Initial Hematoma Volume Research Articles

Prognostic Factors Associated with Post-Stroke Dysphagia in Intracerebral Hemorrhage Patients.

Spontaneous intracerebral hemorrhage (ICH) constitutes a significant portion of acute stroke incidents worldwide, often leading to post-stroke dysphagia (PSD), affecting 50-77% of survivors and worsening patient morbidity. This study aimed to identify predictive variables for PSD among patients with spontaneous ICH. A retrospective cohort study was conducted on adult patients with acute spontaneous ICH, confirmed by brain computed tomography, from June 2019 to June 2023. We analyzed demographic, neuroimaging, and stroke-specific characteristics and rehabilitation indicators. PSD was evaluated using nasogastric (NG) tube retention and the Functional Oral Intake Scale (FOIS) levels at 4 and 12 weeks post-ICH. Statistical analyses involved univariate and multivariate logistic regression to identify PSD predictors. A total of 310 ICH patients were included in the study. At 4 weeks, significant predictors for NG tube retention included 24-hour National Institute of Health Stroke Scale (NIHSS) scores, estimated glomerular filtration rate and sitting balance. At 12 weeks, hospital stay duration and ICH score were significant predictors for NG tube retention. Regarding the FOIS, significant predictors at 4 weeks included higher 24-hour NIHSS scores, compromised sitting balance, immobility-related complications, initial hematoma volume and intraventricular hemorrhages. At 12 weeks, older age and higher 24-hour NIHSS scores significantly predicted lower FOIS levels. Our findings demonstrate that PSD in ICH patients is influenced by a complex interplay of factors, including stroke severity, renal function, and physical impairment. The study highlights the importance of early neurological assessment, physical function, and comprehensive management in improving swallowing outcomes, emphasizing a multifaceted approach to enhancing outcomes for ICH survivors.

The National Institutes of Health Stroke Scale is comparable to the ICH score in predicting outcomes in spontaneous acute intracerebral hemorrhage.

Validating the National Institutes of Health NIH Stroke Scale (NIHSS) as a tool to assess deficit severity and prognosis in patients with acute intracerebral hemorrhage would harmonize the assessment of intracerebral hemorrhage (ICH) and acute ischemic stroke (AIS) patients, enable clinical use of a readily implementable and non-imaging dependent prognostic tool, and improve monitoring of ICH care quality in administrative datasets. Among randomized trial ICH patients, the relation between NIHSS scores early after Emergency Department arrival and 3-month outcomes of dependency or death (modified Rankin Scale, mRS 3-6) and case fatality was examined. NIHSS predictive performance was compared to a current standard prognostic scale, the intracerebral hemorrhage score (ICH score). Among the 384 patients, the mean age was 65 (±13), with 66% being male. The median NIHSS score was 16 (interquartile range (IQR) 9-25), the mean initial hematoma volume was 29 mL (±38), and the ICH score median was 1 (IQR 0-2). At 3 months, the mRS had a median of 4 (IQR 2-6), with dependency or death occurring in 70% and case fatality in 26%. The NIHSS and ICH scores were strongly correlated (r = 0.73), and each was strongly correlated with the 90-day mRS (NIHSS, r = 0.61; ICH score, r = 0.62). The NIHSS performed comparably to the ICH score in predicting both dependency or death (c = 0.80 vs. 0.80, p = 0.83) and case fatality (c = 0.78 vs. 0.80, p = 0.29). At threshold values, the NIHSS predicted dependency or death with 74.1% accuracy (NIHSS 17.5) and case fatality with 75.0% accuracy (NIHSS 18.5). The NIHSS forecasts 3-month functional and case fatality outcomes with accuracy comparable to the ICH Score. Widely documented in routine clinical care and administrative data, the NIHSS can serve as a valuable measure for clinical prognostication, therapy development, and case-mix risk adjustment in ICH patients.Clinical trial registrationClinicaltrials.gov, NCT00059332.

Predicting hematoma expansion using machine learning: An exploratory analysis of the ATACH 2 trial

IntroductionHematoma expansion (HE) in patients with intracerebral hemorrhage (ICH) is a key predictor of poor prognosis and potentially amenable to treatment. This study aimed to build a classification model to predict HE in patients with ICH using deep learning algorithms without using advanced radiological features. MethodsData from the ATACH-2 trial (Antihypertensive Treatment of Acute Cerebral Hemorrhage) was utilized. Variables included in the models were chosen as per literature consensus on salient variables associated with HE. HE was defined as increase in either >33% or 6 mL in hematoma volume in the first 24 h. Multiple machine learning algorithms were employed using iterative feature selection and outcome balancing methods. 70% of patients were used for training and 30% for internal validation. We compared the ML models to a logistic regression model and calculated AUC, accuracy, sensitivity and specificity for the internal validation models respective models. ResultsAmong 1000 patients included in the ATACH-2 trial, 924 had the complete parameters which were included in the analytical cohort. The median [interquartile range (IQR)] initial hematoma volume was 9.93.mm3 [5.03–18.17] and 25.2% had HE. The best performing model across all feature selection groups and sampling cohorts was using an artificial neural network (ANN) for HE in the testing cohort with AUC 0.702 [95% CI, 0.631–0.774] with 8 hidden layer nodes The traditional logistic regression yielded AUC 0.658 [95% CI, 0.641–0.675]. All other models performed with less accuracy and lower AUC. Initial hematoma volume, time to initial CT head, and initial SBP emerged as most relevant variables across all best performing models. ConclusionWe developed multiple ML algorithms to predict HE with the ANN classifying the best without advanced radiographic features, although the AUC was only modestly better than other models. A larger, more heterogenous dataset is needed to further build and better generalize the models.

