Prediction of hematoma expansion in spontaneous intracerebral hemorrhage using support vector machine

Abstract

Background Spontaneous intracerebral hemorrhage (ICH) is a devastating disease with high mortality rate. This study aimed to predict hematoma expansion in spontaneous ICH from routinely available variables by using support vector machine (SVM) method. Methods We retrospectively reviewed 1157 patients with spontaneous ICH who underwent initial computed tomography (CT) scan within 6 h and follow-up CT scan within 72 h from symptom onset in our hospital between September 2013 and August 2018. Hematoma region was manually segmented at each slice to guarantee the measurement accuracy of hematoma volume. Hematoma expansion was defined as a proportional increase of hematoma volume > 33% or an absolute growth of hematoma volume > 6 mL from initial CT scan to follow-up CT scan. Univariate and multivariate analyses were performed to assess the association between clinical variables and hematoma expansion. SVM machine learning model was developed to predict hematoma expansion. Findings 246 of 1157 (21.3%) patients experienced hematoma expansion. Multivariate analyses revealed the following 6 independent factors associated with hematoma expansion: male patient (odds ratio [OR] = 1.82), time to initial CT scan (OR = 0.73), Glasgow Coma Scale (OR = 0.86), fibrinogen level (OR = 0.72), black hole sign (OR = 2.52), and blend sign (OR = 4.03). The SVM model achieved a mean sensitivity of 81.3%, specificity of 84.8%, overall accuracy of 83.3%, and area under receiver operating characteristic curve (AUC) of 0.89 in prediction of hematoma expansion. Interpretation The designed SVM model presented good performance in predicting hematoma expansion from routinely available variables. Fund This work was supported by , China, , China (LQ15H180002), the , China (Y20180112), Scientific Research Staring Foundation for the Returned Overseas Chinese Scholars of , and , China. The funders had no role in study design, data collection, data analysis, interpretation, writing of the report.

Inter- and Intrarater Agreement of Spot Sign and Noncontrast CT Markers for Early Intracerebral Hemorrhage Expansion

“…In conclusion, the high interrater and intrarater reliability suggests that all NCCT signs and SS are easy to use, thereby supporting their use in emerging scores and development and validation of machine learning tools to predict hematoma expansion, or either within randomized clinical or therapeutic trials targeting hematoma expansion [6,15,16,29].…”

Island Sign Predicts Hematoma Expansion and Poor Outcome After Intracerebral Hemorrhage: A Systematic Review and Meta-Analysis

“…Because HE is a very complex process involving numerous pathological processes, prediction models with multiple biomarkers or a combination of a single model are imperative. New developments in machine learning and big data may help to promote the development of NCCT imaging signs (30).…”

Association Between Eosinophilic Leukocyte Count and Hematoma Expansion in Acute Spontaneous Intracerebral Hemorrhage

“…The relative growth definition of >33% was used by many studies (3, 5, 21), since it could improve the detection rate of HE for ICH that presented with a small volume upon admission. In another prediction model, HE was defined as the combination of 6 mL and 33% increase (18), which was also widely applied in recent investigations (22–24). When using the absolute growth of >12.5 mL, the HE rate we observed was the lowest, consisting with the previous publication (4).…”