and recurrence (aOR, 1.21; 95%CI,1.00-1.47) compared with the lowest quartile of LDH (<161 U/L). Stroke recurrence during follow-up explained 12.90% (95%CI, 6.22-21.16%) of the relationship between LDH and functional disability. Positive correlation between LDH and hs-CRP was found and mediation effects of recurrence in the association between LDH or hs-CRP and functional disability were both less than 20%. Sensitivity analyses in different subgroups showed comparable results. Conclusion: The relationship between LDH and functional disability at 90 days among AIS patients is partially mediated by stroke recurrence, accounting for less than 20%. LDH deserves equal attention as hs-CRP in predicting recurrence and functional outcome. In addition to traditional secondary prevention measures, innovative anti-inflammatory strategies warrant further investigation.

Machine learning-based prediction of early neurological deterioration after intravenous thrombolysis for stroke: insights from a large multicenter study.

Background: This investigation seeks to ascertain the efficacy of various machine learning models in forecasting early neurological deterioration (END) following thrombolysis in patients with acute ischemic stroke (AIS). Methods: Employing data from the Shenyang Stroke Emergency Map database, this multicenter study compiled information on 7,570 AIS patients from 29 comprehensive hospitals who received thrombolytic therapy between January 2019 and December 2021. An independent testing cohort was constituted from 2,046 patients at the First People's Hospital of Shenyang. The dataset incorporated 15 pertinent clinical and therapeutic variables. The principal outcome assessed was the occurrence of END post-thrombolysis. Model development was executed using an 80/20 split for training and internal validation, employing classifiers like logistic regression with lasso regularization (lasso regression), support vector machine (SVM), random forest (RF), gradient-boosted decision tree (GBDT), and multi-layer perceptron (MLP). The model with the highest area under the curve (AUC) was utilized to delineate feature significance. Results: Baseline characteristics showed variability in END incidence between the training (n = 7,570; END incidence 22%) and external validation cohorts (n = 2,046; END incidence 10%; p < 0.001). Notably, all machine learning models demonstrated superior AUC values compared to the reference model, indicating their enhanced predictive capacity. The lasso regression model achieved the highest AUC at 0.829 (95% CI: 0.799-0.86; p < 0.001), closely followed by the MLP model with an AUC of 0.828 (95% CI: 0.799-0.858; p < 0.001). The SVM, RF, and GBDT models also showed commendable AUCs of 0.753, 0.797, and 0.774, respectively. Decision curve analysis revealed that the SVM and MLP models demonstrated a high net benefit. Feature importance analysis emphasized "Onset To Needle Time" and "Admission NIHSS Score" as significant predictors. Conclusion: Our research establishes the MLP and lasso regression as robust tools for predicting early neurological deterioration in acute ischemic stroke patients following thrombolysis. Their superior predictive accuracy, compared to traditional models, highlights the significant potential of machine learning approaches in refining prognosis and enhancing clinical decisions in stroke care management. This advancement paves the way for more tailored therapeutic strategies, ultimately aiming to improve patient outcomes in clinical practice.

Effectiveness of the acute stroke care map program in reducing in-hospital delay for acute ischemic stroke in a Chinese urban area: an interrupted time series analysis.

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.

Machine learning-based prediction of symptomatic intracerebral hemorrhage after intravenous thrombolysis for stroke: a large multicenter study.

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.

Nomogram to predict 6-month mortality in acute ischemic stroke patients treated with endovascular treatment.

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.