Predicting Progression of Intracranial Hemorrhage in the Prehospital TXA for TBI Trial.

Progression of intracranial hemorrhage is a common, potentially devastating complication after moderate/severe traumatic brain injury (TBI). Clinicians have few tools to predict which patients with traumatic intracranial hemorrhage on their initial head computed tomography (hCT) scan will progress. The objective of this investigation was to identify clinical, imaging, and/or protein biomarkers associated with progression of intracranial hemorrhage (PICH) after moderate/severe TBI and to create an accurate predictive model of PICH based on clinical features available at presentation. We analyzed a subset of subjects from the phase II double-blind, multi-center, randomized "Prehospital Tranexamic Acid Use for TBI" trial. This subset was limited to the placebo arm of the parent trial with evidence of hemorrhage on the initial hCT and a follow-up hCT 6 h after. PICH was defined as an increase in hemorrhage size by 30% or more, or the development of new hemorrhage in the intra- and extra-axial intracranial vault between the initial and the follow-up hCT. Two independent radiologists evaluated each hCT, and conflicts were adjudicated by a third. Clinical and radiographic characteristics were collected, along with plasma protein biomarkers at admission. Principal component analysis (PCA) was performed, and each principal component (PC) was interrogated for its association with PICH. Finally, expert opinion and recursive feature extraction (RFE) were used to select input features for the construction of several supervised classification models. Their ability to predict PICH was quantified and compared. In this subset of subjects (n = 104), 46% (n = 48) demonstrated PICH. Univariate analyses showed no association between PICH and age, sex, admission Glasgow Coma Scale (GCS), GCS motor subscore, presence of midline shift, admission platelet count or admission INR. Radiographic severity scores (Marshall score [p = 0.007], Rotterdam score [p = 0.004]), and initial hematoma volume [p = 0.005] were associated with PICH. Higher levels of admission glial fibrillary acidic protein (p < 0.001) and MAP (p = 0.011) were also associated with PICH. Of the PCs, PC1 was significantly associated with PICH (p = 0.0125). Using multimodal data input, machine learning classifiers successfully discriminated patients with or without PICH. Models composed of machine-selected features performed better than models composed of expert-selected variables (reaching an average of 77% accuracy, AUC = 0.78 versus AUC = 0.68 for the expert-selected variables). Predictive models utilizing variables measured at admission can accurately predict PICH, confirmed by the 6-hour follow-up hCT. Our best-performing models must now be externally validated in a separate cohort of TBI patients with low GCS and initial hCT positive for hemorrhage.

Venous thromboembolism in patients with isolated moderate to severe traumatic brain injury

Background. Traumatic brain injury (TBI) remains a big problem of modern neurosurgery, accompanied by high rates of disability and lethality. Venous thromboembolism (VTE) including venous thrombosis and pulmonary embolism (PE) plays a significant role in the structure of mortality in this pathology. Regimens and schemes of pharmacological prevention of VTE in TBI as well as corresponding preventative measures are not yet determined completely.Aim. To identify the frequency of VTE in patients with isolated moderate and severe TBI, and to evaluate the results of prevention and treatment of these complications in patients of this category.Materials and methods. Over a 3‑year period (from 2020 to 2023) 73 patients with isolated moderate and severe TBI (51 men and 22 women, mean age 61.0 ± 13.0 years) were treated in the V. M. Buyanov City Clinical Hospital. Of these, 31 patients received only conservative therapy, and 42 patients underwent surgery (craniotomy with hematoma removal, closed external hematoma drainage, and installation of intracranial pressure sensor). Ultrasound examination of the lower limb veins was performed at patient admission, then every 7 days until discharge from the hospital. Pharmacological prevention of VTE using low molecular weight heparin in non‑surgical patients was started after 1–2 days if computed tomography of the brain 24 h after admission showed no negative hematoma dynamics. Surgical patients were prescribed preventive medications 24 h after surgery if computed tomography confirmed intracranial hemostasis.Results. Venous thrombosis was detected in 22 (30.1 %) of 73 patients. PE complicated the underlying disease in 1 (1.4 %) case and was non‑fatal. There was no fatal PE in the study group. An increase of the initial intracranial hematoma volume occurred in 3 (4.1 %) patients, in 2 (2.8 %) patients the recurrence of hemorrhage occurred before the beginning of heparin administration, and in 1 (1.4 %) case against the background of therapeutic doses of anticoagulants prescribed for venous thrombosis. In the majority of cases (82.0 %; 18 of 22 patients) thromboses were localized in deep veins of the lower leg and were asymptomatic. Intrahospital mortality was 23.3 % (17 patients), all lethal outcomes were due to the course of traumatic brain disease.Conclusion. VTE is a frequent complication of TBI with intracranial hemorrhage. Regular ultrasound diagnostics makes it possible to diagnose asymptomatic distal venous thrombosis in a timely manner and to prescribe therapeutic doses of low molecular weight heparin in time which in turn allows to avoid fatal PE. Currently, there are no clear domestic recommendations for the prevention and, most importantly, for the treatment of these complications in patients with isolated moderate and severe TBI, which requires further active study of this problem.

