Hematoma expansion is more frequent in deep than lobar intracerebral hemorrhage

Hybrid clinical-radiomics model based on fully automatic segmentation for predicting the early expansion of spontaneous intracerebral hemorrhage: A multi-center study

BACKGROUND

Early prediction of hematoma expansion (HE) is important for the development of therapeutic strategies for spontaneous intracerebral hemorrhage (sICH). Radiomics can help to predict early hematoma expansion in intracerebral hemorrhage. However, complex image processing procedures, especially hematoma segmentation, are time-consuming and dependent on assessor experience. We provide a fully automated hematoma segmentation method, and construct a hybrid predictive model for risk stratification of hematoma expansion.

PURPOSE

To propose an automatic approach for predicting early hemorrhage expansion after spontaneous intracerebral hemorrhage using deep-learning and radiomics methods.

METHODS

A total of 258 patients with sICH were retrospectively enrolled for model construction and internal validation, while another two cohorts (n=87, 149) were employed for independent validation. For hemorrhage segmentation, an iterative segmentation procedure was performed to delineate the area using an nnU-Net framework. Radiomics models of intra-hemorrhage and multiscale peri-hemorrhage were established and evaluated, and the best discriminative-scale peri-hemorrhage radiomics model was selected for further analysis. Combining clinical factors and intra- and peri-hemorrhage radiomics signatures, a hybrid nomogram was constructed for the early HE prediction using multivariate logistic regression. For model validation, the receiver operating characteristic (ROC) curve analyses and DeLong test were used to evaluate the performances of the constructed models, and the calibration curve and decision curve analysis were performed for clinical application.

RESULTS

Our iterative auto-segmentation model showed satisfactory results for hematoma segmentation in all four cohorts. The Dice similarity coefficient of this hematoma segmentation model reached 0.90, showing an expert-level accuracy in hematoma segmentation. The consumed time of the efficient delineation was significantly decreased, from 18 min to less than 2 min, with the assistance of the auto-segmentation model. The radiomics model of 2-mm peri-hemorrhage had a preferable area under ROC curve (AUC) of 0.840 (95 % confidence interval [CI]: 0.768, 0.912) compared with the original (0-mm dilatation) model with an AUC of 0.796 (95 % CI: 0.717, 0.875). The clinical-radiomics hybrid model showed better performances for HE prediction, with AUC of 0.853, 0.852, 0.772, and 0.818 in the training, internal validation, and independent validation cohorts 1 and 2, respectively.

CONCLUSIONS

The fully automatic clinical-radiomics model based on deep learning and radiomics exhibits a good ability for hematoma segmentation and a favorable performance in stratifying HE risks.

The clinical potential of radiomics to predict hematoma expansion in spontaneous intracerebral hemorrhage: a narrative review

Spontaneous intracerebral hemorrhage (sICH) is associated with significant morbidity and mortality, with subsequent hematoma expansion (HE) linked to worse neurologic outcomes. Accurate, real-time predictions of the risk of HE could enable tailoring management-including blood pressure control or surgery-based on individual patient risk. Although multiple radiographic markers of HE have been proposed based on standard imaging, their clinical utility remains limited by a reliance on subjective interpretation of often ambiguous findings and a poor overall predictive power. Radiomics refers to the quantitative analysis of medical images that can be combined with machine-learning algorithms to identify predictive features for a chosen clinical outcome with a granularity beyond human limitations. Emerging data have supported the potential utility of radiomics in the prediction of HE after sICH. In this review, we discuss the current clinical management of sICH, the impact of HE and standard imaging predictors, and finally, the current data and potential future role of radiomics in HE prediction and management of patients with sICH.

Admission Viscoelastic Hemostatic Assay Parameters Predict Poor Long-Term Intracerebral Hemorrhage Outcomes

BACKGROUND

Viscoelastic hemostatic assays (VHAs) provide more comprehensive assessments of coagulation compared with conventional coagulation assays. Although VHAs have enabled guided hemorrhage control therapies, improving clinical outcomes in life-threatening hemorrhage, the role of VHAs in intracerebral hemorrhage (ICH) is unclear. If VHAs can identify coagulation abnormalities relevant for ICH outcomes, this would support the need to investigate the role of VHAs in ICH treatment paradigms. Thus, we investigated whether VHA assessments of coagulation relate to long-term ICH outcomes.

METHODS

Patients with spontaneous ICH enrolled into a single-center cohort study receiving admission Rotational Thromboelastometry (ROTEM) VHA testing between 2013 and 2020 were assessed. Patients with previous anticoagulant use or coagulopathy on conventional coagulation assays were excluded. Primary ROTEM exposure variables were coagulation kinetics and clot strength assessments. Poor long-term outcome was defined as modified Rankin Scale ≥ 4 at 6 months. Logistic regression analyses assessed associations of ROTEM parameters with clinical outcomes after adjusting for ICH severity and hemoglobin concentration.

RESULTS

Of 44 patients analyzed, the mean age was 64 years, 57% were female, and the median ICH volume was 23 mL. Poor 6-month outcome was seen in 64% of patients. In our multivariable regression models, slower, prolonged coagulation kinetics (adjusted odds ratio for every second increase in clot formation time 1.04, 95% confidence interval 1.00-1.09, p = 0.04) and weaker clot strength (adjusted odds ratio for every millimeter increase of maximum clot firmness 0.84, 95% confidence interval 0.71-0.99, p = 0.03) were separately associated with poor long-term outcomes.

CONCLUSIONS

Slower, prolonged coagulation kinetics and weaker clot strength on admission VHA ROTEM testing, not attributable to anticoagulant use, were associated with poor long-term outcomes after ICH. Further work is needed to clarify the generalizability and the underlying mechanisms of these VHA findings to assess whether VHA-guided treatments should be incorporated into ICH care.

Emergent Management of Intracerebral Hemorrhage

OBJECTIVE

Nontraumatic intracerebral hemorrhage (ICH) is a potentially devastating cerebrovascular disorder. Several randomized trials have assessed interventions to improve ICH outcomes. This article summarizes some of the recent developments in the emergent medical and surgical management of acute ICH.

LATEST DEVELOPMENTS

Recent data have underscored the protracted course of recovery after ICH, particularly in patients with severe disability, cautioning against early nihilism and withholding of life-sustaining treatments. The treatment of ICH has undergone rapid evolution with the implementation of intensive blood pressure control, novel reversal strategies for coagulopathy, innovations in systems of care such as mobile stroke units for hyperacute ICH care, and the emergence of newer minimally invasive surgical approaches such as the endoport and endoscope-assisted evacuation techniques.

