Objectives:To evaluate the predictive value of Tabular Prior-data Fitted Network(TabPFN) for short-term outcome in patients with spontaneous intracerebral hemorrhage (sICH), and compared with the Extreme Gradient Boosting (XGboost) model and traditional logistic regression (LR) model. Methods:Patients with sICH admitted to the Department of Neurology, Hefei Second People's Hospital from January 2018 to March 2024 were included retrospectively. The demographic and baseline data were collected. At 3 months after onset, the modified Rankin Scale score was used to determine the outcome, 0-2 was defined as good outcome and >2 was defined as poor outcome. All enrolled patients were randomly divided into a training set and a testing set at a ratio of 7:3. Feature selection was performed using recursive feature elimination (RFE) method, and then the selected feature variables were included into TabPFN, XGboost, and LR models for training and testing. The area under the curve (AUC) of receiver operating characteristic (ROC) curve was used to evaluate the predictive ability of the models. Shapley additive explanations (SHAP) method was used for model interpretation.Results:A total of 547 patients with sICH were enrolled, including 367 males (67.1%), with a median age of 65 (interquartile range, 54-76) years. Two hundred twenty-six patients (41.3%) had poor outcome. Age, baseline blood pressure (systolic blood pressure, diastolic blood pressure), baseline laboratory tests (white blood cell count, red blood cell count, platelet count, neutrophil count, hemoglobin, fasting blood glucose, creatinine, uric acid, urea nitrogen, alanine aminotransferase, aspartate aminotransferase), hematoma rupture into the ventricle, island sign, baseline hematoma volume, and baseline National Institutes of Health Stroke Scale (NIHSS) score were selected as characteristic variables using RFE method. ROC curve analysis showed that the ROC AUC for TabPFN, Xgboost, and LR models predicting poor short-term outcome in the testing set were 0.918 (95% confidence interval [ CI] 0.870-0.966], 0.883 (95% CI 0.826-0.940), and 0.905 (95% CI 0.854-0.957), respectively. SHAP analysis showed that the top four important variables in the TabPFN model were baseline NIHSS score, baseline hematoma volume, baseline aspartate aminotransferase, and age. Conclusions:The TabPFN model is superior to the LR model and the XGBoost model in predicting poor outcome in patients with sICH. In the TabPFN model, baseline NIHSS score, baseline hematoma volume, aspartate aminotransferase, and age are the most important predictors of poor outcome in patients with sICH.Objectives To evaluate the predictive value of Tabular Prior-data Fitted Network(TabPFN) for short-term outcome in patients with spontaneous intracerebral hemorrhage (sICH), and compared with the Extreme Gradient Boosting (XGboost) model and traditional logistic regression (LR) model. Methods Patients with sICH admitted to the Department of Neurology, Hefei Second People's Hospital from January 2018 to March 2024 were included retrospectively. The demographic and baseline data were collected. At 3 months after onset, the modified Rankin Scale score was used to determine the outcome, 0-2 was defined as good outcome and >2 was defined as poor outcome. All enrolled patients were randomly divided into a training set and a testing set at a ratio of 7:3. Feature selection was performed using recursive feature elimination (RFE) method, and then the selected feature variables were included into TabPFN, XGboost, and LR models for training and testing. The area under the curve (AUC) of receiver operating characteristic (ROC) curve was used to evaluate the predictive ability of the models. Shapley additive explanations (SHAP) method was used for model interpretation. Results A total of 547 patients with sICH were enrolled, including 367 males (67.1%), with a median age of 65 (interquartile range, 54-76) years. Two hundred twenty-six patients (41.3%) had poor outcome. Age, baseline blood pressure (systolic blood pressure, diastolic blood pressure), baseline laboratory tests (white blood cell count, red blood cell count, platelet count, neutrophil count, hemoglobin, fasting blood glucose, creatinine, uric acid, urea nitrogen, alanine aminotransferase, aspartate aminotransferase), hematoma rupture into the ventricle, island sign, baseline hematoma volume, and baseline National Institutes of Health Stroke Scale (NIHSS) score were selected as characteristic variables using RFE method. ROC curve analysis showed that the ROC AUC for TabPFN, Xgboost, and LR models predicting poor short-term outcome in the testing set were 0.918 (95% confidence interval [ CI] 0.870-0.966], 0.883 (95% CI 0.826-0.940), and 0.905 (95% CI 0.854-0.957), respectively. SHAP analysis showed that the top four important variables in the TabPFN model were baseline NIHSS score, baseline hematoma volume, baseline aspartate aminotransferase, and age. Conclusions The TabPFN model is superior to the LR model and the XGBoost model in predicting poor outcome in patients with sICH. In the TabPFN model, baseline NIHSS score, baseline hematoma volume, aspartate aminotransferase, and age are the most important predictors of poor outcome in patients with sICH.

