Abstract P427: Use of Machine Learning to Determine Predictors of Intracerebral Hemorrhage Expansion

• Published in: Stroke (1970) Vol. 52; no. Suppl_1; p. AP427
• Main Authors: Azher, Aidan I, Coronado, Ivan, Savitz, Sean I, Aronowski, Jaroslaw A, Salazar-Marioni, Sergio, Abdelkhaleq, Rania, Abdulrazzak, Mohammad Ammar, Greco, Jonathan, Sheth, Sunil, Giancardo, Luca
• Format: Journal Article
• Language: English
• Published: Lippincott Williams & Wilkins 01.03.2021
• ISSN: 0039-2499; 1524-4628
• DOI: 10.1161/str.52.suppl_1.P427

BackgroundIntracerebral hemorrhage (ICH) constitutes upto 40% mortality in first 30 days. Early identification of predictors of hematoma expansion (HE) may improve efforts to prevent its occurrence and improve clinical outcome. MethodsWe identified patients with ICH and follow-up imaging. HE was defined as a combination of absolute volume increase of 6cc, new IVH, or proportional increase of 33% in our dataset on 72h follow up scan. Presence of IVH was also included in hematoma expansion. We evaluated the predictive ability of 3 machine learning classifiers, Random Forest, Support Vector Machine (with RBF kernel) and Logistic regression (with L1 regularization). The evaluation was done using a K-fold stratified cross validation to avoid overfitting. K was selected to be the number of subjects with HE. The features employed by classifiers were entirely based on the baseline imagingHematoma volume, Systolic BP, Diastolic BP, Black hole signs, Island signs, Blend signs, Fluid level, Swirl signs, Spot signs. ResultsOur dataset comprised of 91 patients (n=21 HE, n=70 no HE). According to the area under the ROC (AUC), the two top performing classifiers were Support Vector Machine (AUC=0.66 CI 0.50-0.79) and Logistic Regression (AUC=0.64 CI 0.49-0.80). The statistical significance of the prediction is confirmed by the Mann-Whitney U test, p=0.01 and p=0.04 respectively. Random Forest did not reach statistical significance. Finally, we evaluated what were the highest and lowest weighted features across the cross-validation with Logistic Regression. The 3 top features werepresence of black hole and island signs and the systolic blood pressure. The 3 least useful features werepresence of spot and swirl signs and hematoma volume. ConclusionUsing our cohort, we developed a machine learning algorithm that predicts hematoma expansion using imaging features and blood pressure. MBL provided better sensitivity of these imaging markers compared with previous studies.