ESSENTIAL POINTS

This review discusses the current state of evidence in ICH and its implications for practice, using case illustrations to highlight some of the nuances involved in the management of acute ICH.

Association of non-contrast CT markers with long-term functional outcome in deep intracerebral hemorrhage

Objective

Hematoma expansion (HE) is the most important therapeutic target during acute care of patients with intracerebral hemorrhage (ICH). Imaging biomarkers such as non-contrast CT (NCCT) markers have been associated with increasing risk for HE. The aim of the present study was to evaluate the influence of NCCT markers with functional long-term outcome and with HE in patients with deep (basal ganglia and thalamus) ICH who represent an important subgroup of patients at the highest risk for functional deterioration with HE due to the eloquence of the affected brain region.

Methods

From our prospective institutional database, all patients maximally treated with deep ICH were included and retrospectively analyzed. NCCT markers were recorded at diagnostic imaging, ICH volume characteristics were volumetrically evaluated, and all patients received follow-up imaging within 0-48 h. We explored associations of NCCT makers with unfavorable functional outcome, defined as modified Rankin scale 4-6, after 12 months and with HE. Bias and confounding were addressed by multivariable regression modeling.

Results

In 322 patients with deep ICH, NCCT markers were distributed as follows: irregular shape: 69.6%, heterogenous density: 55.9%, hypodensities: 52.5%, island sign: 19.3%, black hole sign: 11.5%, and blend sign: 4.7%. Upon multivariable regression analyses, independent associations were documented with the functional outcome for irregular shape (aOR: 2.73, 95%CI: 1.42-5.22, p = 0.002), heterogenous density (aOR: 2.62, 95%CI: 1.40-4.90, p = 0.003) and island sign (aOR: 2.54, 95%CI: 1.05-6.14, p = 0.038), and with HE for heterogenous density (aOR: 5.01, 95%CI: 1.93-13.05, p = 0.001) and hypodensities (aOR: 3.75, 95%CI: 1.63-8.62, p = 0.002).

Conclusion

NCCT markers are frequent in deep ICH patients and provide important clinical implications. Specifically, markers defined by diverging intra-hematomal densities provided associations with a 5-times higher risk for HE and a 2.5-times higher likelihood for unfavorable functional long-term outcome. Hence, these markers allow the identification of patients with deep ICH at high risk for clinical deterioration due to HE.

Optimal cut-off values of haematoma volume for predicting haematoma expansion at different intracerebral haemorrhage locations

BACKGROUND

Haematoma expansion (HE) is a frequent manifestation of acute intracerebral haemorrhage (ICH) and is associated with early disease progression and poor functional status. Approximately 30 % of patients with ICH experience substantial HE within the first few hours of onset.

OBJECTIVES

This study aimed to investigate the relationship between HE and initial volume at different locations in patients with ICH.

METHODS

We investigated consecutive patients with ICH admitted to the emergency room at Xiangyang No. 1 People's Hospital between January 2018 and June 2022. Haematoma volume was calculated using a three-dimensional slicer platform. Prediction models were assessed using a logistic regression model. The Youden index was used to assess the haematoma volume cut-off values for predicting HE.

RESULTS

This study included 306 patients: 161 had basal ganglia ICH, 41 lobar ICH, and 104 thalamic ICH. The area under the ROC curve (AUC) for the thalamic ICH score in predicting intraventricular haemorrhage (IVH) expansion ≥ 1 mL or delayed IVH expansion was 0.786, and the best cut-off value was 7.05 mL (specificity, 85.3 %; sensitivity, 62.8 %; and accuracy, 76.0 %). The AUC for the thalamic ICH and lobar ICH scores in predicting haematoma or IVH expansion were 0.756 and 0.653, respectively; the best cut-offs were 7.05 mL for the thalamus (specificity, 84.8 %; sensitivity, 60.0 %; and accuracy, 74.0 %) and 31.89 mL in the lobar area (specificity, 81.8 %; sensitivity, 52.3 %; and accuracy, 68.3 %).

CONCLUSIONS

Initial ICH volume predicted haematoma or IVH expansion at different locations. Moreover, it can assist clinicians in determining whether patients are suitable for future surgical interventions or other procedures.

Blend Sign and Haemorrhage Location and Volume Predict Late Recurrence and Mortality in Intracerebral Haemorrhage Patients

BACKGROUND

Studies on risk factors for primary intracerebral haemorrhage (ICH) focus on short-term predictive values of distinct clinical parameters or computed tomography (CT) markers and disregard the others. We, therefore, studied independent predictive values of demographic, clinical, and CT markers regarding ICH expansion, late ICH recurrence, and late mortality.

METHODS

In a retrospective study of 288 patients with primary ICH, ICH localization (158 lobar, 81 deep, and 49 cerebellar), volume, blend sign, spot sign, finger-like projections, and subarachnoid haemorrhages were evaluated. ICH localization-specific differences for demographic (age, sex), clinical parameters (vascular risk factors, antiplatelet, and anticoagulation therapy), and CT markers were evaluated using logistic regression. We applied Cox proportional hazards modelling using these parameters to predict risk factors for ICH expansion, late ICH recurrence, and late mortality.

RESULTS

The blend sign in lobar ICH relates to increased risk of ICH expansion (HR2.3), late ICH recurrence (HR2.3), and mortality (HR1.6). Age, conditions requiring antiplatelet medication, deep ICH localization, volume, and blend sign represented the most important independent factors impacting overall mortality.

CONCLUSIONS

Blend sign at baseline ICH is a manifestation of underlying detrimental vascular processes that signal increased ICH expansion risk, although is also indicative of long-term risks for late recurrent ICH and late mortality.

Associations of renal function with cerebral small vessel disease and functional outcome in acute intracerebral haemorrhage: A hospital-based prospective cohort study

BACKGROUND

Intracerebral haemorrhage (ICH) is a severe clinical consequence of cerebral small vessel disease (SVD), but associations between renal impairment and SVD in patients with ICH have not been fully characterised.

METHODS

Using data from the CROMIS-2 ICH observational study, we compared SVD neuroimaging markers and total burden (score 0-3) identified using CT brain imaging in patients with and without renal impairment (estimated glomerular filtration rate, eGFR<60). We assessed functional outcome at 6-month follow-up using the modified Rankin scale.

