Development and validation of a machine learning-based predictive model for assessing the 90-day prognostic outcome of patients with spontaneous intracerebral hemorrhage.

BACKGROUND: Spontaneous intracerebral hemorrhage (sICH) is associated with significant mortality and morbidity. Predicting the prognosis of patients with sICH remains an important issue, which significantly affects treatment decisions. Utilizing readily available clinical parameters to anticipate the unfavorable prognosis of sICH patients holds notable clinical significance. This study employs five machine learning algorithms to establish a practical platform for the prediction of short-term prognostic outcomes in individuals afflicted with sICH. METHODS: Within the framework of this retrospective analysis, the model underwent training utilizing data gleaned from 413 cases from the training center, with subsequent validation employing data from external validation center. Comprehensive clinical information, laboratory analysis results, and imaging features pertaining to sICH patients were harnessed as training features for machine learning. We developed and validated the model efficacy using all the selected features of the patients using five models: Support Vector Machine (SVM), Logistic Regression (LR), Random Forest (RF), XGboost and LightGBM, respectively. The process of Recursive Feature Elimination (RFE) was executed for optimal feature screening. An internal five-fold cross-validation was employed to pinpoint the most suitable hyperparameters for the model, while an external five-fold cross-validation was implemented to discern the machine learning model demonstrating the superior average performance. Finally, the machine learning model with the best average performance is selected as our final model while using it for external validation. Evaluation of the machine learning model's performance was comprehensively conducted through the utilization of the ROC curve, accuracy, and other relevant indicators. The SHAP diagram was utilized to elucidate the variable importance within the model, culminating in the amalgamation of the above metrics to discern the most succinct features and establish a practical prognostic prediction platform. RESULTS: A total of 413 patients with sICH patients were collected in the training center, of which 180 were patients with poor prognosis. A total of 74 patients with sICH were collected in the external validation center, of which 26 were patients with poor prognosis. Within the training set, the test set AUC values for SVM, LR, RF, XGBoost, and LightGBM models were recorded as 0.87, 0.896, 0.916, 0.885, and 0.912, respectively. The best average performance of the machine learning models in the training set was the RF model (average AUC: 0.906 ± 0.029, P < 0.01). The model still maintains a good performance in the external validation center, with an AUC of 0.817 (95% CI 0.705-0.928). Pertaining to feature importance for short-term prognostic attributes of sICH patients, the NIHSS score reigned supreme, succeeded by AST, Age, white blood cell, and hematoma volume, among others. In culmination, guided by the RF model's variable importance weight and the model's ROC curve insights, the NIHSS score, AST, Age, white blood cell, and hematoma volume were integrated to forge a short-term prognostic prediction platform tailored for sICH patients. CONCLUSION: We constructed a prediction model based on the results of the RF model incorporating five clinically accessible predictors with reliable predictive efficacy for the short-term prognosis of sICH patients. Meanwhile, the performance of the external validation set was also more stable, which can be used for accurate prediction of short-term prognosis of sICH patients.

Thiazolidinediones Decrease the Recurrence of Intracerebral Hemorrhage in Type 2 Diabetes Mellitus Patients: A Nested Case-Control Study.

INTRODUCTION: Preclinical evidence demonstrated the therapeutic potential of thiazolidinediones (TZDs) for the treatment of intracerebral hemorrhage (ICH). The present study conducted an investigation of cerebrovascular and cardiovascular outcomes following ICH in patients with type 2 diabetes mellitus (T2DM) treated with or without TZDs. METHODS: This retrospective nested case-control study used data from the Taiwan National Health Insurance Research Database. A total of 62,515 T2DM patients who were hospitalized with a diagnosis of ICH were enrolled, including 7,603 TZD users. Data for TZD non-users were extracted using propensity score matching. Primary outcomes included death and major adverse cardiovascular events (MACEs), which were defined as a composite of ischemic stroke, hemorrhagic stroke (HS), acute myocardial infarction, and congestive heart failure. Patients aged <20 years with a history of traumatic brain injury or any prior history of MACEs were excluded. RESULTS: TZD users had significantly lower MACE risks compared with TZD non-users following ICH (adjusted hazard ratio [aHR]: 0.90, 95% confidence interval [CI]: 0.85-0.94, p < 0.001). The most significant MACE difference reported for TZD users was HS, which possessed lower incidence than in TZD non-users, especially for the events that happened within 3 months following ICH (aHR: 0.74, 95% CI: 0.62-0.89 within 1 month, p < 0.01; aHR: 0.68, 95% CI: 0.54-0.85 between 1 and 3 month). CONCLUSION: The use of TZD in patients with T2DM was associated with a lower risk of subsequent HS and mortality following ICH.