Abstract TMP74: Association Between Hematoma Volume After Risk of Subsequent Ischemic Stroke: A MISTIE III and ATACH-2 Analysis

Background: Non-traumatic intracerebral hemorrhage (ICH) is independently associated with long-term increased risk of major arterial ischemic events. Whether hematoma volume influences this risk is poorly understood. Methods: We pooled individual patient data from the MISTIE III (Minimally Invasive Surgery Plus Alteplase for Intracerebral Hemorrhage Evacuation phase 3) and the ATACH-2 (Antihypertensive Treatment of Acute Cerebral Hemorrhage) trials. The exposure was hematoma volume. In the primary analysis, hematoma volume was treated as a continuous measure after natural logarithmic transformation to approximate linearity, and in the secondary analysis, it was dichotomized by the median. The outcome was an ischemic stroke, adjudicated centrally within each trial. We evaluated the association between hematoma volume and the risk of an ischemic stroke using Cox regression analyses after adjustment for demographics, vascular comorbidities, and ICH characteristics. Results: Of 1,499 ICH patients, the mean age was 61.7 (SD, 12.8) years and 574 (38.3%) were female. The median hematoma volume was 17.3 mL (IQR, 7.2-35.7). During a median follow up of 107 days (IQR, 91-140), 30 ischemic strokes occurred of which 22 were in patients with median ICH volume &gt; 17.3 mL with a cumulative incidence of 4.6% (95% CI, 3.1-7.1). Among patients with median ICH volume &lt; 17.3 mL, there were 8 ischemic strokes with a cumulative incidence of 3.1% (95% CI, 1.7-6.0). Using adjusted Cox regression models, log-transformed ICH volume (continuous measure) was associated with an increased risk of ischemic stroke (HR, 1.5 per log-unit increase; 95% CI, 1.1-2.8). Similarly, ICH volume &gt; 17.3 mL was associated with an increased risk of ischemic stroke (HR, 2.5; 95% CI, 1.1-7.2), compared to those with an ICH volume &lt; 17.3 mL. Conclusions: In a heterogeneous cohort of ICH patients, initial hematoma volume was associated with a heightened risk of subsequent ischemic stroke.

Abstract WP209: Functional Outcomes After Craniotomy or Endoscopic Procedure for Hematoma Evacuation in Patients of Intracerebral Hemorrhage Associated With Oral Anticoagulants

Background and Purpose: The role of surgical evacuation using craniotomy or endoscopic procedure in patients with intracerebral hemorrhage (ICH) associated with oral anticoagulants is not well described. We investigated the 6-month functional outcomes of patients with ICH associated with oral anticoagulants after hematoma evacuation using either craniotomy or endoscopic procedures. Methods: We analyzed data of consecutive ICH patients who underwent hematoma evacuation using either craniotomy or endoscopic procedures. We compared the outcomes between patients with ICH associated with oral anticoagulants to those with spontaneous ICH. We also compared the results between patients treated with craniotomy and those treated with endoscopic procedures. We performed multivariate analyses to assess the effect of ICH associated with oral anticoagulants on modified Rankin Scale (mRS) at 6 months, which was analyzed both as dichotomous and ordinal endpoints after adjusting for age, gender, initial GCS score, initial hematoma volume, and presence or absence of intraventricular hemorrhage. Results: Of the 148 ICH patients undergoing hematoma evacuation, 25 (17%) had ICH associated with oral anticoagulants. There were no statistically significant differences between the two groups in terms of age, gender, admission Glasgow Coma scale (GCS) score, admission National Institutes of Health Stroke Scale (NIHSS) score, peri and post-operative hematoma volume, presence of cardiovascular disease, hypertension, or dyslipidemia. There was no difference in the proportion of patients with mRS 0-2 at 6 months among patients with and without ICH related to oral anticoagulants (4/25 (16%) versus 27/123 (22%), p-value = 0.5). In the ordinal analysis, there was no significant association between ICH associated with oral anticoagulants and mRS grades (OR 1.62 (0.25, 9.65), p-value 0.598. Conclusion: Prior anticoagulation use is not associated with poor functional outcome (mRS 3-6) in patients with intracerebral hemorrhage, procedure use for hematoma evacuation (craniotomy or endoscopic) does not predict good functional outcome at 6 months.