RESULTS

1027 participants were included (mean age 72.8, 57.1% male); 274 with and 753 without renal impairment. 18.7% of the eGFR<60 group had moderate-to-severe SVD burden (score 2-3), compared with 14.0% of those with eGFR>60 (p = 0.039). SVD burden was associated with renal impairment after adjusting for hypertension (OR 1.36, 95% CI 1.04-1.77, p = 0.023), but not after adjusting for age. Cerebral atrophy was more prevalent in patients with eGFR<60 (81.2% vs. 72.0%, p = 0.002), as were WMH (45.6% vs. 36.6%, p = 0.026). Neither was associated with renal function after adjusting for age and vascular risk factors. Renal impairment was associated with functional outcome (OR 0.65, 95% CI 0.47-0.89, p = 0.007), but not after adjusting for age, pre-morbid function and comorbidities (OR 0.95, 95% CI 0.65-1.38, p = 0.774).

CONCLUSION

In acute ICH, renal impairment is associated with a higher cerebral SVD burden independent of hypertension, but not age. Reduced eGFR is associated with worse functional outcome, but not independent of age and comorbidities. Since CT has limited sensitivity to detect SVD severity and distribution, further studies including MRI are needed.

Perihematomal edema-based CT-radiomics model to predict functional outcome in patients with intracerebral hemorrhage

PURPOSE

The purpose of this study was to identify possible association between noncontrast computed tomography (NCCT)-based radiomics features of perihematomal edema (PHE) and poor functional outcome at 90 days after intracerebral hemorrhage (ICH) and to develop a NCCT-based radiomics-clinical nomogram to predict 90-day functional outcomes in patients with ICH.

MATERIALS AND METHODS

In this multicenter retrospective study, 107 radiomics features were extracted from 1098 NCCT examinations obtained in 1098 patients with ICH. There were 652 men and 446 women with a mean age of 60 ± 12 (SD) years (range: 23-95 years). After harmonized and univariable and multivariable screening, seven of these radiomics features were closely associated with the 90-day functional outcome of patients with ICH. The radiomics score (Rad-score) was calculated based on the seven radiomics features. A clinical-radiomics nomogram was developed and validated in three cohorts. The model performance was evaluated using area under the curve analysis and decision and calibration curves.

RESULTS

Of the 1098 patients with ICH, 395 had a good outcome at 90 days. Hematoma hypodensity sign and intraventricular and subarachnoid hemorrhages were identified as risk factors for poor outcomes (P < 0.001). Age, Glasgow coma scale score, and Rad-score were independently associated with outcome. The clinical-radiomics nomogram showed good predictive performance with AUCs of 0.882 (95% CI: 0.859-0.905), 0.834 (95% CI: 0.776-0.891) and 0.905 (95% CI: 0.839-0.970) in the three cohorts and clinical applicability.

CONCLUSION

NCCT-based radiomics features from PHE are highly correlated with outcome. When combined with Rad-score, radiomics features from PHE can improve the predictive performance for 90-day poor outcome in patients with ICH.

Noncontrast Computed Tomography Markers Associated with Hematoma Expansion: Analysis of a Multicenter Retrospective Study

BACKGROUND

Hematoma expansion (HE) is a significant predictor of poor outcomes in patients with intracerebral hemorrhage (ICH). Non-contrast computed tomography (NCCT) markers in ICH are promising predictors of HE. We aimed to determine the association of the NCCT markers with HE by using different temporal HE definitions.

METHODS

We utilized Risa-MIS-ICH trial data (risk stratification and minimally invasive surgery in acute intracerebral hemorrhage). We defined four HE types based on the time to baseline CT (BCT) and the time to follow-up CT (FCT). Hematoma volume was measured by software with a semi-automatic edge detection tool. HE was defined as a follow-up CT hematoma volume increase of >6 mL or a 33% hematoma volume increase relative to the baseline CT. Multivariable regression analyses were used to determine the HE parameters. The prediction potential of indicators for HE was evaluated using receiver-operating characteristic analysis.

RESULTS

The study enrolled 158 patients in total. The time to baseline CT was independently associated with HE in one type (odds ratio (OR) 0.234, 95% confidence interval (CI) 0.077-0.712, p = 0.011), and the blend sign was independently associated with HE in two types (OR, 6.203-6.985, both p < 0.05). Heterogeneous density was independently associated with HE in all types (OR, 6.465-88.445, all p < 0.05) and was the optimal type for prediction, with an area under the curve of 0.674 (p = 0.004), a sensitivity of 38.9%, and specificity of 96.0%.

CONCLUSION

In specific subtypes, the time to baseline CT, blend sign, and heterogeneous density were independently associated with HE. The association between NCCT markers and HE is influenced by the temporal definition of HE. Heterogeneous density is a stable and robust predictor of HE in different subtypes of hematoma expansion.

Relationships of Hemoglobin Concentration, Ischemic Lesions, and Clinical Outcomes in Patients With Intracerebral Hemorrhage

BACKGROUND

Hemoglobin concentration and diffusion-weighted imaging (DWI) ischemic lesions are separately known to be associated with poor intracerebral hemorrhage (ICH) outcomes. While hemoglobin concentrations have known relationships with ischemic stroke, it is unclear whether hemoglobin concentration is associated with DWI ischemic lesions after ICH. We sought to investigate the hypothesis that hemoglobin concentrations would associate with DWI lesions after ICH and further investigated their relationships with clinical outcomes.

METHODS

Supratentorial ICH patients enrolled between 2010 and 2016 to a prospective, multicenter, observational cohort study (ERICH study [Ethnic/Racial Variations of Intracerebral Hemorrhage]) were assessed. Patients from this study with baseline, admission hemoglobin, and hospitalization magnetic resonance imaging were analyzed. Hemoglobin was examined as the primary exposure variable defined as a continuous variable (g/dL). Magnetic resonance imaging DWI ischemic lesion presence was assessed as the primary radiographic outcome. Primary analyses assessed relationships of hemoglobin with DWI lesions. Secondary analyses assessed relationships of DWI lesions with poor 3-month outcomes (modified Rankin Scale score, 4-6). These analyses were performed using separate multivariable logistic regression models adjusting for relevant covariates.

RESULTS

Of 917 patients with ICH analyzed, mean baseline hemoglobin was 13.8 g/dL (±1.9), 60% were deep ICH, and DWI lesions were identified in 27% of the cohort. In our primary analyses, increased hemoglobin, defined as a continuous variable, was associated with DWI lesions (adjusted odds ratio, 1.21 per 1 g/dL change in hemoglobin [95% CI, 1.07-1.37]) after adjusting for sex, race, ICH severity, time to magnetic resonance imaging, and acute blood pressure change. In secondary analyses, DWI lesions were associated with poor 3-month outcomes (adjusted odds ratio, 1.83 [95% CI, 1.24-2.69]) after adjusting for similar covariates.

CONCLUSIONS

We identified novel relationships between higher baseline hemoglobin concentrations and DWI ischemic lesions in patients with ICH. Further studies are required to clarify the role of hemoglobin concentration on both cerebral small vessel disease pathophysiology and ICH outcomes.