Systematic Evaluation of Hematoma Expansion Models in Spontaneous Intracerebral Hemorrhage: A Meta-Analysis and Meta-Regression Approach.

INTRODUCTION: Accurate prediction of hematoma expansion (HE) in spontaneous intracerebral hemorrhage (sICH) is crucial for tailoring patient-specific treatments and improving outcomes. Recent advancements have yielded numerous HE risk factors and predictive models. This study aims to evaluate the characteristics and efficacy of existing HE prediction models, offering insights for performance enhancement. METHODS: A comprehensive search was conducted in PubMed for observational studies and randomized controlled trials focusing on HE prediction, written in English. The prediction models were categorized based on their incorporated features and modeling methodology. Rigorous quality and bias assessments were performed. A meta-analysis of studies reporting C-statistics was executed to assess and compare the performance of current HE prediction models. Meta-regression was utilized to explore heterogeneity sources. RESULTS: From 358 initial records, 22 studies were deemed eligible, encompassing traditional models, hematoma imaging feature models, and models based on artificial intelligence or radiomics. Meta-analysis of 11 studies, involving 12,087 sICH patients, revealed an aggregated C-statistic of 0.74 (95% CI: 0.69-0.78) across seven HE prediction models. Eight characteristics related to development cohorts were identified as key factors contributing to performance variability among these models. CONCLUSION: The findings indicate that the current predictive capacity for HE risk remains suboptimal. Enhanced accuracy in HE prediction is vital for effectively targeting patient populations most likely to benefit from tailored treatment strategies.

Postoperative fever and clinical outcomes after endoscopic surgery for spontaneous intracerebral hemorrhage: a retrospective database study.

BACKGROUND: Spontaneous intracerebral hemorrhage (SICH) is a severe stroke with high mortality and disability rates. Endoscopic surgery is an increasingly widely used minimally invasive method for the treatment of SICH. However, the impact of fever on patient outcomes remains unclear. METHODS: We retrospectively included patients aged 18 years or older with supratentorial SICH confirmed by CT, who underwent endoscopic hematoma evacuation within 48 h of symptom onset. The primary outcome was the modified Rankin Scale (mRS) score at 3 months. Secondary outcomes included hospital and neurosurgical intensive care unit (NSICU) stays, and perioperative complications. We analyzed the association between postoperative fever (highest temperature within 24 h after surgery) and these outcomes using multivariate analysis, generalized additive models, and segmented regression analysis. RESULTS: Of the 56 patients, 38 had favorable outcomes (mRS ≤ 3) and 18 had unfavorable outcomes (mRS > 3) at 3 months. A threshold effect at 38.2 °C was observed between postoperative body temperature and clinical outcomes. The mean age was 56 years (SD = 9) for the > 38.2 °C group and 58 years (SD = 8) for the ≤ 38.2 °C group, with a similar proportion of male patients (63% vs. 69%, P = 0.635). Patients with postoperative fever had larger hematoma volumes (65 vs. 56 mL; P = 0.008). Other characteristics were similar between the groups. Postoperative fever (> 38.2 °C) was independently associated with a 4.99-fold increased risk of unfavorable outcomes (95% CI = [1.13 to 25.90]; P = 0.040), which remained significant after excluding patients with postoperative complications (adjusted RR = 16.03, 95% CI = [1.69 to 417.24]; P = 0.033). The association was consistent across subgroups with different Glasgow Coma Scale scores, hematoma volumes, and intraventricular extension. Postoperative fever was also associated with longer NSICU stays (3.1 vs. 2.3 days; P = 0.023), longer hospital stays (17.2 vs. 13.6 days; P = 0.010), more residual hematoma, and greater edema volume. Different antipyretic therapies did not affect outcomes. CONCLUSIONS: This study identifies a temperature threshold (38.2 °C) associated with poor outcomes in SICH patients undergoing endoscopic surgery. Further research is needed to mitigate postoperative fever and improve patient outcomes.

Machine learning based classification of spontaneous intracranial hemorrhages using radiomics features.

