Predictors Of Stroke Recurrence Research Articles

Left atrial cardiomyopathy predicts stroke recurrence and atrial fibrillation

Abstract Background Markers of atrial cardiomyopathy, encompassing both left atrial (LA) structure and function, have been linked to an increased long-term risk of ischemic stroke and atrial fibrillation (AF). However, the short-term risk associated with these markers in patients with stroke without previously known or detected AF during stroke workup remains insufficiently characterized. Purpose To investigate the association between functional and structural markers of atrial cardiomypathy using cardiac magnetic resonance (CMR) with late gadolinium enhancement (LGE) in patients with stroke of either i) undetermined etiology or ii) small or large-vessel stroke and the recurrence of stroke or new-onset AF. Methods Between 2019 and 2021 we consecutively included 91 patients with a recent stroke (<30 days) without known or detected AF during at least 48-hours of continuous monitoring. All patients had CMR with LGE to determine LA emptying fraction, LA volumes, and LA fibrosis. The primary endpoint was a composite of stroke recurrence or new-onset AF. Results Baseline characteristics are presented in Table 1. Over a median follow-up of 2.3 years, fourteen patients (15%) reached the combined endpoint of stroke or new-onset AF. Multivariable cause specific regression analysis demonstrated that a lower LA emptying fraction was associated with the primary endpoint (hazard ratio [HR], 1.41 per 5% decrease [95% CI, 1.09–1.82]). LA volumes and LA fibrosis did not show any associations with the combined endpoint (Table 2). Subgroup analysis indicated that the results were predominantly driven by new-onset AF in patients with stroke of undetermined etiology Conclusion Our results suggests that LA emptying fraction, measured using CMR, may serve as a prognostic indicator for stroke recurrence or new-onset atrial fibrillation in patients without detected AF, especially in those with stroke of undetermined etiology. Surprisingly, LA fibrosis was not associated with either recurrence of stroke or new-onset AF.

Stroke recurrence prediction using machine learning and segmented neural network risk factor aggregation

Stroke has remained a major cause of mortality and disability in the United States for years, and its recurrence significantly increased the risks. For predicting stroke recurrence, traditional data aggregation methods have limitations in effectively handling the numerous subcategories of stroke risk factors. This pilot study proposed a Segmented Neural Network-Driven Aggregation (SNA) method, and it aimed to improve the prediction model’s accuracy. Utilizing the TriNetX diagnosis dataset, we processed various risk factors and demographic information through traditional and our proposed data aggregation techniques. We applied logistic regression and random forest classifiers to predict stroke recurrence. Our findings revealed that using the SNA method significantly outperformed other aggregation methods for both classifiers. Using the SNA method with a random forest classifier achieved higher accuracy (84.2%) and a better balance between sensitivity and specificity (AUC of ROC = 0.928, AUC of PR = 0.940) compared to other combinations. These results showed the potential of machine-learning supervised encoding methods in stroke recurrence predictions, providing implications for clinical practice and future epidemiological research.

High fibrin and platelet clot predicts stroke recurrence or mortality after thrombectomy in patients with active cancer

BackgroundFibrin and platelet (FP)-rich clots have been shown to be associated with cancer-related stroke. This study aims to investigate the prognostic role of thrombus composition in clinical outcomes among cancer...

Multimodal ischemic stroke recurrence prediction model based on the capsule neural network and support vector machine.

Ischemic stroke (IS) has a high recurrence rate. Machine learning (ML) models have been developed based on single-modal biochemical tests, and imaging data have been used to predict stroke recurrence. However, the prediction accuracy of these models is not sufficiently high. Therefore, this study aimed to collect biochemical detection and magnetic resonance imaging (MRI) data to establish a dataset and propose a high-performance heterogeneous multimodal IS recurrence prediction model based on deep learning. This is a retrospective cohort study. Data were retrospectively collected from 634 IS patients in Zhuhai, China, a 12-month follow-up was conducted to determine stroke recurrence. We propose the ischemic stroke multi-group learning (ISGL) model, an integrated model for predicting the recurrence risk of multimodal IS in patients, based on a capsule neural network and a linear support vector machine (SVM). Two capsule neural network prediction models based on T1 and T2 signals in the MRI data and a SVM prediction model based on biochemical test data were established. Finally, a vote was conducted on the final judgment of the integrated model. The ISGL model was compared with 6 classical ML and deep learning models: k-nearest neighbors, SVM, logistic regression, random forest, eXtreme Gradient Boosting, and visual geometry group. The results revealed that the accuracy, specificity, sensitivity and the area under the curve of the ISGL model were 95%, 96%, 94%, and 95%, respectively. Among the comparison models, the visual geometry group method exhibited the best performance, but it much lower than those of the ISGL model. Analysis of the importance of biochemical test data revealed that low-density lipoprotein, smoking, and heart disease history were the positively correlated factors, and total cholesterol, high-density lipoprotein, and diabetes were and the negatively correlated factors. This study proposes the ISGL model can be used simultaneously with MRI and biochemical data to predict IS recurrence. This combination resulted in higher rate of performance than that of the other ML models. Additionally, this study found related risk factors affected recurrence, which can be used to intervene in high-risk patients' recurrence as early as possible and promote the development of secondary prevention of stroke.

