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

Machine learning for predicting hematoma expansion in spontaneous intracerebral hemorrhage: a systematic review and meta-analysis

PURPOSE

Early identification of hematoma enlargement and persistent hematoma expansion (HE) in patients with cerebral hemorrhage is increasingly crucial for determining clinical treatments. However, due to the lack of clinically effective tools, radiomics has been gradually introduced into the early identification of hematoma enlargement. Though, radiomics has limited predictive accuracy due to variations in procedures. Therefore, we conducted a systematic review and meta-analysis to explore the value of radiomics in the early detection of HE in patients with cerebral hemorrhage.

METHODS

Eligible studies were systematically searched in PubMed, Embase, Cochrane and Web of Science from inception to April 8, 2024. English articles are considered eligible. The radiomics quality scoring (RQS) tool was used to evaluate included studies.

RESULTS

A total of 34 studies were identified with sample sizes ranging from 108 to 3016. Eleven types of models were involved, and the types of modeling contained mainly clinical, radiomic, and radiomic plus clinical features. The radiomics models seem to have better performance (0.77 and 0.73 C-index in the training cohort and validation cohort, respectively) than the clinical models (0.69 C-index in the training cohort and 0.70 C-index in the validation cohort) in discriminating HE. However, the C-index was the highest for the combined model in both the training (0.82) and validation (0.79) cohorts.

CONCLUSIONS

Machine learning based on radiomic plus clinical features has the best predictive performance for HE, followed by machine learning based on radiomic features, and can be used as a potential tool to assist clinicians in early judgment.

Value of Image Biomarkers Based on Dual-Energy Computed Tomography Angiography Material Separation Technique in Predicting Early Hematoma Expansion in Spontaneous Intracerebral Hemorrhage

OBJECTIVE

This study aims to investigate the connection between the leakage sign (LS) and hematoma expansion (HE) in cases of spontaneous intracerebral hemorrhage. The investigation employs dual-energy computed tomography angiography (DECTA).

METHODS

A prospective cohort study was conducted, in which clinical and DECTA imaging data were collected from intracerebral hemorrhage patients within 6 hours of onset between January 2021 and June 2023. Exposure factors included DE-LS and traditional imaging biomarkers. The occurrence of HE on computed tomography rescanned within 24 hours was the observed outcome. Exposed and confounding factors were considered in both univariate and multivariate regression analyses based on the results. Logistic and adjusted Poisson regressions were employed, and odds ratios (ORs) and relative risks (RRs) were calculated with 95% confidence intervals.

RESULTS

The study enrolled a total of 90 patients, of whom 32 cases manifested HE, while 58 cases did not exhibit HE. Univariate analysis revealed statistically significant differences in parameters such as admission diastolic blood pressure, C-reactive protein, Glasgow Coma Scale, baseline hematoma volume, and imaging biomarkers like DE-spot sign and DE-LS. The OR value of DE-LS was determined as 48.21, with an RR value of 7.51. Multivariate adjusted Poisson regression analysis demonstrated that DE-LS was a robust independent predictor (RR = 4.11, 95% confidence interval: 1.49-11.35; P < 0.001).

CONCLUSIONS

DECTA-based DE-LS stands out as an independent predictor of HE. The utilization of RR values over OR values is endorsed when assessing the risk of HE prediction.