Large vessel occlusion due to intracranial atherosclerotic disease (ICAD-LVO) is one of the types of ischemic stroke with poor outcome. This article summarizes the relevant studies of ICAD-LVO in recent years, and reviews the imaging evaluation and treatment regimens to provide reference for clinical practice.

Objectives:To develop a machine learning prediction model for poor outcome of acute minor ischemic stroke (AMIS) at 90 days after onset and to explain the importance of various risk factors.Methods:Patients with AMIS admitted to the Second People's Hospital of Hefei from June 2022 to December 2023 were included retrospectively. AMIS was defined as the National Institutes of Health Stroke Scale (NIHSS) score ≤5 at admission. According to the modified Rankin Scale score at 90 days after onset, the patients were divided into a good outcome group (<2) and a poor outcome group (≥2). Recursive feature elimination (RFE) method was used to screen characteristic variables of poor outcome. Based on logistic regression (LR), supported vector machine (SVM), and extreme Gradient Boosting (XGBoost) machine learning algorithms, prediction models for poor outcome of AMIS were developed, and the predictive performance of the models was compared by the area under the curve (AUC) of receiver operating characteristic (ROC) curve and the calibration curve. Shapley Additive exPlanations (SHAP) algorithm was used to explain the role of characteristic variables in the optimal prediction model. Results:A total of 225 patients with AMIS were included, of which 152 (67.56%) had good outcome and 73 (32.44%) had poor outcome. Multivariate analysis showed that baseline NIHSS score, baseline systolic blood pressure, hypertension, diabetes, low-density lipoprotein cholesterol, homocysteine, body mass index, D-dimer, and age were the characteristic variables associated with poor outcome in patients with AMIS. The ROC curve analysis shows that the LR model had the best predictive performance (AUC=0.888, 95% confidence interval [ CI] 0.807-0.970), the next was the XGBoost model (AUC=0.888, 95% CI 0.796-0.980), while the SVM model had the lowest performance (AUC=0.849, 95% CI 0.754-0.944). The calibration curve showed that the LR model performed the best in terms of calibration accuracy. SHAP showed that baseline systolic blood pressure, baseline NIHSS score, diabetes, hypertension and body mass index were the top five risk factors for poor outcome of patients with AMIS. Conclusions:The LR algorithm has stable and superior performance in predicting poor outcome of patients with AMIS. Baseline systolic blood pressure, baseline NIHSS score, diabetes, hypertension and body mass index are the important risk factors for poor outcome of patients with AMIS.