PURPOSE: To assess the efficacy of radiomics features extracted from non-contrast computed tomography (NCCT) scans in differentiating multiple etiologies of spontaneous intracerebral hemorrhage (ICH). METHODS: CT images and clinical data from 141 ICH patients from 2010 to 2022 were collected. The cohort comprised primary (n = 57), tumorous (n = 46), and vascular malformation-related ICH (n = 38). Radiomics features were extracted from the initial brain NCCT scans and identified potential features using mutual information. A hierarchical classification with AdaBoost classifiers was employed to classify the multiple etiologies of ICH. Age of the patient and ICH's location were examined alongside radiomics features. The accuracy, area under the curve (AUC), sensitivity, and specificity were used to evaluate classification performance. RESULTS: The proposed method achieved an accuracy of 0.79. For identifying primary ICH, the model achieved a sensitivity of 0.86 and specificity of 0.87. Meanwhile, the sensitivity and specificity for identifying tumoral causes were 0.78 and 0.93, respectively. For vascular malformation, the model reached a sensitivity and specificity of 0.72 and 0.89, respectively. The AUCs for primary, tumorous, and vascular malformation were 0.86, 0.85, and 0.82, respectively. The findings further highlight the importance of texture-based variables in ICH classification. The age and location of the ICH can enhance the classification performance. CONCLUSION: The use of a machine learning model with radiomics features has the potential in classifying the three types of non-traumatic ICH. It may help the radiologist decide on an appropriate further examination plan to arrive at a correct diagnosis.

Associations of serum Dickkopf-1 levels with disease severity and 90-day Prognosis after spontaneous intracerebral hemorrhage: results from the prospective cohort study.

Dickkopf-1 (DKK-1) may be involved in inflammatory response and secondary brain injury after acute brain injury. We gauged serum DKK-1 levels and further assessed its correlation with disease severity and investigated its predictive value for 90-day prognosis in patients with spontaneous intracerebral hemorrhage (sICH). Serum DKK-1 levels were measured in 128 sICH patients and 128 healthy controls. The severity of sICH was assessed using the Glasgow Coma Scale (GCS) scores and hematoma volumes. Poor prognosis was referred to as a Glasgow Outcome Scale (GOS) score of 1-3 at 90 days after stroke. Multivariate analysis was performed to identify associations of serum DKK-1 levels with disease severity, early neurological deterioration (END) and poor prognosis. Receiver operating characteristic curve (ROC) was built to investigate the prognostic predictive capability. The serum DKK-1 levels of patients were significantly higher than those of controls (median, 4.74 ng/mL versus 1.98 ng/mL; P < 0.001), and were independently correlated with hematoma volumes (ρ = 0.567, P < 0.001; t = 3.444, P = 0.001) and GCS score (ρ = -0.612, P < 0.001; t = -2.048, P = 0.043). Serum DKK-1 significantly differentiated patients at risk of END (area under ROC curve (AUC), 0.850; 95% confidence interval (CI), 0.777-0.907; P < 0.001) and poor prognosis (AUC, 0.830; 95% CI, 0.753-0.890; P < 0.001), which had similar prognostic ability, as compared to GCS scores and hematoma volumes. Subsequent Logistic regression model affirmed that GCS score, hematoma volume, and serum DKK-1 levels were independently associated with END and poor prognosis at 90 days after sICH. The models, which contained them, performed well using ROC curve analysis and calibration curve analysis. Serum DKK-1 levels are markedly associated with disease severity, END and 90-day poor prognosis in sICH. Hence, serum DKK-1 is presumed to be used as a potential prognostic biomarker of sICH.

Timing Matters: Ultra-Early and Early versus Late Thromboprophyaxis Following Spontaneous Intracerebral Hemorrhage: A Systematic Review and Meta-Analysis.

Spontaneous intracerebral hemorrhage (ICH) represents a critical and potentially devastating medical event resulting from the rupture of intracerebral vessels. Patients afflicted with ICH face an increased risk of venous thromboembolism (VTE) due to factors such as immobility. However, determining the ideal timing for initiating venous thromboembolism thromboprophylaxis (TP) remains uncertain, as it may carry the potential risk of exacerbating hematoma expansion. Thus, our objective was to ascertain the optimal timing for initiating TP following ICH through a comprehensive systematic review and meta-analysis.This systematic review and meta-analysis were performed following the Cochrane Collaboration and the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) statement guidelines, considering outcomes based on the time of intervention: Ultra early (UEPT) < 24 h, Early (EPT) < 48 h, Late (LPT) > 48 h to perform an analysis on hematoma expansion and mortality.Of 2.777 Hematoma expansion was not more frequent in the 440 patients receiving UEPT/EPT (n = 440) versus 565 receiving LPT (Odds ratio (OR) 0.94 (95% CI; 0.62 to 1.43; I2 = 0%)). Similarly, mortality was not lower in the 293 received UEPT or EPT versus 477 receiving LPT (OR 0.63 (95% CI; 0.39 to 1.0; I2 = 0%).This study, through a systematic review and meta-analysis, conclusively found no difference in intracranial hematoma expansion and/or increased mortality between the use of heparin in the early thromboprophylaxis (< 48 h) group compared to the late thromboprophylaxis (> 48 h) group. Implementing this approach in the management of spontaneous cerebral hemorrhage could facilitate progress towards more optimal care protocols.