Assessing Stroke Recurrence Risk by Using a Lipoprotein-Associated Phospholipase A2 and Platelet Count-Based Nomogram.

Stroke recurrence remains a critical challenge in clinical neurology, necessitating the identification of reliable predictive markers for better management and treatment strategies. This study investigates the interaction between lipoprotein-associated phospholipase A2 (Lp-PLA2) and platelets as a potential predictor for stroke recurrence, aiming to refine risk assessment and therapeutic approaches. In a retrospective cohort of 580 ischemic stroke patients, we analyzed clinical data with a focus on Lp-PLA2 and platelet levels. By using multivariable logistic regression, we identified independent predictors of stroke recurrence. These predictors were then used to develop a comprehensive nomogram. The study established diabetes mellitus, hypertension, low-density lipoprotein (LDL), Lp-PLA2 levels, and platelet counts as independent predictors of stroke recurrence. Crucially, the interaction parameter Lp-PLA2 * platelet (multiplication of Lp-PLA2 and platelet count) exhibited superior predictive power over each factor considered separately. Our nomogram incorporated diabetes mellitus, cerebral infarction causes, hypertension, LDL, and the Lp-PLA2 * platelet count interaction and demonstrated enhanced accuracy in predicting stroke recurrence compared to traditional risk models. The interaction between Lp-PLA2 and platelets emerged as a significant predictor for stroke recurrence when integrated with traditional risk factors. The developed nomogram offers a novel and practical tool in molecular neurobiology for assessing individual risks, facilitating personalized treatment strategies. This approach underscores the importance of multifactorial assessment in stroke management and opens avenues for targeted interventions to mitigate recurrence risks.

Predictors of recurrent stroke and subsequent mortality among patients experiencing housing instability

BackgroundThe experience of homelessness has been linked with developing poor health outcomes. Little is known about the risk of recurrent stroke among these individuals. This study investigated the correlates of developing recurrent stroke and subsequent mortality among Veterans with housing instability. MethodsUsing a national sample of Veterans from the U.S. Department of Veterans Affairs who had an indicator of housing instability between 2014–2018 (n=659,987), we identified 15,566 Veterans who experienced incident stroke. We compared characteristics of Veterans who experienced incident stroke and did and did not experience recurrent stroke and conducted logistic regressions using a discrete-time survival framework to assess two outcomes: recurrent stroke and all-cause mortality. ResultsAmong our cohort, 91.3% did not experience recurrent stroke while 8.7% did during the observation period. The receipt of any level of primary care outpatient visits was associated with a reduction in the odds of recurrent stroke. Several medical diagnoses were also associated with increased odds of recurrent stroke, including hypertension (aOR 1.35, 95% CI 1.15-1.59), diabetes (aOR 1.21, 95% CI 1.07-1.36), and renal disease (aOR 1.17, 95% CI 1.02, 1.35). Veterans who used any level of VA Homeless Programs had reduced odds of all-cause mortality (high level: aOR 0.65, 95% CI 0.60-0.71; low level: aOR 0.66, 95% CI 0.60-0.73). ConclusionOur study found several predictors of developing recurrent stroke and subsequent death in a population of Veterans experiencing housing instability. Implications include the need to monitor closely high-risk patients who have experienced incident stroke and have other co-occurring needs.