Clinical potential of automated convolutional neural network-based hematoma volumetry after aneurysmal subarachnoid hemorrhage

ObjectivesCerebrospinal fluid hemoglobin has been positioned as a potential biomarker and drug target for aneurysmal subarachnoid hemorrhage-related secondary brain injury (SAH-SBI). The maximum amount of hemoglobin, which may be released into the cerebrospinal fluid, is defined by the initial subarachnoid hematoma volume (ISHV). In patients without external ventricular or lumbar drain, there remains an unmet clinical need to predict the risk for SAH-SBI. The aim of this study was to explore automated segmentation of ISHV as a potential surrogate for cerebrospinal fluid hemoglobin to predict SAH-SBI. MethodsThis study is based on a retrospective analysis of imaging and clinical data from 220 consecutive patients with aneurysmal subarachnoid hemorrhage collected over a five-year period. 127 annotated initial non-contrast CT scans were used to train and test a convolutional neural network to automatically segment the ISHV in the remaining cohort. Performance was reported in terms of Dice score and intraclass correlation. We characterized the associations between ISHV and baseline cohort characteristics, SAH-SBI, ventriculoperitoneal shunt dependence, functional outcome, and survival. Established clinical (World Federation of Neurosurgical Societies, Hunt & Hess) and radiological (modified Fisher, Barrow Neurological Institute) scores served as references. ResultsA strong volume agreement (0.73 Dice, range 0.43 - 0.93) and intraclass correlation (0.89, 95% CI, 0.81-0.94) were shown. While ISHV was not associated with the use of antithrombotics or cardiovascular risk factors, there was strong evidence for an association with a lower Glasgow Coma Scale at hospital admission. Aneurysm size and location were not associated with ISHV, but the presence of intracerebral or intraventricular hemorrhage were independently associated with higher ISHV. Despite strong evidence for a positive association between ISHV and SAH-SBI, the discriminatory ability of ISHV for SAH-SBI was insufficient. The discriminatory ability of ISHV was, however, higher regarding ventriculoperitoneal shunt dependence and functional outcome at three-months follow-up. Multivariate survival analysis provided strong evidence for an independent negative association between survival probability and both ISHV and intraventricular hemorrhage. ConclusionsThe proposed algorithm demonstrates strong performance in volumetric segmentation of the ISHV on the admission CT. While the discriminatory ability of ISHV for SAH-SBI was similar to established clinical and radiological scores, it showed a high discriminatory ability for ventriculoperitoneal shunt dependence and functional outcome at three-months follow-up.

The “SALPARE study” of spontaneous intracerebral hemorrhage: part 1

BackgroundSpontaneous intracerebral hemorrhage (ICH) is a devastating type of stroke with a huge impact on patients and families. Expanded use of oral anticoagulants and ageing population might contribute to an epidemiological change. In view of these trends, we planned a study to obtain a contemporary picture and identify early prognostic factors to improve secondary prevention.MethodsThis multicenter prospective cohort study included consecutive adult patients with non-traumatic ICH admitted to three academic Italian hospitals (Salerno, Padova, Reggio Emilia) over a 2-year period. Demographic characteristics, vascular risk profile, clinical data and main radiological characteristics were correlated to 90-day clinical outcome.ResultsOut of 682 patients [mean age: 73 ± 14 years; 316 (46.3%) females] enrolled in this study, 40% died [86/180 (47.8%) in Salerno, 120/320 (37.5%) in Padova, 67/182 (36.8%) in Reggio Emilia; p < 0.05)] and 36% were severely disabled at 90 days. Several factors were associated with a higher risk of poor functional outcome such as antithrombotic drug use, hyperglycemia, previous cerebrovascular accident, low platelet count, and pontine/massive/intraventricular hemorrhage. However, at multivariate analysis only pre-ICH mRS score (OR 30.84), GCS score at presentation (OR 11.88), initial hematoma volume (OR 29.71), and NIHSS score at presentation (OR 25.89) were independent predictors of death and poor functional outcome.ConclusionDespite the heterogeneity among centers, this study on ICH has identified four simple prognostic factors that can independently predict patients outcome, stratify their risk, and guide their management.