Predicting Hemorrhage Progression in Deep Intracerebral Hemorrhage: A Multicenter Retrospective Cohort Study

BACKGROUND

Hemorrhage progression in deep intracerebral hemorrhage (ICH) involves not only the growth of parenchymal hematoma but also an increase in intraventricular hemorrhage (IVH). The search for methods that predict both the increased risk of parenchymal hematoma and IVH growth is warranted.

METHODS

We conducted a retrospective cohort study at multiple centers. Participants with deep ICH were enrolled from January 2018 to December 2021. Prediction models based on logistic regression analysis included clinical as well as routine radiographic and radiomics variables, separately or in combination. The performance of each model was evaluated using discrimination measures (e.g., area under the curve [AUC]). Evaluation of clinical utility was performed using decision curve analysis (DCA).

RESULTS

Overall, 647 individuals across 4 stroke centers were included. A total of 429 (66%) patients from 3 centers were assigned to the primary cohort and 218 (34%) from another center were placed in the validation cohort. Multivariate analysis showed that the Glasgow Coma Scale score, baseline ICH volume, IVH, blend sign, and radiomics score were associated with hemorrhage progression in the primary cohort. The clinical-radiomics model (AUC = 0.852 and 0.835) improved the prediction performance of hemorrhage progression compared to the Noncontrast computed tomography signs model (AUC = 0.666 and 0.618) in both the primary and validation cohorts, with similar results in the decision curve analysis curves.

CONCLUSIONS

The clinical-radiomics model outperformed the routine Noncontrast computed tomography signs model in predicting the progression of deep ICH. The clinical benefit of screening patients using this model may assist in risk stratification.

Added value of non-contrast CT and CT perfusion markers for prediction of intracerebral hemorrhage expansion and outcome

OBJECTIVES

To test the hypothesis that the combined analysis of non-contrast CT (NCCT) and CT perfusion (CTP) imaging markers improves prediction of hematoma expansion (HE) and outcome in intracerebral hemorrhage (ICH).

METHODS

Retrospective, single-center analysis of patients with primary ICH undergoing NCCT and CTP within 6 h from onset. NCCT images were assessed for the presence of intrahematomal hypodensity and shape irregularity. Perihematomal cerebral blood volume and spot sign were assessed on CTP. The main outcomes of the analysis were HE (growth > 6 mL and/or > 33%) and poor functional prognosis (90 days modified Rankin Scale 3-6). Predictors of HE and outcome were explored with logistic regression.

RESULTS

A total of 150 subjects were included (median age 68, 47.1% males) of whom 54 (36%) had HE and 52 (34.7%) had poor outcome. The number of imaging markers on baseline imaging was independently associated with HE (odds ratio 2.66, 95% confidence interval 1.70-4.17, p < 0.001) and outcome (odds ratio 1.64, 95% CI 1.06-2.56, p = 0.027). Patients with the simultaneous presence of all the four markers had the highest risk of HE and unfavorable prognosis (mean predicted probability of 91% and 79% respectively). The combined-markers analysis outperformed the sensitivity of the single markers analyzed separately. In particular, the presence of at least one marker identified patients with HE and poor outcome with 91% and 87% sensitivity respectively.

CONCLUSION

NCCT and CTP markers provide additional yield in the prediction of HE and ICH outcome.

KEY POINTS

• Perihematomal hypoperfusion is associated with hematoma expansion and poor outcome in acute intracerebral hemorrhage. • Non-contrast CT and CT perfusion markers improve prediction of hematoma expansion and unfavorable prognosis. • A multimodal CT protocol including CT perfusion will help the identification of patients at high risk of clinical deterioration and poor outcome.

Cerebral Amyloid Angiopathy and the Risk of Hematoma Expansion

OBJECTIVE

We assessed whether hematoma expansion (HE) and favorable outcome differ according to type of intracerebral hemorrhage (ICH).

METHODS

Among participants with ICH enrolled in the TICH-2 (Tranexamic Acid for Hyperacute Primary Intracerebral Haemorrhage) trial, we assessed baseline scans for hematoma location and presence of cerebral amyloid angiopathy (CAA) using computed tomography (CT, simplified Edinburgh criteria) and magnetic resonance imaging (MRI; Boston criteria) and categorized ICH as lobar CAA, lobar non-CAA, and nonlobar. The main outcomes were HE and favorable functional outcome. We constructed multivariate regression models and assessed treatment effects using interaction terms.

RESULTS

A total of 2,298 out of 2,325 participants were included with available CT (98.8%; median age = 71 years, interquartile range = 60-80 years; 1,014 female). Additional MRI was available in 219 patients (9.5%). Overall, 1,637 participants (71.2%) had nonlobar ICH; the remaining 661 participants (28.8%) had lobar ICH, of whom 202 patients had lobar CAA-ICH (8.8%, 173 participants according to Edinburgh and 29 participants according to Boston criteria) and 459 did not (lobar non-CAA, 20.0%). For HE, we found a significant interaction of lobar CAA ICH with time from onset to randomization (increasing risk with time, p_interaction  < 0.001) and baseline ICH volume (constant risk regardless of volume, p_interaction  < 0.001) but no association between type of ICH and risk of HE or favorable outcome. Tranexamic acid significantly reduced the risk of HE (adjusted odds ratio = 0.7, 95% confidence interval = 0.6-1.0, p = 0.020) without statistically significant interaction with type of ICH (p_interaction  = 0.058). Tranexamic acid was not associated with favorable outcome.

INTERPRETATION

Risk of HE in patients with lobar CAA-ICH was not independently increased but seems to have different dynamics compared to other types of ICH. The time window for treatment of CAA-ICH to prevent HE may be longer. ANN NEUROL 2022;92:921-930.

Radiomics for prediction of intracerebral hemorrhage outcomes: A retrospective multicenter study

BACKGROUND

Accurate risk stratification of patients with intracerebral hemorrhage (ICH) could help refine adjuvant therapy selection and better understand the clinical course. We aimed to evaluate the value of radiomics features from hematomal and perihematomal edema areas for prognosis prediction and to develop a model combining clinical and radiomic features for accurate outcome prediction of patients with ICH.

METHODS

This multicenter study enrolled patients with ICH from January 2016 to November 2021. Their outcomes at 3 months were recorded based on the modified Rankin Scale (good, 0-3; poor, 4-6). Independent clinical and radiomic risk factors for poor outcome were identified through multivariate logistic regression analysis, and predictive models were developed. Model performance and clinical utility were evaluated in both internal and external cohorts.