Objective:To develop and validate a nomogram model for predicting short-term outcome in patients with acute cardioembolic stroke (CES) due to nonvalvular atrial fibrillation (NVAF).Methods:Patients CES due to NVAF who were hospitalized in the Department of Neurology of Hefei Second People's Hospital from January 2023 to August 2024 were retrospectively included. The modified Rankin Scale was used to evaluate outcome at the 14 th day after discharge or onset. A score ≤2 was defined as good outcome, and a score >2 was defined as poor outcome. The demographic data, National Institutes of Health Stroke Scale (NIHSS) scores at admission, and laboratory tests within 24 hours of admission were collected, and the neutrophil/lymphocyte ratio (NLR) and stress hyperglycemia ratio (SHR) were calculated. Multivariate logistic regression analysis was used to identify the independent risk factors for poor outcome, the nomogram prediction model was developed based on these risk factors, and the internal data was used to validate the predictive performance of the model. Results:A total of 196 patients with CES due to NVAF were enrolled, including 109 females (55.61%), median aged 80 years (interquartile range: 73-84 years). Ninety patients (50.00%) had good outcome, 98 (50.00%) had poor outcome, and 11 (5.61%) died. Multivariate logistic regression analysis showed that higher baseline NIHSS scores (odds ratio [ OR] 1.088, 95% confidence interval [ CI] 1.023-1.157; P=0.007), NLR ( OR 1.279, 95% CI 1.111-1.472; P<0.001), and female gender ( OR 2.288, 95% CI 1.017-5.149; P=0.045) were the independent risk factors for poor short-term outcome. The above variables were included to develop a nomogram prediction model. The internal validation showed that the C-statistic was 0.820 (95% CI 0.761-0.879), indicating good discriminability. In the calibration curve, both the actual curve and the deviation calibration curve tended to approach the ideal curve. Decision curve analysis showed that the model predicted a risk threshold for CES due to NVAF between 0.10-0.30 and 0.33-0.89, which could provide clinical benefits. Conclusions:Baseline NIHSS score, NLR, and gender are the independent risk factors for poor short-term outcome in patients CES due to NVAF. Higher baseline NIHSS score, NLR, and female gender suggest poor short-term outcome. The nomogram developed based on these factors shows good predictive power for poor short-term outcome.

Objectives:To develop a machine learning prediction model for post-stroke depression (PSD) in patients with acute ischemic stroke (AIS) at 3 months after onset.Methods:Patients with AIS admitted to the Second People's Hospital of Hefei from January 2021 to December 2023 were included retrospectively. According to the 17-item Hamilton Depression Rating Scale (HAMD) evaluation results at 3 months after onset, they were divided into PSD group and non-PSD group. The recursive feature elimination (RFE) method was used to screen the characteristic variables of PSD. A PSD prediction model for patients with AIS was developed based on three machine learning algorithms: logistic regression (LR), random forest (RF), and supported vector machine (SVM). The area under a receiver operating characteristic (ROC) curve (AUC) and calibration curve were used to evaluate the performance of the model. The SHapley Additive exPlanations (SHAP) algorithm was used to analyze the contribution of each risk factor. Results:A total of 243 patients with AIS were included, including 159 males (64.6%), aged 64.32±11.54 years, the median years of schooling was 6 years, and 13 males (5.3%) lived alone. 105 patients (42.7%) had a history of stroke. The median baseline National Institutes of Health Stroke Scale (NIHSS) score was 3, and the median baseline Modified Rankin Scale (mRS) score was 2. 33 patients (13.4%) received intravenous thrombolysis treatment. 93 patients (38.27%) had PSD at 3 months after onset. RFE showed that the optimal number of features was 11, including baseline NIHSS score, baseline mRS score, C-reactive protein, intravenous thrombolysis, low-density lipoprotein cholesterol, small vessel occlusion, D-dimer, total cholesterol, alcohol consumption, right side infarction, and baseline systolic blood pressure. ROC curve analysis shows that the RF model had the best predictive performance (AUC=0.831, 95% confidence interval 0.730-0.931), followed by the SVM model (AUC=0.827, 95% confidence interval 0.713-0.941), and the LR model has the lowest predictive performance (AUC=0.771, 95% confidence interval 0.658-0.885). The calibration curve shows that the RF model fits well with the ideal curve, making it the final advantageous model. SHAP showed that the contribution of baseline NIHSS score, baseline mRS score, low-density lipoprotein cholesterol, total cholesterol, and intravenous thrombolysis ranked among the top 5.Conclusions:The RF model can effectively predict the risk of PSD. The baseline NIHSS score, baseline mRS score, low-density lipoprotein cholesterol, and total cholesterol, as well as intravenous thrombolysis are the key predictive factors.

