Independent Validation of the Hematoma Expansion Prediction Score: A Non-contrast Score Equivalent in Accuracy to the Spot Sign

A prediction of hematoma expansion in hemorrhagic patients using a novel dual-modal machine learning strategy

Objective.Hematoma expansion is closely associated with adverse functional outcomes in patients with intracerebral hemorrhage (ICH). Prediction of hematoma expansion would therefore be of great clinical significance. We therefore attempted to predict hematoma expansion using a dual-modal machine learning (ML) strategy which combines information from non-contrast computed tomography (NCCT) images and multiple clinical variables.Approach.We retrospectively identified 140 ICH patients (57 with hematoma expansion) with 5616 NCCT images of hematoma (2635 with hematoma expansion) and 10 clinical variables. The dual-modal ML strategy consists of two steps. The first step is to derive a mono-modal predictor from a deep convolutional neural network using solely NCCT images. The second step is to achieve a dual-modal predictor by combining the mono-modal predictor with 10 clinical variables to predict hematoma growth using a multi-layer perception network.Main results. For the mono-modal predictor, the best performance was merely 69.5% in accuracy with solely the NCCT images, whereas the dual-modal predictor could boost the accuracy greatly to be 86.5% by combining clinical variables.Significance.To our knowledge, this is the best performance from using ML to predict hematoma expansion. It could be potentially useful as a screening tool for high-risk patients with ICH, though further clinical tests would be necessary to show its performance on a larger cohort of patients.

Validation and Comparison of Noncontrast CT Scores to Predict Intracerebral Hemorrhage Expansion

BACKGROUND AND PURPOSE

The BAT, BRAIN, and HEP scores have been proposed to predict hematoma expansion (HE) with noncontrast computed tomography (NCCT). We sought to validate these tools and compare their diagnostic performance.

METHODS

We retrospectively analyzed two cohorts of patients with primary intracerebral hemorrhage. HE expansion was defined as volume growth > 33% or > 6 mL. Two raters analyzed NCCT scans and calculated the scores, blinded to clinical and imaging data. The inter-rater reliability was assessed with the interclass correlation statistic. Discrimination and calibration were calculated with area under the curve (AUC) and Hosmer-Lemeshow χ² statistic, respectively. AUC comparison between different scores was explored with DeLong test. We also calculated the sensitivity, specificity, positive, and negative predictive values of the dichotomized scores with cutoffs identified with the Youden's index.

RESULTS

A total of 230 subjects were included, of whom 86 (37.4%) experienced HE. The observed AUC for HE were 0.696 for BAT, 0.700 for BRAIN, and 0.648 for HEP. None of the scores had a significantly superior AUC compared with the others (all p > 0.4). All the scores had good calibration (all p > 0.3) and good-to-excellent inter-rater reliability (interclass correlation > 0.8). BAT ≥ 3 showed the highest specificity (0.81), whereas BRAIN ≥ 6 had the highest sensitivity (0.76).

CONCLUSIONS

The BAT, BRAIN, and HEP scores can predict HE with acceptable discrimination and require just a baseline NCCT scan. These tools may be used to stratify the risk of HE in clinical practice or randomized controlled trials.

Accuracy of imaging markers on noncontrast computed tomography in predicting intracerebral hemorrhage expansion