Abstract TP127: Application Of Machine Learning Algorithms For Prediction Of Hematoma Expansion In Spontaneous Intracerebral Hemorrhage

Introduction: Hematoma expansion (HE) is a known prognostic indicator of spontaneous intracerebral hemorrhage (sICH). Although several scores exist for prediction of HE, universal adoption has been limited due to their lack of sensitivity and specificity. As machine learning (ML) algorithms have shown promise in the stroke field, here we examine the predictive accuracy of several ML algorithms for HE in sICH patients. Methods: We retrospectively analyzed demographic, clinical data, and radiographic signs of patients with sICH in our 2-hospital database. A total of 61 clinical, imaging, and treatment variables were included in the study. Nine ML models were applied: Adaptive Boost (AdaBoost), Bernoulli Naïve Bayes (BNB), Decision Tree (DT), Gaussian Naïve Bayes (GNB), Logistic Regression (LR), Multi-Layer Perceptron (MLP), Multinomial Naïve Bayes models (MNB), Random Forest (RF), and Extreme Gradient Boosting (XGBoost). All models were trained to predict HE. Model accuracy was assessed using the area under characteristic curve (AUC). Results: Of the 301 patients with sICH, 63 developed HE (21.93%). Of the 9 models studied, MLP had the highest AUC score (0.93±0.042), followed by XGBoost (0.80±0.06). All models demonstrated moderate to high predictive accuracy (AUC 0.64-0.93) for HE. The top predictors in MLP were Baseline NIHSS score, HDL, aPPT, time from last known well to ER, initial hematoma volume, and island sign. MLP had moderate sensitivity of 0.46±0.17 and high specificity of 0.99±0.02. GNB, however, showed the highest sensitivity at 0.86±0.06 and a moderate specificity of 0.65±0.07. Five of the 9 models ranked time last known well to ER presentation as a predictor of HE. Conclusion: In our study, we found all ML models applied had moderate to high predictive accuracy for prediction of HE in sICH, with MLP having the highest accuracy of all models. Future studies examining the use of these algorithms are warranted.

The “SALPARE study” of spontaneous intracerebral haemorrhage—part 2-early CT predictors of outcome in ICH: keeping it simple

BackgroundThe aim of this study was to investigate the prognostic role of hematoma characteristics and hematoma expansion (HE) in patients with spontaneous intracerebral hemorrhage (ICH).MethodsThis multicenter prospective cohort study enrolled consecutive adult patients with non-traumatic ICH admitted to three Italian academic hospitals (Salerno, Padova, Reggio Emilia) over a 2-year period. Early noncontrast CT (NCCT) features of the hematoma, including markers of HE, and 3-month outcome were recorded. Multivariable logistic regression analysis was performed to identify predictors of poor outcome.ResultsA total of 682 patients were included in the study [mean age: 73 ± 14 years; 316 (46.3%) females]. Pontine and massive hemorrhage, intraventricular bleeding, baseline hematoma volume > 15 mL, blend sign, swirl sign, margin irregularity ≥ 4, density heterogeneity ≥ 3, hypodensity ≥ 1, island sign, satellite sign, and black hole sign were associated with a higher risk of mortality and disability. However, at multivariate analysis only initial hematoma volume (OR 29.71) proved to be an independent predictor of poor functional outcome at 3 months.ConclusionSimple hematoma volume measured on baseline CT best identifies patients with a worse outcome, while early NCCT markers of HE do not seem to add any clinically significant information.

553: COMPARISON OF INTRACRANIAL HEMATOMA EXPANSION IN PATIENTS ON WARFARIN VS. DIRECT ORAL ANTICOAGULANTS

Introduction: Anticoagulation associated intracranial hemorrhage has been associated with larger initial hematoma volumes and a greater frequency of hematoma expansion. Preventing hematoma expansion is a promising treatment strategy as expansion is a predictor of poor outcomes. Limited studies have been conducted that directly compare hematoma expansion in patients taking warfarin versus direct oral anticoagulants (DOACs). Due to increased prescribing of DOACs, this study aimed to assess intracranial hematoma expansion in patients taking warfarin compared to DOACs. Methods: This was a retrospective, observational study conducted at an academic, adult level one trauma, and comprehensive stroke center between October 1, 2016 and November 30, 2021. Adult patients were included if they were diagnosed with a primary intracranial hemorrhage, prescribed warfarin or DOACs prior to admission, admitted to an intensive care unit (ICU), and had an initial and follow-up computed tomography (CT) brain within 24 hours. The primary outcome was incidence of hematoma expansion upon repeat CT brain. Secondary outcomes included hospital and ICU length of stay (LOS), incidence and duration of mechanical ventilation, in-hospital mortality, incidence and type of thrombotic complications during hospital stay, and discharge disposition. Results: Of the 56 patients included, 29 were on warfarin and 27 were on a DOAC. Hematoma expansion occurred in 8 (27.6%) warfarin and 9 (33.3%) DOAC patients (P=0.640). Patients in the DOAC group had a significantly shorter ICU LOS (2.7 ± 2.3 vs 4.7 ± 4.1 days; P=0.033) and hospital LOS (6.0 ± 4.9 vs 9.4 ± 6.1; P=0.028) compared to the warfarin group. Additionally, 7 (24.1%) warfarin patients were discharged to hospice compared to 0 (0.0%) in the DOAC group (P=0.011). No other significant differences were observed. Conclusions: There was no statistically significant difference in the incidence of hematoma expansion between groups. However, a shorter ICU and hospital LOS was demonstrated in the DOAC group.