Early postoperative acetylsalicylic acid administration does not increase the risk of postoperative intracranial bleeding in patients with spontaneous intracerebral hemorrhage.

The recent study by Kaiwen Wang et al., titled "Early postoperative acetylsalicylic acid administration does not increase the risk of postoperative intracranial bleeding in patients with spontaneous intracerebral hemorrhage," explores the association between postoperative intracranial bleeding (PIB) and various risk factors, including smoking, pre-hemorrhagic antiplatelet therapy, and dyslipidemia. While the study highlights that smoker, particularly women, are at increased risk for subarachnoid hemorrhage and acknowledges the risks of pre-hemorrhagic antiplatelet use, it overlooks the potential risk of PIB associated with early postoperative aspirin administration. This critique underscores the need to approach the study's findings with caution, given the broader context of aspirin's risk profile. Specifically, aspirin has been associated with a 37% higher relative risk of any intracranial hemorrhage, as indicated by other randomized trials. Additionally, the study's implications regarding the benefits of aspirin in stroke prevention must be critically evaluated, as the increased risk of intracranial bleeding may outweigh the potential benefits. This abstract emphasizes the importance of careful consideration of aspirin's adverse effects in the context of postoperative care.

Early postoperative acetylsalicylic acid administration does not increase the risk of postoperative intracranial bleeding in patients with spontaneous intracerebral hemorrhage.

Administration of acetylsalicylic acid (ASA) at early stage after surgery for spontaneous intracerebral hemorrhage (SICH) may increase the risk of postoperative intracranial bleeding (PIB), because of potential inhibition of platelet function. This study aimed to investigate whether early ASA administration after surgery was related to increased risk of PIB. This retrospective study enrolled SICH patients receiving surgery from September 2019 to December 2022 in seven medical institution. Based on postoperative ASA administration, patients who continuously received ASA more than three days within seven days post-surgery were identified as ASA users, otherwise as non-ASA users. The primary outcome was symptomatic PIB events within seven days after surgery. Incidence of PIB was compared between ASA users and non-ASA users using survival analysis. This study included 744 appropriate patients from 794 SICH patients. PIB occurred in 42 patients. Survival analysis showed no statistical difference between ASA users and non-ASA users in incidence of PIB (P = 0.900). Multivariate Cox analysis demonstrated current smoker (hazard ratio [HR], 2.50, 95%CI, 1.33-4.71, P = 0.005), dyslipidemia (HR = 3.03; 95%CI, 1.31-6.99; P = 0.010) and pre-hemorrhagic antiplatelet therapy (HR = 3.05; 95% CI, 1.64-5.68; P < 0.001) were associated with PIB. Subgroup analysis manifested no significant difference in incidence of PIB between ASA users and non-ASA users after controlling the effect from factors of PIB (i.e., sex, age, current smoker, regular drinker, dyslipidemia, pre-hemorrhagic antiplatelet therapy and hematoma location). This study revealed that early ASA administration to SICH patients after surgery was not related to increased risk of PIB.

The association between high-oxygen saturation and prognosis for intracerebral hemorrhage.

BACKGROUND: Concerns about the adverse effects of excessive oxygen have grown over the years. This study investigated the relationship between high oxygen saturation and short-term prognosis of patients with spontaneous intracerebral hemorrhage (sICH) after liberal use of oxygen. METHODS: This retrospective cohort study collected data from the Medical Information Mart for Intensive Care III (MIMIC-III) database (ICU cohort) and a tertiary stroke center (general ward cohort). The data on pulse oximetry-derived oxygen saturation (SpO2) during the first 24 h in ICU and general wards were respectively extracted. RESULTS: Overall, 1117 and 372 patients were included in the ICU and general ward cohort, respectively. Among the patients from the ICU cohort, a spoon-shaped association was observed between minimum SpO2 and the risk of in-hospital mortality (non-linear P<0.0001). In comparison with minimum SpO2 of 93-97%, the minimum SpO2>97% was associated with a significantly higher risk of in-hospital mortality after adjustment for confounders. Sensitivity analysis conducted using propensity score matching did not change this significance. The same spoon-shaped association between minimum SpO2 and the risk of in-hospital mortality was also detected for the general ward cohort. In comparison with the group with 95-97% SpO2, the group with SpO2>97% showed a stronger association with, but non-significant risk for, in-hospital mortality after adjustment for confounders. The time-weighted average SpO2>97% was associated significantly with in-hospital mortality in both cohorts. CONCLUSION: Higher SpO2 (especially a minimum SpO2>97%) was unrewarding after liberal use of oxygen among patients with sICH and might even be potentially detrimental.