An Integrated Multi-omics prediction model for stroke recurrence based on [formula omitted] transformer layer and dynamic weighting mechanism

Background and objectiveStroke is a disease with high mortality and disability. Importantly, the fatality rate demonstrates a significant increase among patients afflicted by recurrent strokes compared to those experiencing their initial stroke episode. Currently, the existing research encounters three primary challenges. The first is the lack of a reliable, multi-omics image dataset related to stroke recurrence. The second is how to establish a high-performance feature extraction model and eliminate noise from continuous magnetic resonance imaging (MRI) data. The third is how to integration multi-omics data and dynamically weighted for different omics data. MethodsWe systematically compiled MRI and conventional detection data from a cohort comprising 737 stroke patients and established PSTSZC, a multi-omics dataset for predicting stroke recurrence. We introduced the first-ever Integrated Multi-omics Prediction Model for Stroke Recurrence, MPSR, which is based on ResNet, Lnet-transformer, LSTM and dynamically weighted DNN. The MPSR model comprises two principal modules, the Feature Extraction Module, and the Integrated Multi-Omics Prediction Module. In the Feature Extraction module, we proposed a novel Lnet regularization layer, which effectively addresses noise issues in MRI data. In the Integrated Multi-omics Prediction Module, we propose a dynamic weighted mechanism based on evaluators, which mitigates the noise impact brought about by low-performance omics. ResultsWe compared seven single-omics models and six state-of-the-art multi-omics stroke recurrence models. The experimental results demonstrate that the MPSR model exhibited superior performance. The accuracy, AUROC, specificity, and sensitivity of the MPSR model can reach 0.96, 0.97, 1, and 0.94, respectively, which is higher than the results of contrast model. ConclusionMPSR is the first available high-performance multi-omics prediction model for stroke recurrence. We assert that the MPSR model holds the potential to function as a valuable tool in assisting clinicians in accurately diagnosing individuals with a predisposition to stroke recurrence.

HR-MRI-based nomogram network calculator to predict stroke recurrence in high-risk non-disabling ischemic cerebrovascular events patients.

To investigate the use of high-resolution magnetic resonance imaging (HR-MRI) to identify the characteristics of culprit plaques in intracranial arteries, and to evaluate the predictive value of the characteristics of culprit plaques combined with the modified Essen score for the recurrence risk of high-risk non-disabling ischemic cerebrovascular events (HR-NICE) patients. A retrospective analysis was conducted on 180 patients with HR-NICE at the First Affiliated Hospital of Xinxiang Medical University, including 128 patients with no recurrence (non-recurrence group) and 52 patients with recurrence (recurrence group). A total of 65 patients with HR-NICE were collected from the Sixth Affiliated Hospital of Shanghai Jiaotong University as a validation group, and their modified Essen scores, high-resolution magnetic resonance vessel wall images, and clinical data were collected. The culprit plaques were analyzed using VesselExplorer2 software. Univariate and multivariate logistic regression analyses were used to identify independent risk factors for recurrence, and a nomogram was constructed using R software to evaluate the discrimination of the model. The area under the curve (AUC) of the receiver operating characteristic curve (ROC) was used to evaluate the model performance. Calibration curves and Decision Curve Analysis (DCA) were used to evaluate the model efficacy. Intra-plaque hemorrhage (OR = 3.592, 95% CI = 1.474-9.104, p = 0.006), homocysteine (OR = 1.098, 95% CI = 1.025-1.179, p = 0.007), and normalized wall index (OR = 1.114, 95% CI = 1.027-1.222, p = 0.015) were significantly higher in the recurrent stroke group than in the non-recurrent stroke group, and were independent risk factors for recurrent stroke. The performance of the nomogram model (AUC = 0.830, 95% CI: 0.769-0.891; PR-AUC = 0.628) was better than that of the modified Essen scoring model (AUC = 0.660, 95% CI: 0.583-0.738) and the independent risk factor combination model (AUC = 0.827, 95% CI: 0.765-0.889). The nomogram model still had good model performance in the validation group (AUC = 0.785, 95% CI: 0.671-0.899), with a well-fitting calibration curve and a DCA curve indicating good net benefit efficacy for patients. High-resolution vessel wall imaging combined with a modified Essen score can effectively assess the recurrence risk of HR-NICE patients, and the nomogram model can provide a reference for identifying high-risk populations with good clinical application prospects.