RESULTS

Among the 1098 ICH patients evaluated (mean age, 60 ± 13 years), 703 (64 %) had poor outcomes. Age, hemorrhage volume and location, and Glasgow Coma Scale (GCS) were independently associated with outcomes. The area under the receiver operating characteristic curve (AUC) of the clinical model was 0.881 in the external validation cohort. Addition of the Rad-score (combined hematoma and perihematomal edema area) improved predictive accuracy and model performance (AUC, 0.893), net reclassification improvement, 0.140 (P < 0.001), and integrated discrimination improvement, 0.050 (P < 0.001).

CONCLUSIONS

The radiomics features of hematomal and perihematomal edema area have additional value in prognostic prediction; moreover, addition of radiomic features significantly improves model accuracy.

A non-contrast computed tomography-based radiomics nomogram for the prediction of hematoma expansion in patients with deep ganglionic intracerebral hemorrhage

Background and purpose

Hematoma expansion (HE) is a critical event following acute intracerebral hemorrhage (ICH). We aimed to construct a non-contrast computed tomography (NCCT) model combining clinical characteristics, radiological signs, and radiomics features to predict HE in patients with spontaneous ICH and to develop a nomogram to assess the risk of early HE.

Materials and methods

We retrospectively reviewed 388 patients with ICH who underwent initial NCCT within 6 h after onset and follow-up CT within 24 h after initial NCCT, between January 2015 and December 2021. Using the LASSO algorithm or stepwise logistic regression analysis, five models (clinical model, radiological model, clinical-radiological model, radiomics model, and combined model) were developed to predict HE in the training cohort (n = 235) and independently verified in the test cohort (n = 153). The Akaike information criterion (AIC) and the likelihood ratio test (LRT) were used for comparing the goodness of fit of the five models, and the AUC was used to evaluate their ability in discriminating HE. A nomogram was developed based on the model with the best performance.

Results

The combined model (AIC = 202.599, χ2 = 80.6) was the best fitting model with the lowest AIC and the highest LRT chi-square value compared to the clinical model (AIC = 232.263, χ2 = 46.940), radiological model (AIC = 227.932, χ2 = 51.270), clinical-radiological model (AIC = 212.711, χ2 = 55.490) or radiomics model (AIC = 217.647, χ2 = 57.550). In both cohorts, the nomogram derived from the combined model showed satisfactory discrimination and calibration for predicting HE (AUC = 0.900, sensitivity = 83.87%; AUC = 0.850, sensitivity = 80.10%, respectively).

Conclusion

The NCCT-based model combining clinical characteristics, radiological signs, and radiomics features could efficiently discriminate early HE, and the nomogram derived from the combined model, as a non-invasive tool, exhibited satisfactory performance in stratifying HE risks.

Diffusion-weighted imaging hyperintensities during the chronic stage of intracerebral hemorrhage with surgery: A new clinical situation or post-surgery artifact?

Background and objective

Diffusion-weighted imaging (DWI) hyperintensities were occasionally seen at previous hematoma in patients several months after intracerebral hemorrhage with surgery. Whether they are newly occurred clinical situations or post-surgery changes is unknown. This study aims to investigate the prevalence and possible mechanisms for this phenomenon.

Methods

We retrospectively reviewed the MRI database for intracerebral hemorrhage with surgery after 3 months of disease onset in our hospital. We also prospectively performed repeated multimodal MRI scans for two patients at the chronic stage after surgery for intracerebral hemorrhage.

Results

We found that 14 out of 23 patients (60.9%) had DWI hyperintensities at the site of previous hematoma 3 months after intracerebral hemorrhage with surgery. All the DWI lesions were hyperintense on T1- and T2-weighted imaging, most of which appeared long and narrow in shape. The DWI lesions were usually located adjacent to the thin wall of the previous hematoma cavity close to the lateral ventricle. They were more associated with the basal ganglia hemorrhage than with the lobar hemorrhage (P = 0.02) and were more frequently seen for those with intraventricular hemorrhage than without (P = 0.02). Prospectively repeated MRI exams of two patients revealed unchanged DWI hyperintensity during the 18- and 2-month follow-up, respectively.

Conclusion

The DWI lesions at previous hematoma were commonly seen in patients after surgery for intracerebral hemorrhage at the chronic stage which would persist for years. We hypothesized a possible mechanism by which extracellular methemoglobin “islands” are formed with delayed or no absorption by macrophages from adjacent thin residual brain tissue. Unnecessary further examinations and treatment would be avoided by realizing this imaging phenomenon.

Intraventricular Hemorrhage Expansion in the CLEAR III Trial: A Post Hoc Exploratory Analysis

BACKGROUND

The objective of this study was to evaluate factors associated with intraventricular hemorrhage (IVH) expansion and its association with long-term outcomes.

METHODS

We performed a post hoc analysis of the international, multi-center CLEAR III trial (Clot Lysis: Evaluating Accelerated Resolution of Intraventricular Hemorrhage) which enrolled IVH patients between September 1, 2009, and January 31, 2015. The exposure was IVH expansion, defined as >1 mL increase in volume between baseline and stability computed tomography scans, before treatment randomization. We assessed factors associated with IVH expansion and secondarily assessed the relationship of IVH expansion with clinical outcomes: composite of death or major disability (modified Rankin Scale score, >3), and mortality alone at 6 months. The relationship of IVH expansion on ventriculoperitoneal shunt placement was additionally explored. Multivariable logistic regression was used for all analyses.

RESULTS

Of 500 IVH patients analyzed, the mean age was 59 (±11) years old, 44% were female and 135 (27%) had IVH expansion. In multivariable regression models, factors associated with IVH expansion were baseline parenchymal intracerebral hemorrhage (ICH) volume (adjusted odds ratio [OR], 1.04 per 1 mL increase [95% CI, 1.01-1.08]), presence of parenchymal hematoma expansion: >33% (adjusted OR, 6.63 [95% CI, 3.92-11.24]), time to stability head CT (adjusted OR, 0.71 per 1 hour increase [95% CI, 0.54-0.94]), and thalamic hematoma location (adjusted OR, 1.68 [95% CI, 1.01-2.79]) while additionally adjusting for age, sex, and race. In secondary analyses, IVH expansion was associated with higher odds of poor 6-month outcomes (adjusted OR, 1.84 [95% CI, 1.12-3.02]) but not mortality (OR, 1.40 [95% CI, 0.78-2.50]) after adjusting for baseline ICH volume, thalamic ICH location, age, anticoagulant use, Glasgow Coma Scale score, any withdrawal of care order, and treatment randomization arm. However, there were no relationships of IVH expansion on subsequent ventriculoperitoneal shunt placement (adjusted OR, 1.02 [95% CI, 0.58-1.80]) after adjusting for similar covariates.