Research on predicting hematoma expansion in spontaneous intracerebral hemorrhage based on deep features of the VGG-19 network.

PURPOSE: To construct a clinical noncontrastive computed tomography (NCCT) deep learning joint model for predicting early hematoma expansion (HE) after cerebral hemorrhage (sICH) and evaluate its predictive performance. METHODS: All 254 patients with primary cerebral hemorrhage from January 2017 to December 2022 in the General Hospital of the Western Theater Command were included. According to the criteria of hematoma enlargement exceeding 33% or the volume exceeding 6 ml, the patients were divided into the HE group and the hematoma non-enlargement (NHE) group. Multiple models and the 10-fold cross-validation method were used to screen the most valuable features and model the probability of predicting HE. The area under the curve (AUC) was used to analyze the prediction efficiency of each model for HE. RESULTS: They were randomly divided into a training set of 204 cases in an 8:2 ratio and 50 cases of the test set. The clinical imaging deep feature joint model (22 features) predicted the area under the curve of HE as follows: clinical Navie Bayes model AUC 0.779, traditional radiology logistic regression (LR) model AUC 0.818, deep learning LR model AUC 0.873, and clinical NCCT deep learning multilayer perceptron model AUC 0.921. CONCLUSION: The combined clinical imaging deep learning model has a high predictive effect for early HE in sICH patients, which is helpful for clinical individualized assessment of the risk of early HE in sICH patients.

Early Celecoxib Use in Spontaneous Intracerebral Hemorrhage is Associated with Reduced Mortality.

BACKGROUND: Hemorrhagic strokes constitute 10-15% of all strokes and have the worst mortality and morbidity of all subtypes. Mortality and morbidity of spontaneous intracerebral hemorrhage (sICH) are often secondary to the effects of inflammation, brain edema, and swelling. Studies have shown that celecoxib, a selective cyclooxygenase 2 (COX-2) inhibitor, reduces perihematomal edema formation and inflammation. This study aimed to examine the impact of celecoxib on sICH outcomes. METHODS: TriNetX, a multi-institutional research database, was retrospectively queried to identify patients with sICH. Outcomes in patients who received celecoxib within 5 days (cohort 1) were analyzed and compared to those in patients who did not receive celecoxib (cohort 2). The primary end point was mortality within 1 year of sICH. Secondary end points included ventilator dependence, tracheostomy, percutaneous endoscopic gastrostomy tube placement, craniotomy, deep venous thrombosis, pulmonary embolism, ischemic stroke, transient ischemia attack, myocardial infarction, and seizures. Further analysis was performed to assess these outcomes for patients treated with ibuprofen, a nonselective COX inhibitor. RESULTS: After propensity score matching, 833 patients were identified in each cohort based on celecoxib use. Mortality at 1 year was significantly reduced in patients with sICH receiving celecoxib compared to those who did not (13.33% vs. 17.77%; p = 0.0124). Risks of ventilator dependence, tracheostomy, percutaneous endoscopic gastrostomy tube placement, craniotomy, deep venous thrombosis, pulmonary embolism, ischemic stroke, transient ischemia attack, myocardial infarction, and seizures were not significantly increased in patients who received celecoxib within 5 days of sICH compared to those who did not receive celecoxib. There was no significant difference in mortality between patients based on ibuprofen administration. CONCLUSIONS: There exists a growing interest in using COX-2 as a potential target strategy for neuroprotection in patients with sICH, with some evidence of a mortality benefit in small cohort studies. This study shows that early celecoxib use is associated with decreased mortality in patients with sICH.

Mortality, Functional Status, and Quality of Life after 5 Years of Patients Admitted to Critical Care for Spontaneous Intracerebral Hemorrhage.