A Clinical-Radiomics Nomogram for Predicting Early Ischemic Stroke Risk in Patients with Transient Ischemic Attack

To develop and validate a clinical-radiomics nomogram for predicting early ischemic stroke risk in patients who sustain a transient ischemic attack (TIA). A retrospective training dataset (n= 76) and a prospective validation dataset (n= 34) of patients with TIA were studied. Image processing was performed using ITK-snap and Artificial Intelligent Kit. Radiomics features were selected in R. A nomogram predicting recurrent TIA/stroke in 90 days as a recurrent ischemic event was established. Model performance was assessed by computing the receiver operating characteristic curve and decision curve analysis (DCA). We found a higher proportion of diabetes and hypertension in the patients with recurrent TIA compared with the stable patients in both the training and validation datasets (P < 0.05). Recurrent patients had significantly higher ABCD2 scores and plaque scores compared to stable patients. ABCD2 score and necrotic/lipid core area were independent risk factors for recurrent ischemic events (odds ratio [OR], 2.75; 95% confidence interval [CI], 1.47-6.40; and OR, 1.20; 95% CI, 1.07-1.41, respectively). The radiomics model had area under the curve values of 0.737 (95% CI, 0.715-0.878) in the training dataset and 0.899 (95% CI, 0.706-0.936) in the validation dataset, which was superior to the ABCD2 score and plaque model for predicting stroke recurrence (P < 0.05). The nomogram predicting recurrent ischemic events was 0.923 (95% CI, 0.895-0.978) in the training dataset and 0.935 (95% CI, 0.830-0.959) in the validation dataset. DCA confirmed the clinical value of this nomogram. The nomogram, based on clinical ABCD2 score, carotid plaque components and radiomics score, shows good performance in predicting the risk of recurrent ischemic events in patients with TIA.

Recurrent stroke prediction by applying a stroke polygenic risk score in the Japanese population.

Recently, various polygenic risk score (PRS)-based methods were developed to improve stroke prediction. However, current PRSs (including cross-ancestry PRS) poorly predict recurrent stroke. Here, we aimed to determine whether the best PRS for Japanese individuals can also predict stroke recurrence in this population by extensively comparing the methods and maximizing the predictive performance for stroke onset. We used data from the BioBank Japan (BBJ) 1st cohort (n=179,938) to derive and optimize the PRSs using a 10-fold cross-validation. We integrated the optimized PRSs for multiple traits, such as vascular risk factors and stroke subtypes to generate a single PRS using the meta-scoring approach (metaGRS). We used an independent BBJ 2nd cohort (n=41,929) as a test sample to evaluate the association of the metaGRS with stroke and recurrent stroke. We analyzed recurrent stroke cases (n=174) and non-recurrent stroke controls (n=1,153) among subjects within the BBJ 2nd cohort. After adjusting for known risk factors, metaGRS was associated with stroke recurrence (adjusted OR per SD 1.18 [95% CI: 1.00-1.39, p=0.044]), although no significant correlation was observed with the published PRSs. We administered three distinct tests to consider the potential index event bias; however, the outcomes derived from these examinations did not provide any significant indication of the influence of index event bias. The high metaGRS group without a history of hypertension had a higher risk of stroke recurrence than that of the low metaGRS group (adjusted OR 2.24 [95% CI: 1.07-4.66, p=0.032]). However, this association was weak in the hypertension group (adjusted OR 1.21 [95% CI: 0.69-2.13, p=0.50]). The metaGRS developed in a Japanese cohort predicted stroke recurrence in an independent cohort of patients. In particular, it predicted an increased risk of recurrence among stroke patients without hypertension. These findings provide clues for additional genetic risk stratification and help in developing personalized strategies for stroke recurrence prevention.

Enhancing stroke risk prediction in patients with transient ischemic attack: insights from a prospective cohort study implementing fast-track care.