CONCLUSIONS

In a clinical trial cohort of patients with large IVH, acute hematoma characteristics, specifically larger parenchymal volume, hematoma expansion, and thalamic ICH location were associated with IVH expansion. Given that IVH expansion resulted in poor functional outcomes, exploration of treatment approaches to optimize hemostasis and prevent IVH expansion, particularly in patients with thalamic ICH, require further study.

REGISTRATION

URL: https://www.

CLINICALTRIALS

gov; Unique identifier: NCT00784134.

Development and Validation of a Clinical-Based Signature to Predict the 90-Day Functional Outcome for Spontaneous Intracerebral Hemorrhage

We aimed to develop and validate an objective and easy-to-use model for identifying patients with spontaneous intracerebral hemorrhage (ICH) who have a poor 90-day prognosis. This three-center retrospective study included a large cohort of 1,122 patients with ICH who presented within 6 h of symptom onset [training cohort, n = 835; internal validation cohort, n = 201; external validation cohort (center 2 and 3), n = 86]. We collected the patients’ baseline clinical, radiological, and laboratory data as well as the 90-day functional outcomes. Independent risk factors for prognosis were identified through univariate analysis and multivariate logistic regression analysis. A nomogram was developed to visualize the model results while a calibration curve was used to verify whether the predictive performance was satisfactorily consistent with the ideal curve. Finally, we used decision curves to assess the clinical utility of the model. At 90 days, 714 (63.6%) patients had a poor prognosis. Factors associated with prognosis included age, midline shift, intraventricular hemorrhage (IVH), subarachnoid hemorrhage (SAH), hypodensities, ICH volume, perihematomal edema (PHE) volume, temperature, systolic blood pressure, Glasgow Coma Scale (GCS) score, white blood cell (WBC), neutrophil, and neutrophil-lymphocyte ratio (NLR) (p < 0.05). Moreover, age, ICH volume, and GCS were identified as independent risk factors for prognosis. For identifying patients with poor prognosis, the model showed an area under the receiver operating characteristic curve of 0.874, 0.822, and 0.868 in the training cohort, internal validation, and external validation cohorts, respectively. The calibration curve revealed that the nomogram showed satisfactory calibration in the training and validation cohorts. Decision curve analysis showed the clinical utility of the nomogram. Taken together, the nomogram developed in this study could facilitate the individualized outcome prediction in patients with ICH.

Early Deterioration, Hematoma Expansion, and Outcomes in Deep Versus Lobar Intracerebral Hemorrhage: The FAST Trial

BACKGROUND

In patients with intracerebral hemorrhage (ICH), it is unclear whether early neurological deterioration, hematoma expansion (HE), and outcome vary by supratentorial ICH location (deep versus lobar). Herein, we assessed these relationships in a clinical trial cohort that underwent brain imaging early after symptom onset. We hypothesized that HE would occur more frequently, and outcome would be worse in patients with deep ICH.

METHODS

We performed a post hoc analysis of the FAST (Factor-VII-for-Acute-Hemorrhagic-Stroke-Treatment) trial including all patients with supratentorial hemorrhage. Enrolled patients underwent brain imaging within 3 hours of symptom onset and 24 hours after randomization. Multivariable regression was used to test the association between ICH location and 3 outcomes: HE (increase of ≥33% or 6mL), early neurological deterioration (decrease in Glasgow Coma Scale score ≥2 points or increase in National Institutes of Health Stroke Scale ≥4 points within 24 hours of admission), and 90-day outcome (modified Rankin Scale).

RESULTS

Of 841 FAST trial patients, we included 728 (mean age 64 years, 38% women) with supratentorial hemorrhages (deep n=623, lobar n=105). HE (44 versus 27%, P=0.001) and early neurological deterioration (31 versus 17%, P=0.001) were more common in lobar hemorrhages. Deep hemorrhages were smaller than lobar hemorrhages at baseline (12 versus 35mL, P<0.001) and 24 hours (14 versus 38mL, P<0.001). Unadjusted 90-day outcome was worse in lobar compared with deep ICH (median modified Rankin Scale score 5 versus 4, P=0.03). However, when adjusting for variables included in the ICH score including ICH volume, deep location was associated with worse and lobar location with better outcome (odds ratio lobar location, 0.58 [95% CI, 0.38-0.89]; P=0.01).

CONCLUSIONS

In this secondary analysis of randomized trial patients, lobar ICH location was associated with larger ICH volume, more HE and early neurological deterioration, and worse outcome than deep ICH. After adjustment for prognostic variables, however, deep ICH was associated with worse outcome, likely due to their proximity to eloquent brain structures.

Association Between Anatomical Location and Hematoma Expansion in Deep Intracerebral Hemorrhage

Objective

To establish the relationship between hematoma sites of involvement and hematoma expansion (HE) in patients with deep intracerebral hemorrhage (ICH).

Methods

Eligible patients with deep ICH admitted to hospital within 6 hours of onset between 2018 and 2020 were included in this retrospective multi-center study. Individuals with secondary ICH were excluded. The volume of HE was evaluated based on admission and follow-up computed tomography scans. Associations between deep ICH sites of involvement and HE were examined using multivariable logistic regression analysis while adjusting for confounding covariates of HE.

Results

We enrolled 583 individuals from three stroke centers. Data from a final total of 460 patients were used in the analysis; of these patients, 159 (34.6%) had HE. In the crude model without adjustment, external capsule, anterior limb of the internal capsule, and posterior limb of the internal capsule (PLIC) involvement were correlated with HE. After fully adjusted models for sex, age, intraventricular hemorrhage, Glasgow Coma Scale admission score, baseline ICH volume, and time from onset to initial computed tomography, multivariable logistic regression revealed that the PLIC is a robust predictor of HE in patients with deep ICH (adjusted odds ratio = 2.73; 95% confidence interval = 1.75–4.26; p < 0.001).

Conclusion

Involvement of the posterior limb of the internal capsule in deep hemorrhage could be a promising predictor of HE.

Imaging markers of intracerebral hemorrhage expansion in patients with unclear symptom onset

Background:

Hematoma expansion (HE) is common and associated with poor outcome in intracerebral hemorrhage (ICH) with unclear symptom onset (USO).

Aims:

We tested the association between non-contrast computed tomography (NCCT) markers and HE in this population.

Methods:

Retrospective analysis of patients with primary spontaneous ICH admitted at five centers in the United States and Italy. Baseline NCCT was analyzed for presence of the following markers: intrahematoma hypodensities, heterogeneous density, blend sign, and irregular shape. Variables associated with HE (hematoma growth > 6 mL and/or > 33% from baseline to follow-up imaging) were explored with multivariable logistic regression.