BACKGROUND: The objective of this study was to assess long-term outcome in patients with spontaneous intracerebral hemorrhage admitted to the intensive care unit. METHODS: Mortality and Glasgow Outcome Scale, Barthel Index, and 5-level EQ-5D version (EQ-5D-5L) scores were analyzed in a multicenter cohort study of three Spanish hospitals (336 patients). Mortality was also analyzed in the Medical Information Mart for Intensive Care III (MIMIC-III) database. RESULTS: The median (25th percentile-75th percentile) age was 62 (50-70) years, the median Glasgow Coma Score was 7 (4-11) points, and the median Acute Physiology and Chronic Health disease Classification System II (APACHE-II) score was 21 (15-26) points. Hospital mortality was 54.17%, mortality at 90 days was 56%, mortality at 1 year was 59.2%, and mortality at 5 years was 66.4%. In the Glasgow Outcome Scale, a normal or disabled self-sufficient situation was recorded in 21.5% of patients at 6 months, in 25.5% of patients after 1 year, and in 22.1% of patients after 5 years of follow-up (4.5% missing). The Barthel Index score of survivors improved over time: 50 (25-80) points at 6 months, 70 (35-95) points at 1 year, and 90 (40-100) points at 5 years (p < 0.001). Quality of life evaluated with the EQ-5D-5L at 1 year and 5 years indicated that greater than 50% of patients had no problems or slight problems in all items (mobility, self-care, usual activities, pain/discomfort, and anxiety/depression). In the MIMIC-III study (N = 1354), hospital mortality was 31.83% and was 40.5% at 90 days and 56.2% after 5 years. CONCLUSIONS: In patients admitted to the intensive care unit with a diagnosis of nontraumatic intracerebral hemorrhage, hospital mortality up to 90 days after admission is very high. Between 90 days and 5 years after admission, mortality is not high. A large percentage of survivors presented a significant deficit in quality of life and functional status, although with progressive improvement over time. Five years after the hemorrhagic stroke, a survival of 30% was observed, with a good functional status seen in 20% of patients who had been admitted to the hospital.

Application of Robotic Stereotactic Assistance (ROSA) for spontaneous intracerebral hematoma aspiration and thrombolytic catheter placement.

BACKGROUND: Spontaneous intracerebral hemorrhage (ICH) accounts for up to 20% of all strokes and results in 40% mortality at 30 days. Although conservative medical management is still the standard treatment for ICH patients with small hematoma, patients with residual hematoma ≤15 mL after surgery are associated with better functional outcomes and survival rates. This study reported our clinical experience with using Robotic Stereotactic Assistance (ROSA) as a safe and effective approach for stereotactic ICH aspiration and intra-clot catheter placement. METHODS: A retrospective analysis was conducted of patients with spontaneous ICH who underwent ROSA-guided ICH aspiration surgery. ROSA-guided ICH surgical techniques, an aspiration and intra-clot catheter placement protocol, and a specific operative workflow (pre-operative protocol, intraoperative procedure and postoperative management) were employed to aspirate ICH using the ROSA One Brain, and appropriate follow-up care was provided. RESULTS: From September 14, 2021 to May 4, 2022, a total of 7 patients were included in the study. Based on our workflow design, ROSA-guided stereotactic ICH aspiration effectively aspirated more than 50% of hematoma volume (or more than 30 mL for massive hematomas), thereby reducing the residual hematoma to less than 15 mL. The mean operative time of entire surgical procedure was 1.3 ± 0.3 h, with very little perioperative blood loss and no perioperative complications. No patients required catheter replacement and all patients' functional status improved. CONCLUSIONS: Within our clinical practice ROSA-guided ICH aspiration, using our established protocol and workflow, was safe and effective for reducing hematoma volume, with positive functional outcomes.

Left atrial appendage occlusion in patients with spontaneous intracerebral hemorrhage: An observational study.