Fast-track care have been proved to reduce the short-term risk of stroke after transient ischemic attack (TIA). We aimed to investigate stroke risk and to characterize short- and long-term stroke predictors in a large cohort of TIA patients undergoing fast-track management. Prospective study, enrolling consecutive TIA patients admitted to a Northern Italy emergency department from August 2010 to December 2017. All patients underwent fast-track care within 24 h of admission. The primary outcome was defined as the first stroke recurrence at 90 days, 12 and 60 months after TIA. Stroke incidence with 95% confidence interval (CI) at each timepoint was calculated using Poisson regression. Predictors of stroke recurrence were evaluated with Cox regression analysis. The number needed to treat (NNT) of fast-track care in preventing 90-day stroke recurrence in respect to the estimates based on baseline ABCD2 score was also calculated. We enrolled 1,035 patients (54.2% males). Stroke incidence was low throughout the follow-up with rates of 2.2% [95% CI 1.4-3.3%] at 90 days, 2.9% [95% CI 1.9-4.2%] at 12 months and 7.1% [95% CI 5.4-9.0%] at 60 months. Multiple TIA, speech disturbances and presence of ischemic lesion at neuroimaging predicted stroke recurrence at each timepoint. Male sex and increasing age predicted 90-day and 60-month stroke risk, respectively. Hypertension was associated with higher 12-month and 60-month stroke risk. No specific TIA etiology predicted higher stroke risk throughout the follow-up. The NNT for fast-track care in preventing 90-day stroke was 14.5 [95% CI 11.3-20.4] in the overall cohort and 6.8 [95% CI 4.6-13.5] in patients with baseline ABCD2 of 6 to 7. Our findings support the effectiveness of fast-track care in preventing both short- and long-term stroke recurrence after TIA. Particular effort should be made to identify and monitor patients with baseline predictors of higher stroke risk, which may vary according to follow-up duration.

Machine learning model for predicting stroke recurrence in adult stroke patients with moyamoya disease and factors of stroke recurrence

ObjectThe aim of this study was at building an effective machine learning model to contribute to the prediction of stroke recurrence in adult stroke patients subjected to moyamoya disease (MMD), while at analyzing the factors for stroke recurrence. MethodsThe data of this retrospective study originated from the database of JiangXi Province Medical Big Data Engineering & Technology Research Center. Moreover, the information of MMD patients admitted to the second affiliated hospital of Nanchang university from January 1st, 2007 to December 31st, 2019 was acquired. A total of 661 patients from January 1st, 2007 to February 28th, 2017 were covered in the training set, while the external validation set comprised 284 patients that fell into a scope from March 1st, 2017 to December 31st, 2019. First, the information regarding all the subjects was compared between the training set and the external validation set. The key influencing variables were screened out using the Lasso Regression Algorithm. Furthermore, the models for predicting stroke recurrence in 1, 2, and 3 years after the initial stroke were built based on five different machine learning algorithms, and all models were externally validated and then compared. Lastly, the CatBoost model with the optimal performance was explained using the SHapley Additive exPlanations (SHAP) interpretation model. ResultIn general, 945 patients suffering from MMD were recruited, and the recurrence rate of acute stroke in 1, 2, and 3 years after the initial stroke reached 11.43%(108/945), 18.94%(179/945), and 23.17%(219/945), respectively. The CatBoost models exhibited the optimal prediction performance among all models; the area under the curve (AUC) of these models for predicting stroke recurrence in 1, 2, and 3 years was determined as 0.794 (0.787, 0.801), 0.813 (0.807, 0.818), and 0.789 (0.783, 0.795), respectively. As indicated by the results of the SHAP interpretation model, the high Suzuki stage, young adults (aged 18–44), no surgical treatment, and the presence of an aneurysm were likely to show significant correlations with the recurrence of stroke in adult stroke patients subjected to MMD. ConclusionIn adult stroke patients suffering from MMD, the CatBoost model was confirmed to be effective in stroke recurrence prediction, yielding accurate and reliable prediction outcomes. High Suzuki stage, young adults (aged 18–44 years), no surgical treatment, and the presence of an aneurysm are likely to be significantly correlated with the recurrence of stroke in adult stroke patients subjected to MMD.

Stroke recurrence and osteoporotic conditions in postmenopausal patients with atherosclerotic ischemic stroke

Recurrence after stroke is common, and associated with a high mortality rate. Degradation of the elastic tissue in the arterial wall has been shown to aggravate atherosclerosis in blood vessels. Considering that type 1 collagen is present in both bone and vascular smooth muscle cells, we explored whether osteoporotic conditions affect the likelihood of stroke recurrence in postmenopausal women following atherosclerotic ischemic stroke. To determine actual bone mineral density (BMD), the Hounsfield unit values in the frontal skull were evaluated using brain computed tomography (CT) scans taken at admission. A multivariate Cox regression analysis was also performed to examine if osteoporosis could independently predict stroke recurrence in postmenopausal patients with large artery atherosclerosis (LAA) or small vessel occlusion (SVO) stroke. This study included 2130 consecutive patients (both males and females aged 50 and older) with acute LAA or SVO strokes. After adjusting for all covariates, hypothetical osteoporosis was identified as an independent predictor of stroke recurrence in female patients ≥50 years with acute LAA or SVO stroke (hazard ratio, 1.84; 95 % confidence interval, 1.05 to 3.24; p = 0.034). Our findings showed that osteoporosis could potentially affect the recurrence of ischemic stroke in postmenopausal patients with LAA or SVO stroke.

