Radiomics for predicting revised hematoma expansion with the inclusion of intraventricular hemorrhage growth in patients with supratentorial spontaneous intraparenchymal hematomas

Abstract

Background: Previous radiomics analyses of hematoma expansion have been based on the traditional definition, which only focused on changes in intraparenchymal volume. However, the ability of radiomicsrelated models to predict revised hematoma expansion (RHE) with the inclusion of intraventricular hemorrhage expansion remains unclear. To develop and validate a noncontrast computed tomography (NCCT)-based clinical-semantic-radiomics nomogram to identify supratentorial spontaneous intracerebral hemorrhage (sICH) patients with RHE on admission. Methods: In this double-center retrospective study, data from 376 patients with sICH (training set: n=299; test set: n=77; external validation cohort: n=91) were reviewed. A radiomics model, a clinical-semantic model, and a combined model were then constructed based on the logistic regression machine learning approach. Radiomics features were extracted and selected by least absolute shrinkage and selection operator (LASSO) with 5-fold cross validation. Furthermore, the classical BRAIN scoring system was also constructed to predict RHE. Discriminative performance of the models was evaluated on the training and test set with area under the curve (AUC) and decision curve analysis (DCA). Results: The addition of radiomics to clinical-semantic factors significantly improved the prediction performance of RHE compared with the clinical-semantic model alone in the training (AUC, 0.94 vs. 0.81, P<0.05) and test (AUC, 0.84 vs. 0.71, P<0.05) sets, with similar results in the validation set (AUC, 0.83 vs. 0.69, P<0.05). Moreover, the discrimination efficacy of the BRAIN score was significantly lower than the other 3 models (AUC of 0.71 in the training set, P<0.05). Conclusions:The clinical-semantic-radiomics combined model had the greatest potential for discriminating RHE, and significantly outperformed the classical BRAIN scoring system.

Andexanet Alfa for Reversal of Factor Xa Inhibitors in Intracranial Hemorrhage: Observational Cohort Study

“…Patients with ICH continue to bleed after the initial hemorrhage, known as hematoma expansion (HE) which is a well-established independent predictor of clinical deterioration [ 12 ]. HE represents a plausible therapeutic target in many clinical trials due to the characteristic of being potentially preventable and as such, is a very important outcome predictor [ 12 ].…”

“…Patients with ICH continue to bleed after the initial hemorrhage, known as hematoma expansion (HE) which is a well-established independent predictor of clinical deterioration [ 12 ]. HE represents a plausible therapeutic target in many clinical trials due to the characteristic of being potentially preventable and as such, is a very important outcome predictor [ 12 ]. HE is defined as a more than 33% increase in ICH volume within the first 24 h resulting in significant neurological deficits and enhancement of ICH-induced primary and secondary brain injury [ 13 ].…”

Efficacy of non-enhanced computer tomography-based radiomics for predicting hematoma expansion: A meta-analysis

“…Figure 4A presents a network plot of the indicators involved in the composition. In the NMA, 846 patients from five articles were included ( 4 , 6 , 7 , 21 , 22 ). The results synthesized according to Bayesian NMA revealed that the predictive ability of the radiomics model outperformed most of the NCCT biomarkers ( Figure 5 ).…”

“…Ten studies comprising a total of 1525 patients were quantitatively analyzed for hematoma expansion after cerebral hemorrhage using the radiomics method (4,6,7,(17)(18)(19)(20)(21)(22)(23). The pooled Se, Sp, PPV, NPV, and DAR were 0.771 (0.710-0.832), 0.743 (0.684-0.801), 0.612 (0.448-0.737), 0.863 (0.815-0.912), and 0.748 (0.707-0.788), respectively (Figure 3).…”

Combining Non-Contrast CT Signs With Onset-to-Imaging Time to Predict the Evolution of Intracerebral Hemorrhage

“…These compounds have extremely high potential for clinical applications. Various other technologies have also been used to predict hemorrhagic growth [ 26 27 ]. The performance of the radiomics model proposed by Xia et al [ 26 ] was significantly better than the NCCT signs obtained in our study.…”