BACKGROUND: Patients with atrial fibrillation (AF) and intracerebral hemorrhage (ICH) are at high risk of ischemic and recurrent bleeding events. Therefore, the decision of restarting or avoiding anticoagulation is challenging. Left atrial appendage occlusion (LAAO) is an alternative for these patients. However, few data are available about safety of early LAAO and factors associated with ischemic stroke and ICH recurrence. METHODS: A unicentric, observational, retrospective study including all patients with AF and a previous ICH who underwent LAAO. We analyzed baseline clinical and neuroimaging characteristics, procedural outcomes, post-procedural therapies and long-term follow-up. RESULTS: Forty patients were included, whose mean age was 76.6 ±7.6 years and 73 % were men. In patients in whom a Magnetic Resonance (MR) was performed (n=22, 55 %), cortical microbleeds were detected in 15 (68 %) and cortical superficial siderosis in one patient. The procedure was successful and safe in 100 % of the patients and it was performed within 30 days of the ICH in 37 % of them. After a median follow up of 46.2 months [26-69], intracranial hemorrhage (ICrH) recurrence occurred in 6 patients (5 ICH and 1 subdural hematoma -SDH-) and the index ICH was lobar in all of them. Ischemic events were significantly lower than expected according to the CHA2DS2-VASc score (7.5 % vs. 16.6 %, p=0.048) and bleeding events were similar to expected by the HAS-BLED score (20 % vs 23.4 %, p=0.63). CONCLUSIONS: In patients with ICH and AF, early LAAO was found to be safe and associated with a reduction in ischemic stroke. However, recurrent ICH risk remains high, and it appears to be mainly driven by cerebral amyloid angiopathy.

Iatrogenic Cerebral Amyloid Angiopathy: Two Case Reports to Explore Clinical Heterogeneity and Pathological Patterns.

INTRODUCTION: These case reports illustrate Iatrogenic Cerebral Amyloid Angiopathy (iCAA) due to neurosurgical procedures. Recent studies propose prion transmission during neurosurgery as a potential mechanism for ß-amyloid seed implantation, linking neurosurgical history to the development of iCAA. The majority of reported cases in the literature have an unfavorable prognosis, with recurrence of intracerebral hemorrahge (ICH) and subsequent death during the first months of follow-up. There is no effective treatment for preventing the progression of the disease. RESULTS: a 41-year-old man with a previous history of left frontotemporal traumatic brain injury and subsequent neurosurgical intervention in childhood was admitted with an ICH leading to the diagnosis of iCAA. The patient's history of exposure, combined with imaging studies and neuropsychological assessments, supported the suspicion of iCAA. Confirmatory PET-CT scans revealed ß-amyloid deposits in the cortical regions, aligning with the proposed criteria for iCAA. At the 2-year follow-up, the patient presents an NIHSS of 0 and a Modified Rankin Scale (mRS) of 1. The second case involved a 50-year-old man with a history of surgical treatment for Arnold-Chiari malformation, who developed transient neurological deficits and presented multiple ICH. The patient's history of neurosurgical intervention and the radiological and clinical features supported the diagnosis of probable iAAC. Despite a negative PET-CT result, CSF analysis provided evidence of ß-amyloid accumulation in the CNS. At the 6-year follow-up, the patient presented an NIHSS of 1(hemihypoesthesia) and mRS of 3. CONCLUSION: iCAA is an emerging pathology probably driven by prion transmission of ß-amyloid seed after neurosurgical interventions. It is important to suspect this condition in young patients with ICH and a history of neurosurgical procedure. Recognizing iCAA's clinical and radiological features is crucial for early identification. The diagnosis process is based on demonstrating the accumulation of ß-amyloid protein in the central nervous system using PET-CT or cerebrospinal fluid (CSF) studies and also conducting genetics studies. As an evolving pathology without a clear pathophysiology and a potential divergent evolution between phenotypes, establishing standardized diagnostic criteria and a multicenter registry is imperative for a comprehensive understanding of iCAA.

Association between the C-reactive protein to albumin ratio and poor clinical outcome in patients with spontaneous intracerebral hemorrhage.

BACKGROUND: The C-reactive protein-to-albumin ratio (CAR) is a novel prognostic biomarker of systemic inflammation and nutritional status. The association between CAR and the long-term outcome of spontaneous intracerebral hemorrhage (ICH) remains unclear. METHODS: From January 2014 to September 2016, 497 patients with spontaneous ICH were enrolled in our study from 13 hospitals in Beijing. According to the CAR quartiles, patients were classified into four groups (Q1-Q4). Logistic regression was applied to analyze the relationship between different CAR levels and main outcome (90-day and 1-year mRS 4-6). Restricted cubic splines and receiver operating characteristic (ROC) curves of CAR for poor clinical outcomes were assessed. RESULTS: In the multivariate logistic regression model, compared with the lowest quartile of CAR, the adjusted odds ratios of the Q2, Q3, and Q4 group for 90-day mRS score of 4-6 were 3.64 (1.61-8.23), 3.83 (1.67-8.77), and 8.91 (3.85-20.64). In terms of 1-year mRS score of 4-6, compared with the lowest quartile of CAR, the adjusted odds ratios of the Q3 and Q4 group were 3.31 (1.33-8.22) and 6.87 (2.81-16.78). CONCLUSIONS: A high CAR level was associated with a high risk of long-term adverse prognosis in patients with ICH, and the risk of ICH poor outcome increased steadily with CAR rising in a certain range, and maintained in a high level thereafter.