PRERISK: A Personalized, Artificial Intelligence-Based and Statistically-Based Stroke Recurrence Predictor for Recurrent Stroke.

Predicting stroke recurrence for individual patients is difficult, but individualized prediction may improve stroke survivors' engagement in self-care. We developed PRERISK: a statistical and machine learning classifier to predict individual risk of stroke recurrence. We analyzed clinical and socioeconomic data from a prospectively collected public health care-based data set of 41 975 patients admitted with stroke diagnosis in 88 public health centers over 6 years (2014-2020) in Catalonia-Spain. A new stroke diagnosis at least 24 hours after the index event was considered as a recurrent stroke, which was considered as our outcome of interest. We trained several supervised machine learning models to provide individualized risk over time and compared them with a Cox regression model. Models were trained to predict early, late, and long-term recurrence risk, within 90, 91 to 365, and >365 days, respectively. C statistics and area under the receiver operating characteristic curve were used to assess the accuracy of the models. Overall, 16.21% (5932 of 36 114) of patients had stroke recurrence during a median follow-up of 2.69 years. The most powerful predictors of stroke recurrence were time from previous stroke, Barthel Index, atrial fibrillation, dyslipidemia, age, diabetes, and sex, which were used to create a simplified model with similar performance, together with modifiable vascular risk factors (glycemia, body mass index, high blood pressure, cholesterol, tobacco dependence, and alcohol abuse). The areas under the receiver operating characteristic curve were 0.76 (95% CI, 0.74-0.77), 0.60 (95% CI, 0.58-0.61), and 0.71 (95% CI, 0.69-0.72) for early, late, and long-term recurrence risk, respectively. The areas under the receiver operating characteristic curve of the Cox risk class probability were 0.73 (95% CI, 0.72-0.75), 0.59 (95% CI, 0.57-0.61), and 0.67 (95% CI, 0.66-0.70); machine learning approaches (random forest and AdaBoost) showed statistically significant improvement (P<0.05) over the Cox model for the 3 recurrence time periods. Stroke recurrence curves can be simulated for each patient under different degrees of control of modifiable factors. PRERISK is a novel approach that provides a personalized and fairly accurate risk prediction of stroke recurrence over time. The model has the potential to incorporate dynamic control of risk factors.

Potential Protein Signatures for Recurrence Prediction of Ischemic Stroke.

Acute ischemic stroke is a major cause of mortality and disability worldwide, with approximately 7.4% to 7.7% recurrence within the first 3 months. This study aimed to identify potential biomarkers for predicting stroke recurrence. We conducted a nested case-control study using a hospital-based cohort from the Third China National Stroke Registry selecting 214 age- and sex-matched patients with ischemic stroke with hypertension and no history of diabetes or heart disease. Using data-independent acquisition for discovery and multiple reaction monitoring for quantitative validation, we identified 26 differentially expressed proteins in large-artery atherosclerosis (Causative Classification of Ischemic Stroke [CCS]1), 16 in small-artery occlusion (CCS3), and 25 in undetermined causes (CCS5) among patients with recurrent stroke. In the CCS1 and CCS3 subgroups, differentially expressed proteins were associated with platelet aggregation, neuronal death/cerebroprotection, and immune response, whereas differentially expressed proteins in the CCS5 subgroup were linked to altered metabolic functions. Validated recurrence predictors included proteins associated with neutrophil activity and vascular inflammation (TAGLN2 [transgelin 2], ITGAM [integrin subunit α M]/TAGLN2 ratio, ITGAM/MYL9 [myosin light chain 9] ratio, TAGLN2/RSU1 [Ras suppressor protein 1] ratio) in the CCS3 subgroup and proteins associated with endothelial plasticity and blood-brain barrier integrity (ITGAM/MYL9 ratio and COL1A2 [collagen type I α 2 chain]/MYL9 ratio) in the CCS3 and CCS5 subgroups, respectively. These findings provide a foundation for developing a blood-based biomarker panel, using causative classifications, which may be used in routine clinical practice to predict stroke recurrence.