Objective:To investigate the predictive value of monocyte-to-high-density lipoprotein cholesterol ratio (MHR) for early neurological deterioration (END) and hemorrhagic transformation (HT) after intravenous thrombolysis in patients with acute ischemic stroke (AIS).Methods:Patients with AIS received IVT in Hefei Second People's Hospital from May 2020 to January 2022 were retrospectively enrolled. Blood collection was completed and MHR was calculated before intravenous thrombolysis. END was defined as an increase of ≥2 from the baseline in the National Institutes of Health Stroke Scale (NIHSS) score or ≥1 from the baseline in motor function score at any time within 7 d after admission. HT was defined as intracranial hemorrhage newly found by CT/MRI within 24 h after intravenous thrombolysis. Multivariate logistic regression analysis was used to determine the independent predictors of END and HT, and the receiver operating characteristic (ROC) curve was used to analyze the predictive value of MHR for END and HT. Results:A total of 186 patients with AIS treated with IVT were included, of which 50 (26.9%) had END and 31 (16.7%) had HT. The median MHR was 0.43. The MHR in the END group was significantly higher than that in the non-END group (0.49 vs. 0.40; P=0.008), and the MHR in the HT group was significantly higher than that in the non-HT group (0.52 vs. 0.40; P=0.013). All patients were divided into 4 groups (MHR1, MHR2, MHR3 and MHR4) according to the MHR quartile from low to high. Multivariate logistic regression analysis showed that after adjusting for confounding factors, taking MHR1 as a reference, MHR3 (odds ratio [ OR] 6.317, 95% confidence interval [ CI] 1.465-27.237; P=0.013) and MHR4 ( OR 8.064, 95% CI 1.910-34.051; P=0.005) were the significant independent predictors of END; Taking MHR1 as a reference, MHR4 ( OR 5.147, 95% CI 1.194-22.182; P=0.028) was the significant independent predictor of HT. The ROC curve analysis showed that the area under the curve of MHR for predicting END was 0.628 (95% CI 0.554-0.698; P=0.008). When the optimal MHR cutoff value was 0.41, its sensitivity and specificity for predicting END was 74.0% and 53.7% respectively. The area under the curve of MHR for predicting HT was 0.642 (95% CI 0.569-0.711; P=0.013). When the best cutoff value was 0.44, the sensitivity and specificity of MHR for predicting HT were 77.4% and 58.1% respectively. Conclusion:Higher MHR is a risk factor for END and HT after intravenous thrombolysis in patients with AIS, but the predictive value of MHR for END and HT is limited.

Ischemic stroke is the main cause of death and disability in adults, and its incidence is increasing year by year. Obstructive sleep apnea (OSA) is the most common type of sleep-disordered breathing, which can increase the risk of ischemic stroke and affect the outcomes of patients. There is an increasing amount of research on the relationship between OSA and ischemic stroke. This article reviews the bidirectional relationship between OSA and ischemic stroke, the mechanism of OSA causing ischemic stroke, and the diagnosis and treatment of OSA in patients with ischemic stroke.

Carotid atherosclerosis is closely associated with ischemic stroke. Research shows that the rupture of vulnerable carotid plaque is an important reason for carotid atherosclerosis leading to thromboembolic events. Therefore, early identification of vulnerable carotid plaques is of great significance for the diagnosis, treatment, and prevention of ischemic stroke. This article reviews the pathophysiological features, imaging evaluation of carotid plaque and its relationship with ischemic stroke.