Objectives Hematoma expansion (HE) is an important factor of unfavorable outcome in patients with intracerebral hemorrhage (ICH). Imaging markers on noncontrast computed tomography (NCCT) provide increasing value in the prediction of HE due to fast and easy-to-use advantages; however, the accuracy of NCCT-based prediction of intracerebral HE remains unclear. We aimed to investigate the predictive accuracy of NCCT markers for the evaluation of HE using a well-characterized ICH cohort. Methods We retrospectively analyzed 414 patients with spontaneous ICH, who underwent baseline CT within 6 h after symptom onset and follow-up CT within 24 h after ICH. Hematoma volumes were measured on baseline and follow-up CT images, and imaging features that predicted HE were analyzed. The test characteristics for the NCCT predictors were calculated. Results Of the 414 patients investigated, 63 presented blend sign, 45 showed black hole sign, 36 had island sign and 34 had swirl sign. In the 414 patients, 88 presented HE, the incidence was 21.26%. Of the 88 patients with HE, 22 presented blend sign, 11 showed black hole sign, 8 had swirl sign and 7 had island sign. The blend sign showed highest sensitivity (25.00%) and swirl sign showed the highest specificity (92.02%) among the four predictors. We noted excellent interobserver agreement for the identification of HE. Conclusion The four NCCT markers can predict HE with limited sensitivity, high specificity and good accuracy. This may be useful for prompt identification of patients at high risk of active bleeding, and prevention of over-treatment associated with HE. Abbreviations HE, hematoma expansion; ICH, intracerebral hemorrhage; NCCT, noncontrast computed tomography.

Evaluation of andexanet alfa and four-factor prothrombin complex concentrate (4F-PCC) for reversal of rivaroxaban- and apixaban-associated intracranial hemorrhages

BACKGROUND/OBJECTIVE

Before approval of andexanet alfa, off-label treatment with 4-factor prothrombin complex concentrate (4F-PCC) was often utilized for the management of life-threatening hemorrhages associated with oral factor Xa inhibitors. We evaluated the operational processes and outcomes of patients with oral factor Xa inhibitor-associated intracranial hemorrhages (ICH) treated with andexanet alfa or 4F-PCC.

METHODS

We performed a retrospective, single-center case series of rivaroxaban or apixaban-associated ICH between 2016-2019 treated with andexanet alfa or 4F-PCC. Good or excellent hemostatic effectiveness, good functional outcome (Glasgow Outcome Score [GOS]> 3) at hospital discharge, and incidence of thrombosis within 30 days were reported.

RESULTS

Eighteen patients were included in the andexanet alfa cohort and 11 in the 4F-PCC cohort. Excellent or good hemostasis occurred in 88.9% of andexanet alfa-treated patients and 60% of 4F-PCC-treated patients. Good functional outcome on discharge occurred in 55.6% of andexanet alfa-treated patients and 9.1% of 4F-PCC-treated patients. Thrombotic complications occurred in 16.7% of andexanet alfa-treated patients and 9.1% of 4F-PCC-treated patients. Median order-to-administration time was 1.1 hours [0.8-1.4] versus 0.5 hours [0.1-0.8] in the andexanet alfa and 4F-PCC group, respectively. The median cost of therapy was $29970/patient versus $6925/patient in the andexanet alfa and 4F-PCC group, respectively.

CONCLUSIONS

We observed higher rates of occurrence of good or excellent hemostasis and GOS > 3 on hospital discharge and increased incidence of thrombosis in patients who received andexanet alfa compared to 4F-PCC for oral factor Xa inhibitor reversal. However, patients receiving 4F-PCC had lower pre-reversal Glasgow Coma Scale (GCS)score and larger pre-reversal ICH volume.

Standards for Detecting, Interpreting, and Reporting Noncontrast Computed Tomographic Markers of Intracerebral Hemorrhage Expansion

Significant hematoma expansion (HE) affects one-fifth of people within 24 hours after acute intracerebral hemorrhage (ICH), and its prevention is an appealing treatment target. Although the computed tomography (CT)-angiography spot sign predicts HE, only a minority of ICH patients receive contrast injection. Conversely, noncontrast CT (NCCT) is used to diagnose nearly all ICH, so NCCT markers represent a widely available alternative for prediction of HE. However, different NCCT signs describe similar features, with lack of consensus on the optimal image acquisition protocol, assessment, terminology, and diagnostic criteria. In this review, we propose practical guidelines for detecting, interpreting, and reporting NCCT predictors of HE. ANN NEUROL 2019;86:480-492.