Abstract 64: Biomarkers of Atrial Cardiopathy and Outcomes After Cryptogenic Stroke: The ARCADIA Trial

Background: Atrial cardiopathy is associated with incident ischemic stroke in the absence of clinical atrial fibrillation in prospective cohorts. Whether biomarkers of atrial cardiopathy predict recurrent stroke is less clear. Methods: In the ARCADIA trial, a multicenter randomized trial of apixaban versus aspirin in patients with cryptogenic stroke and evidence of atrial cardiopathy, we explored whether the biomarkers P-wave terminal force in ECG lead V 1 (PTFV1), N-terminal pro-Brain natriuretic peptide (NT-proBNP), or left atrial diameter index (LADI) predicted primary and secondary trial outcomes: (1) recurrent stroke of any type; (2) recurrent ischemic stroke or systemic embolism; and (3) recurrent stroke of any type or death. We analyzed the full cohort using Cox proportional hazard models , sequentially adjusting for treatment effect, demographic factors, and clinical risk factors. NT-proBNP concentrations were log-transformed. Results: With 1,015 of the target 1,100 participants enrolled (mean age 68 years, 54.3% female, 21.1% Black, and 8.1% Hispanic) and mean follow-up of 1.8 years, the trial was stopped for futility. Recurrent stroke occurred in 80 patients (annualized rate, 4.4%) and death in 54 patients. NT-proBNP significantly predicted recurrent stroke; recurrent ischemic stroke or systemic embolism; and recurrent stroke or death after adjusting for other risk factors, while PTFV1 and LADI did not (Table). NT-proBNP predicted recurrent stroke and death most strongly and with little change after adjusting for other risk factors. Treatment effect was not significant in any of the models. Conclusions: In this population of patients with cryptogenic stroke and evidence of atrial cardiopathy, NT-proBNP is a predictor of recurrent stroke and, with greater magnitude, of a composite of stroke or death. The role of NT-proBNP measurement in management after stroke deserves further study.

An interpretable machine learning model for stroke recurrence in patients with symptomatic intracranial atherosclerotic arterial stenosis.

Symptomatic intracranial atherosclerotic stenosis (SICAS) is the most common etiology of ischemic stroke and one of the main causes of high stroke recurrence. The recurrence of stroke is closely related to the prognosis of ischemic stroke. This study aims to develop a machine learning model based on high-resolution vessel wall imaging (HR-VWI) to predict the risk of stroke recurrence in SICAS. This study retrospectively collected data from 180 SICAS stroke patients treated at the hospital between 2020.01 and 2022.01. Relevant imaging and clinical data were collected, and follow-up was conducted. The dataset was divided into a training set and a validation set in a ratio of 7:3. We employed the least absolute shrinkage and selection operator (LASSO) regression to perform a selection on the baseline data, laboratory tests, and neuroimaging data generated by HR-VWI scans collected from the training set. Finally, five machine learning techniques, including logistic regression model (LR), support vector machine (SVM), Gaussian naive Bayes (GNB), Complement naive Bayes (CNB), and k-nearest neighbors algorithm (kNN), were employed to develop a predictive model for stroke recurrence. Shapley Additive Explanation (SHAP) was used to provide visualization and interpretation for each patient. The model's effectiveness was evaluated using average accuracy, sensitivity, specificity, precision, f1 score, PR curve, calibration curve, and decision curve analysis. LASSO analysis revealed that "history of hypertension," "homocysteine level," "NWI value," "stenosis rate," "intracranial hemorrhage," "positive remodeling," and "enhancement grade" were independent risk factors for stroke recurrence in SICAS patients. In 10-fold cross-validation, the area under the curve (AUC) ranged from 0.813 to 0.912 in ROC curve analysis. The area under the precision-recall curve (AUPRC) ranged from 0.655 to 0.833, with the Gaussian Naive Bayes (GNB) model exhibiting the best ability to predict stroke recurrence in SICAS. SHAP analysis provided interpretability for the machine learning model and revealed essential factors related to the risk of stroke recurrence in SICAS. A precise machine learning-based prediction model for stroke recurrence in SICAS has been established to assist clinical practitioners in making clinical decisions and implementing personalized treatment measures.

Stroke and Risk Factors in Antiphospholipid Syndrome.