Results:

Of 2074 patients screened, we included 646 subjects (median age = 75, 53.9% males), of whom 178 (27.6%) had HE. Hypodensities (odds ratio (OR) = 2.67, 95% confidence interval (CI) = 1.79–3.98), heterogeneous density (OR = 2.16, 95% CI = 1.46–3.21), blend sign (OR = 2.28, 95% CI = 1.38–3.75) and irregular shape (OR = 1.82, 95% CI = 1.21–2.75) were independently associated with a higher risk of HE, after adjustment for confounders (ICH volume, anticoagulation, and time from last seen well (LSW) to NCCT). Hypodensities had the highest sensitivity for HE (0.69), whereas blend sign was the most specific marker (0.90). All NCCT markers were more frequent in early presenters (time from LSW to NCCT ⩽ 6 h, n = 189, 29.3%), and more sensitive in this population as well (hypodensities had 0.77 sensitivity).

Conclusion:

NCCT markers are associated with HE in ICH with USO. These findings require prospective replication and suggest that NCCT features may help the stratification of HE in future studies on USO patients.

Heterogeneity of Stroke in Patients with Systemic Lupus Erythematosus

Objective The underlying pathophysiology varies according to stroke subtype. However, stroke heterogeneity among patients with systemic lupus erythematosus (SLE) remains unstudied. We hypothesized that the contribution of SLE to stroke might vary according to its subtype and investigated the associations of SLE and various stroke subtypes. Methods Diagnostic codes and electronic medical records were used to identify 70 patients with SLE who developed acute cerebral infarction or intracerebral hemorrhaging at four tertiary referral hospitals between 2008 and 2018. Intracerebral hemorrhaging was classified as lobar or deep, while cerebral infarction was classified according to the SSS-TOAST criteria. Physician notes were used to identify SLE activity, and their prevalences were compared among stroke subtypes. Outcomes were collected from the patients' medical records. Results The most common stroke subtype in patients with SLE was that of undetermined causes (31%), followed by small artery occlusion (16%), cardioaortic embolism (13%), other causes (11%), lobar hemorrhaging (10%), deep hemorrhaging (10%), and large artery atherosclerosis (9%). Stroke onset occurred during a period of high SLE activity in 21 patients (30%). The proportion of patients with high SLE activity varied according to stroke subtype (p=0.039) and was highest for cerebral infarction with undetermined causes. Stroke recurrence or death was observed in 40% of patients within 5 years after the initial stroke onset. Conclusion The contributions of SLE to stroke varied significantly according to the stroke subtype. Given the unfavorable prognosis, close stroke subtype-specific observation by rheumatologists and stroke specialists is recommended after stroke events.

Different Effects of Hematoma Expansion on Short-Term Functional Outcome in Basal Ganglia and Thalamic Hemorrhages

Purpose

To investigate the impact of hematoma expansion (HE) on short-term functional outcome of patients with thalamic and basal ganglia intracerebral hemorrhage.

Methods

Data of 420 patients with deep intracerebral hemorrhage (ICH) that received a baseline CT scan within 6 hours from symptom onset and a follow-up CT scan within 72 hours were retrospectively analyzed. The poor functional outcome was defined as modified Rankin score (mRS) > 3 at 30 days. Receiver operating characteristic (ROC) curves for relative and absolute growth of HE were generated and compared. Multivariable logistic regression models were used to analyze the impact of HE on the functional outcome in basal ganglia and thalamic hemorrhages. The predictive values for different thresholds of HE were calculated, and correlation coefficient matrices were used to explore the correlation between the covariables.

Results

Basal ganglia ICH showed a higher possibility of absolute hematoma growth than thalamic ICH. The area under the curve (AUC) for absolute and relative growth of thalamic hemorrhage was lower than that of basal ganglia hemorrhage (AUC 0.71 and 0.67, respectively) in discriminating short-term poor outcome with an AUC of 0.59 and 0.60, respectively. Each threshold of HE independently predicted poor outcome in basal ganglia ICH (P < 0.001), with HE > 3 ml and > 6 ml showing higher positive predictive values and accuracy compared to HE > 33%. In contrast, thalamic ICH had a smaller baseline volume (BV, 9.55 ± 6.85 ml) and was more likely to initially involve the posterior limb of internal capsule (PLIC) (85/153, 57.82%), and the risk of HE was lower without PLIC involvement (4.76%, P = 0.009). Therefore, in multivariate analysis, the effect of thalamic HE on poor prognosis was largely replaced by BV and the involvement of PLIC, and the adjusted odds ratios (ORs) of HE was not significant (P > 0.05).

Conclusion

Though HE is a high-risk factor for short-term poor functional outcome, it is not an independent risk factor in thalamic ICH, and absolute growth is more predictive of poor outcome than relative growth for basal ganglia ICH.

A Novel CT-based Radiomics-Clinical Nomogram for the Prediction of Short-Term Prognosis in Deep Intracerebral Hemorrhage

OBJECTIVE

To develop and validate a radiomics-clinical nomogram for the prediction of short-term prognosis in patients with deep intracerebral hemorrhage (DICH) on admission.

METHODS

A total of 326 patients with DICH (development cohort = 187; testing cohort = 81; validation cohort = 58) were retrospectively included. Radiomics features were extracted from computed tomography (CT) images and optimal features were selected using least absolute shrinkage and selection operator regression. A radiomics score (R-score) was developed using the optimal features. Univariate and multivariate analyses were used to determine independent risk factors for poor outcomes at 30 days. A radiomics-clinical (R-C) nomogram was developed and validated in the three cohorts. Receiver operating characteristic curve (ROC), calibration curve and decision curve analyses were conducted to evaluate the performances of the R-C nomogram.

RESULTS

Only 4 of 396 radiomics features were selected to develop R-scores. Age, onset-to-CT time, Glasgow Coma Scale score, midline shift, and R-score were detected as independent predictors of poor prognosis of DICH. The R-C nomogram was developed by the independent predictors and showed acceptable discrimination with areas under ROCs of 0.80, 0.79, and 0.70 in the development, testing and validation cohorts, respectively. The R-C nomogram showed good agreement between the predicted probability and the actual probability (all P > 0.05) and clinical applicability in each cohort.

CONCLUSIONS

The R-C nomogram is a stable and effective tool for predicting the short-term prognosis of DICH, which may help clinicians perform individual risk assessments and make decisions for patients with DICH.

