Predicting functional outcome in acute ischemic stroke patients after endovascular treatment by machine learning.

Background: Endovascular therapy (EVT) was the standard treatment for acute ischemic stroke with large vessel occlusion. Prognosis after EVT is always a major concern. Here, we aimed to explore a predictive model for patients after EVT. Method: A total of 156 patients were retrospectively enrolled. The primary outcome was functional dependence (defined as a 90-day modified Rankin Scale score ≤ 2). Least absolute shrinkage and selection operator and univariate logistic regression were used to select predictive factors. Various machine learning algorithms, including multivariate logistic regression, linear discriminant analysis, support vector machine, k-nearest neighbors, and decision tree algorithms, were applied to construct prognostic models. Result: Six predictive factors were selected, namely, age, baseline National Institute of Health Stroke Scale (NIHSS) score, Alberta Stroke Program Early CT (ASPECT) score, modified thrombolysis in cerebral infarction score, symptomatic intracerebral hemorrhage (sICH), and complications (pulmonary infection, gastrointestinal bleeding, and cardiovascular events). Based on these variables, various models were constructed and showed good discrimination. Finally, a nomogram was constructed by multivariate logistic regression and showed a good performance. Conclusion: Our nomogram, which was composed of age, baseline NIHSS score, ASPECT score, recanalization status, sICH, and complications, showed a very good performance in predicting outcome after EVT.

Correction: Liu et al. A Predictive Model for the Risk of Posterior Circulation Stroke in Patients with Intracranial Atherosclerosis Based on High Resolution MRI. Diagnostics 2022, 12, 812.

Errors occurred in the number of patients in the posterior circulation ischemic stroke (PCIS) group and non-PCIS group described in the original publication [...].

A Nomogram for Predicting Symptomatic Intracranial Hemorrhage after Endovascular Thrombectomy.

BACKGROUND: Symptomatic intracranial hemorrhage (sICH) is a devastating complication of endovascular thrombectomy (EVT). We aim to develop and validate a nomogram for predicting sICH in patients with large vessel occlusion (LVO) in the anterior circulation. METHODS: We performed a single-center retrospective analysis on collected data from patients undergoing EVT for LVO in the anterior circulation between January 2018 and December 2021. Forward stepwise logistic regression was performed to identify independent predictors of sICH and establish a nomogram. The discrimination and calibration of the model was accessed using the area under the receiver operating characteristic curve (AUC-ROC) and calibration plot. The model was internally validated using bootstrap and 5-fold cross-validation. RESULTS: 243 patients were included, among whom 23 developed sICH (9.5%). After multivariate logistic regression, baseline glucose level (odds ratio [OR], 1.16; p = 0.022), Alberta Stroke Program Early CT Score (OR, 0.44; p < 0.001), regional Leptomeningeal Collateral score (OR, 0.74; p < 0.001) were identified as independent predictors of sICH, which were then incorporated into a predictive nomogram. The ROC curve of the model showed good discriminative ability with an AUC of 0.856 (95% CI: 0.785-0.928). The calibration plot of the model demonstrated good consistency between the actual observed and the predicted probability of sICH. The model was internally validated by using bootstrap (1000 resamples) with an AUC of 0.835 (95%CI: 0.782-0.887) and 5-fold cross-validation with an AUC of 0.831 (95%CI: 0.775-0.887). CONCLUSION: Our model is a reliable tool to predict sICH after EVT. Although the model was internally validated, further external validation is also warranted.

A Predictive Model for the Risk of Posterior Circulation Stroke in Patients with Intracranial Atherosclerosis Based on High Resolution MRI.

Intracranial vertebrobasilar atherosclerosis is the main cause of posterior circulation ischemic stroke. We aimed to construct a predictive model for the risk of posterior circulation ischemic stroke in patients with posterior circulation atherosclerosis based on high-resolution MRI (HR-MRI). A total of 208 consecutive patients with posterior circulation atherosclerosis confirmed by HR-MRI, from January 2020 to July 2021, were retrospectively assessed. They were assigned to the posterior circulation stroke (49 patients) and non-posterior circulation stroke group (159 patients) based on clinical presentation and diffusion-weighted imaging (DWI). Demographic data, risk factors of atherosclerosis, laboratory findings, and imaging characteristics were extracted from electronic health records. Plaque features were investigated by HR-MRI. Fifty-three clinical or imaging features were used to derive the model. Multivariable logistic regression analysis was employed to construct the prediction model. The nomogram was evaluated for calibration, differentiation, and clinical usefulness. Plaque enhancement, plaque irregular surface morphology, artery location of plaque, and dorsal quadrant of plaque location were significant predictors for posterior circulation stroke in patients with intracranial atherosclerosis. Subsequently, these variables were selected to establish a nomogram. The model showed good distinction (C-index 0.830, 95% CI 0.766-0.895). The calibration curve also showed excellent consistency between the prediction of the nomogram and the observed curve. Decision curve analysis further demonstrated that the nomogram conferred significantly high clinical net benefit. The nomogram calculated from plaque characteristics in HR-MRI may accurately predict the posterior circulation stroke occurrence and be of great help for stratification of stroke decision making.