Stroke is considered one of the most common and life-threatening manifestations of antiphospholipid syndrome (APS), which leads to high mortality and permanent disability. This study investigated the prevalence and the potential risk factors of stroke in APS. We enrolled 361 APS patients retrospectively from 2009 to 2022 at Peking University People's Hospital. Stroke was found in 25.8% (93/361) of the participants. The multivariate logistic regression showed that hypertension, diabetes, livedo reticularis, and other central nervous system involvements were significant related factors for stroke. The use of hydroxychloroquine appeared to relate to a lower incidence of stroke. During a median follow-up of 3.0 years, 11.8% (11/93) of the individuals with a previous stroke developed stroke recurrence, and thrombocytopenia seemed to be a predictor of stroke recurrence.

Left atrial strain predicts stroke recurrence and death in patients with cryptogenic stroke

Abstract Background Left atrial strain (LAS) has been widely studied as predictor of atrial fibrillation (AF) after cryptogenic stroke (CS). However, the evidence about its prognostic role in terms of stroke recurrence and death in this setting remains scarce. Methods From April 2019 to April 2022, 92 consecutive patients with ischemic stroke or transient ischemic attack with ABCD2 scale ≥4 of unknown etiology were prospectively recruited. Echocardiography, including LAS was performed during admission. The primary outcome was the composite of stroke recurrence or death. Results Mean age was 77.5±7.7 and 58% of patient were female. After a median follow up of 28 months, the primary outcome measure occurred in 15 patients (16%). The primary outcome was more frequent in patients with diabetes (53% vs 21%; p=0.02), chronic kidney disease (33% vs 10%; p=0.034) and history of heart failure (13% vs 0%; p=0.025). LAS reservoir (LASr) and LAS conduct (LAScd) were lower in patients developing the primary outcome (21±7 vs 28.8±11%; p=0.017 and 7.7±3.9 vs 13.7±7%; p=0.007, respectively). On multivariate analysis, diabetes (HR 7.4, 95%CI 1.2-47; p=0.034)), LASr (HR 0.2, 95%CI 0.05-0.8; p=0.023), LAScd (HR 0.17, 95%CI 0.04-0.7; p=0.013) and LAS contraction (HR 0.2, 95%CI 0-05-0.8; p=0.025) were independent predictors of stroke recurrence or all-cause death after CS (Table). On long-rank test (using the discriminatory cut-off values of LASr &amp;lt;23% and LAScd &amp;lt;10%), LASr (p=0.009) (Figure 1) and LAScd (p=0.016) were associated with higher risk of the primary outcome. Conclusion Lower values of LAS reservoir, conduct and contraction are independently associated with higher risk of stroke recurrence or death after CS

Left Atrial Strain Predicts Stroke Recurrence and Death in Patients With Cryptogenic Stroke

Left atrial strain (LAS) has been widely studied as a predictor of atrial fibrillation (AF) after cryptogenic stroke (CS). However, the evidence about its prognostic role in terms of stroke recurrence and death in this setting remains scarce. A total of 92 consecutive patients with ischemic stroke or transient ischemic attack with ABCD2 scale ≥4 of unknown etiology were prospectively recruited. Echocardiography, including LAS was performed during admission. The primary outcome measure was the composite of stroke recurrence or death. The mean age was 77.5 ± 7.7, and 58% of patients were female. After a median follow up of 28 months, the primary outcome measure occurred in 15 patients (16%). The primary outcome was more frequent in patients with diabetes (53% vs 21%, p=0.02), chronic kidney disease (33% vs 10%, p=0.034), and a history of heart failure (13% vs 0%, p=0.025). LAS reservoir (LASr) and LAS conduit (LAScd) were lower in patients developing the primary outcome (21% ± 7% vs 28.8% ± 11%, p=0.017 and 7.7% ± 3.9% vs 13.7% ± 7%, p=0.007, respectively). On multivariate analysis, LASr (hazard ratio 0.9, 95% confidence interval 0.85 to 0.99, p=0.048) and diabetes (hazard ratio 3.3, 95% confidence interval 1.03 to 10.4, p=0.045) were associated with stroke recurrence or all-cause death after CS. On the log-rank test (using the discriminatory cut-off value of LASr <23%), LASr (p=0.009) was associated with higher risk of the primary outcome. In conclusion, lower values of the LAS reservoir were associated with a higher risk of stroke recurrence or death after CS. LAS may identify patients at higher risk of thromboembolism and stress conditions.