Atrial Fibrillation in Spontaneous Intracerebral Hemorrhage, Dijon Stroke Registry (2006-2017)

Background

Atrial fibrillation (AF) represents a major indication for oral anticoagulants (OAC) that contribute to spontaneous intracerebral hemorrhage (ICH). This study evaluated AF prevalence among patients with ICH, temporal trends, and early functional outcomes and death of patients.

Methods and Results

Patients with first‐ever ICH were prospectively recorded in the population‐based stroke registry of Dijon, France, (2006–2017). Association between AF and early outcome of patients with ICH (ordinal modified Rankin Scale score and death at discharge) were analyzed using ordinal and logistic regressions. Among 444 patients with ICH, 97 (21.9%) had AF, including 65 (14.6%) with previously known AF treated with OAC, and 13 (2.9%) with newly diagnosed AF. AF prevalence rose from 17.2% (2006–2011) to 25.8% (2012–2017) (P‐trend=0.05). An increase in the proportion of AF treated with OAC (11.3% to 17.5%, P‐trend=0.09) and newly diagnosed AF (1.5% to 4.2%, P‐trend=0.11) was observed. In multivariable analyses, after adjustment for premorbid OAC, AF was not significantly associated with ordinal modified Rankin Scale score (odds ratio [OR], 1.29; 95% CI, 0.69–2.42) or death (OR, 0.89; 95% CI, 0.40–1.96) in patients with ICH. Nevertheless, adjusted premorbid OAC use remained highly associated with a higher probability of death (OR, 2.53; 95% CI, 1.11–5.78).

Conclusions

AF prevalence and use of OAC among patients with ICH increased over time. Premorbid use of OAC was associated with poor outcome after ICH, thus suggesting a need to better identify ICH risk before initiating or pursuing OAC therapy in patients with AF, and to develop acute treatment and secondary prevention strategies after ICH in patients with AF.

Recommended Primary Outcomes for Clinical Trials Evaluating Hemostatic Agents in Patients With Intracranial Hemorrhage: A Consensus Statement

IMPORTANCE

In patients with acute spontaneous or traumatic intracranial hemorrhage, early hemostasis is thought to be critical to minimize ongoing bleeding. However, research evaluating hemostatic therapies has been hampered by a lack of standardized clinical trial outcome measures.

OBJECTIVE

To identify appropriate primary outcomes for phase 2 and 3 clinical trials of therapies aimed at reducing acute intracranial bleeding.

EVIDENCE REVIEW

A comprehensive review of all previous clinical trials of hemostatic therapy for intracranial bleeding was performed, and studies measuring the frequency, risk factors, and association of intracranial bleeding with outcome of hemorrhage growth were included.

FINDINGS

A hierarchy of 3 outcome measures is recommended, with the first choice being a global patient-centered clinical outcome scale measured 30 to 180 days after the event; the second, a combined clinical and radiographic end point associating hemorrhage expansion with a poor patient-centered outcome at 24 hours or later; and the third, a radiographic measure of hemorrhage expansion at 24 hours alone. Additional recommendations stress the importance of separating various subtypes of bleeding when possible, early treatment within a standardized treatment window, and the routine use of computerized planimetry comparing continuous measures of absolute and relative hemorrhage growth as either a primary or secondary end point.

CONCLUSIONS AND RELEVANCE

Standardization of outcome measures in studies of intracranial bleeding and hemostatic therapy will support comparative effectiveness research and meta-analysis, with the goal of accelerating the translation of research into clinical practice. The 3 outcome measures proposed in this consensus statement could help this process.

Predicting intraventricular hemorrhage growth with a machine learning-based, radiomics-clinical model

We constructed a radiomics-clinical model to predict intraventricular hemorrhage (IVH) growth after spontaneous intracerebral hematoma. The model was developed using a training cohort (N=626) and validated with an independent testing cohort (N=270). Radiomics features and clinical predictors were selected using the least absolute shrinkage and selection operator (LASSO) method and multivariate analysis. The radiomics score (Rad-score) was calculated through linear combination of selected features multiplied by their respective LASSO coefficients. The support vector machine (SVM) method was used to construct the model. IVH growth was experienced by 13.4% and 13.7% of patients in the training and testing cohorts, respectively. The Rad-score was associated with severe IVH and poor outcome. Independent predictors of IVH growth included hypercholesterolemia (odds ratio [OR], 0.12 [95%CI, 0.02-0.90]; p=0.039), baseline Graeb score (OR, 1.26 [95%CI, 1.16-1.36]; p<0.001), time to initial CT (OR, 0.70 [95%CI, 0.58-0.86]; p<0.001), international normalized ratio (OR, 4.27 [95%CI, 1.40, 13.0]; p=0.011), and Rad-score (OR, 2.3 [95%CI, 1.6-3.3]; p<0.001). In the training cohort, the model achieved an AUC of 0.78, sensitivity of 0.83, and specificity of 0.66. In the testing cohort, AUC, sensitivity, and specificity were 0.71, 0.81, and 0.64, respectively. This radiomics-clinical model thus has the potential to predict IVH growth.

Hematoma Expansion in Intracerebral Hemorrhage With Unclear Onset

OBJECTIVE

To investigate the prevalence, predictors, and prognostic effect of hematoma expansion (HE) in patients with intracerebral hemorrhage (ICH) with unclear symptom onset (USO).

METHODS

We performed a retrospective analysis of patients with primary spontaneous ICH admitted at 5 academic medical centers in the United States and Italy. HE (volume increase >6 mL or >33% from baseline to follow-up noncontrast CT [NCCT]) and mortality at 30 days were the outcomes of interest. Baseline NCCT was also analyzed for presence of hypodensities (any hypodense region within the hematoma margins). Predictors of HE and mortality were explored with multivariable logistic regression.

RESULTS

We enrolled 2,165 participants, 1,022 in the development cohort and 1,143 in the replication cohort, of whom 352 (34.4%) and 407 (35.6%) had ICH with USO, respectively. When compared with participants having a clear symptom onset, patients with USO had a similar frequency of HE (25.0% vs 21.9%, p = 0.269 and 29.9% vs 31.5%, p = 0.423). Among patients with USO, HE was independently associated with mortality after adjustment for confounders (odds ratio [OR] 2.64, 95% confidence interval [CI] 1.43-4.89, p = 0.002). This finding was similar in the replication cohort (OR 3.46, 95% CI 1.86-6.44, p < 0.001). The presence of NCCT hypodensities in patients with USO was an independent predictor of HE in the development (OR 2.59, 95% CI 1.27-5.28, p = 0.009) and replication (OR 2.43, 95% CI 1.42-4.17, p = 0.001) population.

CONCLUSION

HE is common in patients with USO and independently associated with worse outcome. These findings suggest that patients with USO may be enrolled in clinical trials of medical treatments targeting HE.