Objective:To investigate the impact of obstructive sleep apnea (OSA) on neurological function outcome in patients with acute ischemic stroke (AIS) at 90 days after onset.Methods:Patients with AIS admitted to Hefei Second People's Hospital from September 2022 to June 2023 were prospectively included. According to the modified Rankin Scale score at 90 days after onset, they were divided into a good outcome group (0-2) and a poor outcome group (>2). The demographic data, vascular risk factors, baseline laboratory tests, National Institutes of Health Stroke Scale (NIHSS) scores at admission, severity of obstructive sleep apnea (OSA), and apnea hypopnea index (AHI) were compared between the two groups. Multivariate logistic regression analysis was used to determine the independent risk factors for poor outcomes. Results:A total of 104 patients with AIS were enrolled, including 62 males (59.6%), with a median age of 65.5 years (interquartile range, 57.0-72.0 years). The median baseline NIHSS score was 3.00 (interquartile range, 2.00-4.00). The median AHI was 18.14/h (interquartile range, 11.34-27.88/h), 43 patients (41.35%) with no/mild OSA and 61 patients (58.65%) with moderate to severe OSA. Seventy-four patients (71.2%) had good outcome, and 30 patients (28.8%) had poor outcome. When introducing AHI as a categorical variable into the logistic regression model, the higher baseline NIHSS score (odds ratio [ OR] 3.041, 95% confidence interval [ CI] 1.797-5.145; P<0.001) and moderate to severe OSA ( OR 4.413, 95% CI 1.032-18.877; P=0.045) were independent risk factors for poor outcome; When introducing AHI as a continuous variable into the logistic regression model, higher baseline NIHSS score ( OR 3.176, 95% CI 1.844-5.472; P<0.001), age ( OR 1.093, 95% CI 1.014-1.177; P=0.020), and AHI ( OR 1.044, 95% CI 1.002-1.089; P=0.042) were independent risk factors for poor outcome. Conclusion:Moderate to severe OSA is an independent risk factor for poor functional outcome in patients with AIS at 90 days after onset, and a higher AHI indicates poor outcome in patients.

Objective:To develop a short-term prognostic model of spontaneous cerebral hemorrhage based on eXtreme Gradient Boosting (XGBoost) machine learning, and to compare its predictive performance with a Logistic regression model.Methods:Patients with sICH admitted to Department of Neurology, Second People's Hospital of Hefei from January 2018 to March 2022 were chosen; their general demographic characteristics, medical history, laboratory indices and cranial imaging data were retrospectively collected. The prognoses of patients 90 d after discharge were evaluated according to modified Rankin Scale (mRS) scores (good prognosis: mRS scores<3; poor prognosis: mRS scores≥3). XGboost and multiple Logistic regression models were used to screen out the factors for prognoses of patients 90 d after discharge, and area under receiver operating characteristic (ROC) curves, sensitivity, specificity and prediction accuracy of the 2 models were analyzed and compared.Results:A total of 413 patients with sICH were included; 180 patients(43.6 %) had poor prognosis and 233 (56.4%) had good prognosis 90 d after discharge. Multivariate Logistic regression results showed that age≥65 years, hemorrhage into the ventricle, hematoma volume of 20-40 mL, hematoma volume>40 mL and National Institutes of Health Stroke Scale (NIHSS) scores were independent influencing factors for short-term prognoses of sICH ( P<0.05). The variables in the XGBoost model were ranked in order of importance: NIHSS scores, systolic blood pressure at admission, Glasgow coma scale (GCS) scores, age≥65 years, hemorrhage into the ventricle, hematoma volume of 20-40 mL, and hematoma volume>40 mL. AUC of XGBoost model in predicting the prognosis was 0.895 (95% CI: 0.820-0.947), enjoying sensitivity of 68.89%, specificity of 94.83%, and prediction accuracy of 83.5%. AUC of Logistic regression model in predicting the prognosis was 0.894 (95% CI: 0.818-0.946), enjoying sensitivity of 93.33%, specificity of 70.69%, and prediction accuracy of 80.58%. Conclusion:The short-term prognostic model based on XGboost for sICH patients has high predictive efficacy, whose predictive accuracy is better than traditional Logistic regression.