Posterior Circulation ASPECTS on CT Angiography Predicts Futile Recanalization of Endovascular Thrombectomy for Acute Basilar Artery Occlusion.

Background: Acute basilar artery occlusion (BAO) is the most potentially disastrous outcome and has a high risk of recurrence stroke in posterior circulation infarction (PCI). However, the rate of futile recanalization remains high despite successful recanalization. The objective of this study was to investigate 90 days functional outcomes among patients with BAO who underwent endovascular thrombectomy (EVT) and to identify the risk factors associated with futile recanalization. Methods: We retrospectively analyzed 72 patients with acute BAO who received EVT from January 2018 to June 2021. CT angiography source images posterior circulation Acute Stroke Prognosis Early CT Score (CTA-SI pc-ASPECTS) evaluated the extensive hypoattenuation in patients with BAO. Futile recanalization defined an modified Rankin Scale (mRS) of 3-6 at 90 days despite a successful recanalization. Logistic regression analysis was performed to investigate the predictors of futile recanalization. Results: Our sample included a total of 55 eligible patients. Patients with poor outcomes showed that the pc-ASPECTS score was lower in patients with poor outcomes than that in patients with good outcomes (P = 0.017). Longer time from symptoms onset-to-the puncture (P = 0.014) and elevation of leucocytes (P = 0.012) were associated with poor outcomes. The multivariable logistic analysis showed that pc-ASPECTS and onset-to-puncture time (OPT) were independent predictors of futile recanalization. Conclusions: This study suggested that pc-ASPECTS and OPT are independent predictors of futile recanalization after EVT in patients with BAO. The lower pc-ASPECTS score and longer puncture time will have a poor clinical outcome.

Psychological impact on COVID-19 patients during the outbreak in China: A case-control study.

BACKGROUND: The coronavirus disease 2019 (COVID-19) has caused widespread panic due to its highly infectious and pandemic transmission. We aimed to evaluate the psychological impact of the COVID-19 outbreak on infected subjects in China. METHODS: This case-control, survey-based study assessed the psychological status of COVID-19 patients and non-infected controls from February 10 to March 18, 2020, in China. Sex, age, education years, marital status, jobs, annual household income, living status, and geographic origin were matched between the two groups. The main outcome measures included anxiety, depression, insomnia, help-seeking behaviors, and treatment for mental problems. RESULTS: A total of 326 patients and 1304 (1:4 ratio) matched non-infected controls were enrolled. Compared with controls, patients had higher scores on the Beck Anxiety Inventory (BAI), Patient Health Questionnaire-9 (PHQ-9), and Insomnia Severity Index (ISI) (all p<0.01). Patients had higher rate of any mental problems (62.6% vs 42.5%, p<0.01), anxiety (27.3% vs 12.2%, p<0.01), depression (26.7% vs 14.6%, p<0.01), suicidal ideation (16.0% vs 10.7%, p<0.01), and insomnia (57.7% vs 36.7%, p<0.01). Among the subjects with mental problems, the proportion of seeking help (15.2% vs 6.9%, p<0.01) and receiving treatment (11.3% vs 4.3%, p<0.01) was higher in patients than controls. CONCLUSIONS: Our study showed a higher prevalence of mental problems in COVID-19 patients compared to controls, suggesting a great psychological impact of COVID-19 infection. Our findings highlighted the urgent need for psychological assistance for COVID-19 patients.

Mental Health and Psychological Responses During the Coronavirus Disease 2019 Epidemic: A Comparison Between Wuhan and Other Areas in China.