Identification of key genes in spontaneous cerebral hemorrhage and prevention of disease damage: LASSO and SVM regression.

Prevention is more important than treatment, and the incidence of intracerebral hemorrhage can be effectively reduced by intervening on the risk factors of intracerebral hemorrhage. By studying the risk factors of spontaneous intracerebral hemorrhage, we can identify the risk factors to achieve the target of treatment and prevention. Through the use of the Least Absolute Shrinkage and Selection Operator (LASSO) and the Support Vector Machine (SVM), the two essential SICH-related genes, NUAK1 and ERO1L, were eliminated from consideration. A Venn analysis was performed, and based on the two important modules, it found that SICH was related with four critical genes: VCM1, CRNDE, COL6A2, and HSPB6. One gene (NUAK1) was dramatically downregulated in the illness group compared to the control group, whereas three essential genes (ERO1L, VCAM1, and COL6A2) were significantly upregulated in the disease group. In the end, the genes ERO1L, VCAM1, COL6A2, and NUAK1 were shown to be the most important ones for SICH. It is anticipated that these genes will become novel biomarkers as well as targets for the development of new pharmacotherapies for SICH.

Prediction of poor outcome in stroke patients using radiomics analysis of intraparenchymal and intraventricular hemorrhage and clinical factors.

PURPOSE: To build three prognostic models using radiomics analysis of the hemorrhagic lesions, clinical variables, and their combination, to predict the outcome of stroke patients with spontaneous intracerebral hemorrhage (sICH). MATERIALS AND METHODS: Eighty-three sICH patients were included. Among them, 40 patients (48.2%) had poor prognosis with modified Rankin scale (mRS) of 5 and 6 at discharge, and the prognostic model was built to differentiate mRS ≤ 4 vs. 5 + 6. The region of interest (ROI) of intraparenchymal hemorrhage (IPH) and intraventricular hemorrhage (IVH) were separately segmented. Features were extracted using PyRadiomics, and the support vector machine was applied to select features and build radiomics models based on IPH and IPH + IVH. The clinical models were built using multivariate logistic regression, and then the radiomics scores were combined with clinical variables to build the combined model. RESULTS: When using IPH, the AUC for radiomics, clinical, and combined model was 0.78, 0.82, and 0.87, respectively. When using IPH + IVH, the AUC was increased to 0.80, 0.84, and 0.90, respectively. The combined model had a significantly improved AUC compared to the radiomics by DeLong test. A clinical prognostic model based on the ICH score of 0-1 only achieved AUC of 0.71. CONCLUSIONS: The combined model using the radiomics score derived from IPH + IVH and the clinical factors could achieve a high accuracy in prediction of sICH patients with poor outcome, which may be used to assist in making the decision about the optimal care.

Systemic inflammation and immune index predicting outcomes in patients with intracerebral hemorrhage.

OBJECT: Recent evidence has suggested that systemic inflammatory and immune index (SIRI) and systematic inflammation index (SII) could predict prognosis in stroke patients. This study aimed to determine the effects of SIRI and SII on predicting in-hospital infections and unfavorable outcomes in patients with acute intracerebral hemorrhage (ICH). METHODS: We used the data from a prospective and registry-based study recruiting ICH patients between January 2014 and September 2016 in a single comprehensive stroke center. All patients were stratified by quartiles of SIRI or SII. Logistic regression analysis was used to estimate the associations with follow-up prognosis. The receiver operating characteristics (ROC) curves were performed to examine the predictive utility of these indexes for infections and prognosis. RESULTS: Six hundred and forty spontaneous ICH patients were enrolled in this study. Compared with the lowest quartile (Q1), SIRI or SII values both showed positive correlations with increased risks for poor 1-month outcomes (adjusted ORs in Q4 was 2.162 [95% CI: 1.240-3.772] for SIRI, 1.797 [95% CI: 1.052-3.070] for SII). Additionally, a higher level of SIRI, but not SII, was independently associated with a higher risk of infections and an unfavorable 3-month prognosis. The C-statistic for the combined SIRI and ICH score was higher than SIRI or ICH score alone for predicting in-hospital infections and poor outcomes. CONCLUSION: Elevated SIRI values were associated with in-hospital infections and poor functional outcomes. It may provide a new biomarker for ICH prognosis prediction, especially in the acute stage.