The clinical value of neutrophil-to-lymphocyte ratio, platelet-to-lymphocyte ratio, and D-dimer-to-fibrinogen ratio for predicting pneumonia and poor outcomes in patients with acute intracerebral hemorrhage.

BackgroundThis study aimed to investigate the neutrophil-to-lymphocyte ratio (NLR), platelet-to-lymphocyte ratio (PLR), and D-dimer-to-fibrinogen ratio (DFR) as predictors of pneumonia and poor outcomes in patients with acute intracerebral hemorrhage (ICH).MethodsWe retrospectively examined patients with acute ICH treated in our institution from May 2018 to July 2020. Patient characteristics, laboratory testing data, radiologic imaging data, and 90-day outcomes were recorded and analyzed.ResultsAmong the 329 patients included for analysis, 183 (55.6%) developed pneumonia. Systolic blood pressure, initial hematoma volume, D-dimer concentration, NLR, PLR, DFR, and white blood cell, platelet, neutrophil, and lymphocyte counts at admission were significantly higher in patients who developed pneumonia than in those who did not; however, the Glasgow coma scale (GCS) score at admission was significantly lower in pneumonia patients compared with non-pneumonia patients (all P <0.05). Multivariate logistic regression showed that the NLR and PLR were independent predictors of pneumonia, and the NLR and DFR were independent predictors of poor 90-day outcomes (modified Rankin scale score 4–6).ConclusionThe NLR and PLR were independent predictors of pneumonia and the NLR and DFR were independent predictors of poor 90-day outcomes. The NLR, PLR, and DFR can provide prognostic information about acute ICH patients.

Intracerebral hemorrhage markers on non-contrast computed tomography as predictors of the dynamic spot sign on CT perfusion and associations with hematoma expansion and outcome.

To assess the association between non-contrast computed tomography (NCCT) hematoma markers and the dynamic spot sign on computed tomography perfusion (CTP), and their associations with hematoma expansion, clinical outcome, and in-hospital mortality. Patients who presented with intracerebral hemorrhage (ICH) to a stroke center over an 18-month period and underwent baseline NCCT and CTP, and a follow-up NCCT within 24h after the baseline scan were included. The initial and follow-up hematoma volumes were calculated. Two raters independently assessed the baseline NCCT for hematoma markers and concurrently assessed the CTP for the dynamic spot sign. Univariate and multivariate logistic regression analyses were performed to assess the association between the hematoma markers and the dynamic spot sign, adjusting for known ICH expansion predictors. Eighty-five patients were included in our study and 55 patients were suitable for expansion analysis. Heterogeneous density was the only NCCT hematoma marker to be associated with the dynamic spot sign after multivariate analysis (odds ratio, 58.61; 95% confidence interval, 9.13-376.05; P < 0.001). The dynamic spot sign was present in 22 patients (26%) and significantly predicted hematoma expansion (odds ratio, 36.6; 95% confidence interval, 2.51-534.2; P = 0.008). All patients with a spot sign had a swirl sign. A co-located hypodensity and spot sign was significantly associated with in-hospital mortality (odds ratio, 6.17; 95% confidence interval, 1.09-34.78; P = 0.039). Heterogeneous density and swirl sign are associated with the dynamic spot sign. The dynamic spot sign is a stronger predictor than NCCT hematoma markers of significant hematoma expansion. A co-located spot sign and hypodensity predicts in-hospital mortality.

P.169 Tissue plasminogen activator in addition to twist drill drainage as a treatment for chronic subdural hematomas – a descriptive analysis

Background: Current literature provides little consensus on universal guidelines for first-line treatment of chronic subdural hematomas (cSDH). However, administration of local tissue plasminogen activator (tPA) may enhance the traditional method of twist drill drainage (TDD). The study aims to explore the efficacy of TDD with and without tPA, at achieving clinically relevant drainage (200mL) and reducing recurrence of cSDH. Methods: A retrospective review of patients (N=34) with cSDH is presented. Patients who received TDD with tPA (n=17) were identified and matched, based primarily on age and hematoma volume, to a control group (n=17), TDD without tPA. Variables of interest include initial hematoma volume, volume drained, length of stay, and recurrence rates. Descriptive analysis was run. Results: Average age for patients was 74.6 with 76% male. Mean drainage volumes for the tPA cohort was 381.6mL and TDD without tPA cohort was 151.3mL. The addition of tPA resulted in drainage volumes nearly double (1.9x) the clinically relevant amount and had low recurrence rates (12.5%). TDD without tPA failed to result in clinically relevant drainage and had a recurrence rate of 52.9%. Average length of stay differed by two days (9.71 tPA; 7.71 control). Conclusions: TDD with tPA was effective at treating cSDH in our population.