OBJECTIVE: This study aimed to compare the mental health and psychological responses in Wuhan, a severely affected area, and other areas of China during the coronavirus disease 2019 (COVID-19) epidemic. METHODS: This cross-sectional study was conducted on February 10-20, 2020. A set of online questionnaires was used to measure mental health and responses. A total of 1397 participants from Wuhan (age, 36.4 ± 10.7 years; male, 36.1%) and 2794 age- and sex-matched participants from other areas of China (age, 35.9 ± 9.9 years; male, 39.0%) were recruited. RESULTS: Compared with their counterparts, participants from Wuhan had a significantly higher prevalence of any mental health problems (46.6% versus 32.2%; adjusted odds ratio [OR] = 1.89, 95% confidence interval [CI] = 1.65-2.17), anxiety (15.2% versus 6.2%; adjusted OR = 2.65, 95% CI = 2.14-3.29), depression (18.3% versus 9.7%; adjusted OR = 2.11, 95% CI = 1.74-2.54), suicidal ideation (10.5% versus 7.1%; adjusted OR = 1.60, 95% CI = 1.28-2.02), and insomnia (38.6% versus 27.6%; adjusted OR = 1.70, 95% CI = 1.48-1.96). Participants from Wuhan had a slightly higher rate of help-seeking behavior (7.1% versus 4.2%; adjusted OR = 1.76, 95% CI = 1.12-2.77) but similar rate of treatment (3.5% versus 2.7%; adjusted OR = 1.23, 95% CI = 0.68-2.24) for mental problems than did their counterparts. In addition, compared with their counterparts, participants from Wuhan gave higher proportions of responses regarding "fearful" (52% versus 36%, p < .001), "discrimination against COVID-19 cases" (64% versus 58%, p = .006), "strictly comply with preventive behaviors" (98.7% versus 96%, p = .003), and "fewer living and medical supplies" (<2 weeks: 62% versus 57%, p = .015). CONCLUSIONS: The COVID-19 epidemic has raised enormous challenges regarding public mental health and psychological responses, especially in the highly affected Wuhan area. The present findings provide important information for developing appropriate strategies for the prevention and management of mental health problems during COVID-19 and other epidemics.

Statin on post-stroke epilepsy: A systematic review and meta-analysis.

INTRODUCTION: Recent research has shown that statins can reduce the incidence of epilepsy after stroke, especially ischemic stroke, but the results are inconsistent. In view of current stroke guidelines do not recommend the use of anti-epileptic drugs (AED) for the prevention of epilepsy after stroke, statins may be a good choice. The purpose of this study was to conduct a systematic review and meta-analysis to determine the effect of statins on the prevention of epilepsy after stroke. METHODS: Correlative cohort studies were identified through search of PubMed, Cochrane Library and Embase databases. The main outcomes included post-stroke epilepsy (PSE) and early-onset seizure (ES). Subgroup analyses and Sensitivity analysis were performed to evaluate the influences of the predefined study characteristics on the outcome. RESULTS: Seven studies were included (n = 40831). Statin use was associated with a lower risk of PSE (including 6 articles) (odds ratio [OR] 0.60, 95% confidence interval [CI] [0.42, 0.84], p = 0.003), and there is a remarkable effect in ES (including 6 articles) (OR 0.36, 95% CI [0.25, 0.54], p < 0.00001). CONCLUSION: Appropriate use of statins after stroke can reduce the risk of PSE, especially ES.

The mental health of frontline and non-frontline medical workers during the coronavirus disease 2019 (COVID-19) outbreak in China: A case-control study.

BACKGROUND AND OBJECTIVE: Coronavirus disease 2019 (COVID-19) is a new infectious disease with high transmissibility and morbidity. It has caused substantial mental distress to medical professionals. We aimed to compare the psychological impact of the COVID-19 outbreak between frontline and non-frontline medical workers in China. METHODS: This case-control study recruited 1173 frontline and 1173 age- and sex-matched non-frontline medical workers during the COVID-19 outbreak (February 11 to 26, 2020). A set of online questionnaires were used to measure mental problems (i.e., anxiety, insomnia, and depressive symptoms), and help-seeking behavior and treatment for these mental problems. RESULTS: Frontline medical workers had higher rates of any mental problem (52.6% vs. 34.0%, adjusted OR=1.88, 95% CI=1.57-2.25), anxiety symptoms (15.7% vs. 7.4%, adjusted OR=1.95, 95% CI=1.46-2.61), depressed mood (marginally insignificant; 14.3% vs. 10.1%, adjusted OR=1.32, 95% CI=0.99-1.76) and insomnia (47.8% vs. 29.1%, adjusted OR=1.96, 95% CI=1.63-2.36) than non-frontline medical workers. No significant difference was observed in terms of suicidal ideation (12.0% vs. 9.0%, adjusted OR=1.25, 95% CI=0.92-1.71), help-seeking (4.5% vs. 4.5%, adjusted OR=1.00, 95% CI=0.53-1.87) or treatment (3.4% vs. 2.3%, adjusted OR=1.38, 95% CI=0.54-3.52) for mental problems. LIMITATIONS: The case-control nature of the data precludes causal inferences, and there is a possibility of bias related to self-reports. CONCLUSIONS: Frontline medical workers had more mental problems but comparable help-seeking behaviors and treatment for these problems than non-frontline medical workers. These findings highlight the timely mental support and intervention for medical workers, especially for those on the frontline.