Defining Delayed Perihematomal Edema Expansion in Intracerebral Hemorrhage: Segmentation, Time Course, Risk Factors and Clinical Outcome.

We attempt to generate a definition of delayed perihematomal edema expansion (DPE) and analyze its time course, risk factors, and clinical outcomes. A multi-cohort data was derived from the Chinese Intracranial Hemorrhage Image Database (CICHID). A non-contrast computed tomography (NCCT) -based deep learning model was constructed for fully automated segmentation hematoma and perihematomal edema (PHE). Time course of hematoma and PHE evolution correlated to initial hematoma volume was volumetrically assessed. Predictive values for DPE were calculated through receiver operating characteristic curve analysis and were tested in an independent cohort. Logistic regression analysis was utilized to identify risk factors for DPE formation and poor outcomes. The test cohort’s Dice scores of lesion segmentation were 0.877 and 0.642 for hematoma and PHE, respectively. Overall, 1201 patients were enrolled for time-course analysis of ICH evolution. A total of 312 patients were further selected for DPE analysis. Time course analysis showed the growth peak of PHE approximately concentrates in 14 days after onset. The best cutoff for DPE to predict poor outcome was 3.34 mL of absolute PHE expansion from 4-7 days to 8-14 days (AUC=0.784, sensitivity=72.2%, specificity=81.2%), and 3.78 mL of absolute PHE expansion from 8-14 days to 15-21 days (AUC=0.682, sensitivity=59.3%, specificity=92.1%) in the derivation sample. Patients with DPE was associated with worse outcome (OR: 12.340, 95%CI: 6.378-23.873, P<0.01), and the larger initial hematoma volume (OR: 1.021, 95%CI: 1.000-1.043, P=0.049) was the significant risk factor for DPE formation. This study constructed a well-performance deep learning model for automatic segmentations of hematoma and PHE. A new definition of DPE was generated and is confirmed to be related to poor outcomes in ICH. Patients with larger initial hematoma volume have a higher risk of developing DPE formation.

National Institutes of Health Stroke Scale Correlates Well with Initial Intracerebral Hemorrhage Volume

The US Centers for Medicare and Medicaid Services (CMS) currently publicly reports hospital-quality, risk-adjusted mortality measure for ischemic stroke but not intracerebral hemorrhage (ICH). The NIHSS, which is captured in CMS administrative claims data, is a candidate metric for use in ICH risk adjustment and has been shown to predict clinical outcome with accuracy similar to the ICH Score. Correlation between early NIHSS and initial ICH volume would further support use of the NIHSS for ICH risk adjustment. Among 372 ICH patients enrolled in a large multicenter trial (FAST-MAG), the relation between early NIHSS and early ICH volume was assessed with correlation and linear trend analysis. Overall, there was strong correlation between NIHSS and ICH volume, r=0.77 (p<0.001), and for every 10cc increase in ICH the NIHSS increased by 4.5 points. Correlation coefficients were comparable in all subgroups, but magnitude of NIHSS increase with ICH unit volume increase was greater with left than right hemispheric ICH, with presence rather than absence of IVH, with imaging done within the first hour than second hour after last known well, with men than women, and with younger than older patients. Early NIHSS neurologic deficit severity values correlate strongly with initial ICH hematoma volume. As with ischemic stroke, lesion volume increases produce greater NIHSS change in the left than right hemisphere, reflecting greater NIHSS sensitivity to left hemisphere function. These findings provide further support for the use of NIHSS in risk-adjusted mortality measures for intracerebral hemorrhage.

Abstract 101: Predicting Hematoma Expansion Using An Artificial Neural Network: An Exploratory Analysis Of The Atach 2 Trial

Introduction: Hematoma expansion (HE) in patients with intracerebral hemorrhage (ICH) is a key predictor of poor prognosis and potentially amenable to treatment. Current clinical scoring models, radiological markers, and labs have limited ability to predict HE. This study aimed to create a more robust classification model to predict HE in patients with ICH using a deep learning algorithm, an artificial neural network (ANN). Methods: Data from the ATACH 2 trial (Antihypertensive Treatment of Acute Cerebral Hemorrhage) was utilized. Variables included in the models were chosen as per literature consensus on salient factors associated with HE and clinical expertise. HE was defined as increase in either &gt;33% or 6mL in hematoma volume in the first 24 hours. A multi-layer feedforward ANN was trained using the back-propagation method to minimize the loss function with 5-fold cross validation. 80% of patients were used for training and 20% for testing. The ANN was compared to a logistic regression model (GLM). Given the imbalance in patients with HE, AUPRC (area under the precision-recall curve), recall and precision were calculated for the respective models. Results: Of the 963 patients in the study (mean age 62±13.0, 38.5% female), 31% had hematoma expansion. The median [interquartile range (IQR)] initial hematoma volume was 10.5mm 3 [5.16 - 20.25], median admission SBP [IQR] was 200 [184-217], median platelet count [IQR] was 213 [178-256], median INR [IQR] was 1.0 [0.9-1.0], and median admission GCS [IQR] was 15 [13-15]. The GLM model had AUPRC of 0.38 with recall of 0.60 and precision of 0.38 in the testing cohort. The ANN training model demonstrated AUPRC of 0.92 with recall of 0.72 with precision of 0.39 during testing. Initial ICH volume, platelets, INR, and GCS had the highest feature importance. Conclusion: We developed an ANN to predict HE in ICH patients performing with improved sensitivity and similar positive predictive value when compared to GLM. We support that ANN can capture complex associations between variables not attainable in classic regression models. This model may help identify patients at risk for HE who warrant careful monitoring and aggressive treatment upfront including those suitable for clinical trials for treatments.

Abstract WP78: National Institutes Of Health Stroke Scale Correlates Well With Initial Intracerebral Hemorrhage Volume

Introduction: The US Centers for Medicare and Medicaid Services (CMS) currently publicly reports hospital-quality, risk-adjusted mortality measure for ischemic stroke but not intracerebral hemorrhage (ICH). The NIHSS, which is captured in CMS administrative claims data, is a candidate metric for use in ICH risk adjustment and has been shown to predict clinical outcome with accuracy similar to the ICH Score. Correlation between early NIHSS and initial ICH volume would further support use of the NIHSS for ICH risk adjustment. Methods: Among consecutive ICH patients enrolled in a large multicenter trial (FAST-MAG), the relation between early NIHSS and early ICH volume was assessed with correlation and linear trend analysis, in all patients and separately in; left vs right; IVH-positive vs IVH-negative, hyperacute (≤60min) vs acute (61-120min) imaging; men vs women; and younger (&lt;65y) vs older (≥65y). Results: Among 372 patients with ICH, age was 65y (SD 13), 67% were men, early NIHSS was 16 (IQR 9-25) and initial ICH volume was 14.9 cc (IQR 6.1-36.4). Overall, there was substantial correlation between NIHSS and ICH volume, r=0.77 (p&lt;0.001), and for every 10cc increase in ICH the NIHSS increased by 4.5 points. Correlations remained substantial and similar in all subgroups (Table), but magnitude of NIHSS change with ICH volume alteration varied, including greater NIHSS change with ICH unit volume increase in left than right hemisphere, absence of IVH, earlier (≤60min) than later presentation (61-120min), men than women, and younger than older patients (Table). Conclusion: Early NIHSS deficit severity values correlate strongly with initial ICH hematoma volume. As with ischemic stroke, lesion volume increases produce greater NIHSS changes in the left than right hemisphere, reflecting greater NIHSS sensitivity to left hemisphere function. These findings provide further support for the use of the NIHSS in risk-adjusted mortality measures for intracerebral hemorrhage.

Total intracranial volume as a covariate for predicting prognosis in patients with primary intracerebral hemorrhage

ObjectivesThe initial hematoma volume is reliable and stable imaging predictor for the outcome of patients with intracerebral hemorrhage, and the total intracranial volume varies between patients. However, the role of total intracranial volume in predicting the prognosis of spontaneous intracerebral hemorrhage has not been previously addressed. Methods782 patients with spontaneous intracerebral hemorrhage were selected in this retrospective cohort at the Neurosurgery Emergency Unit of The First Affiliated Hospital of Harbin Medical University. Due to missing CT images, initial CT exceeding 24 h, traumatic cerebral hemorrhage, and aneurysm, 145 patients were excluded and the remaining 637 patients were included in our analysis. Functional outcome was assessed using the modified Rankin Scale(mRS) and mortality at 3-months after spontaneous intracerebral hemorrhage. CT image datasets were calculated by 3D-Slicer. The initial hematoma volume was normalized to the total intracranial volume to evaluate poor functional outcomes (mRS, 4–6) and mortality. ResultsThe results demonstrated that normalized initial hematoma volume can be used as an indicator of poor functional outcome (mRS, 4–6) (AUCNrIHV=0.753, 95%-CI:0.710–0.795, p < 0.001), mortality (AUCNrIHV=0.808, 95%-CI:0.754–0.862, p < 0.001) and hematoma expansion (AUCNrIHV=0.690, 95%-CI:0.613–0.767, p < 0.001). Meanwhile, the initial hematoma volume in predicting poor functional outcome (AUCIHV=0.749, 95%-CI:0.707–0.792, p < 0.001), mortality (AUCIHV=0.816, 95%-CI: 0.763–0.870, p < 0.001) and hematoma expansion (AUCIHV=0.704, 95%-CI: 0.626–0.782, p < 0.001) was similar to the normalized initial hematoma volume. ConclusionsThe normalized initial hematoma volume has no apparent benefit in predicting the prognosis of patients with cerebral hemorrhage compared with initial hematoma volume.