Identifying risk factors of intracerebral hemorrhage stability using explainable attention model.

Segmentation of intracerebral hemorrhage (ICH) helps improve the quality of diagnosis, draft the desired treatment methods, and clinically observe the variations with healthy patients. The clinical utilization of various ICH progression scoring systems has limitations due to the systems' modest predictive value. This paper proposes a single pipeline of a multi-task model for end-to-end hemorrhage segmentation and risk estimation. We introduce a 3D spatial attention unit and integrate it into the state-of-the-art segmentation architecture, UNet, to enhance the accuracy by bootstrapping the global spatial representation. We further extract the geometric features from the segmented hemorrhage volume and fuse them with clinical features such as CT angiography (CTA) spot, Glasgow Coma Scale (GCS), and age to predict the ICH stability. Several state-of-the-art machine learning techniques such as multilayer perceptron (MLP), support vector machine (SVM), gradient boosting, and random forests are applied to train stability estimation and to compare the performances. To align clinical intuition with model learning, we determine the shapely values (SHAP) and explain the most significant features for the ICH risk scoring system. A total of 79 patients are included, of which 20 are found in critical condition. Our proposed single pipeline model achieves a segmentation accuracy of 86.3%, stability prediction accuracy of 78.3%, and precision of 82.9%; the mean square error of exact expansion rate regression is observed to be 0.46. The SHAP analysis reveals that CTA spot sign, age, solidity, location, and length of the first axis of the ICH volume are the most critical characteristics that help define the stability of the stroke lesion. We also show that integrating significant geometric features with clinical features can improve the ICH progression scoring by predicting long-term outcomes. Graphical abstract Overview of our proposed method comprising of spatial attention and feature extraction mechanisms. The architecture is trained on the input CT images, and the first step output is the predicted segmentation of the hemorrhagic region. The output is fed into a geometric feature extractor and is fused with clinical features to estimate ICH stability using a multilayer perceptron (MLP).

External Validation of Hematoma Expansion Scores in Spontaneous Intracerebral Hemorrhage in an Asian Patient Cohort.

BACKGROUND: Hematoma expansion (HE) occurs in approximately one-third of patients with intracerebral hemorrhage (ICH) and is known to be a strong predictor of neurological deterioration as well as poor functional outcome. This study aims to externally validate three risk prediction models of HE (PREDICT, 9-point, and BRAIN scores) in an Asian population. METHODS: A prospective cohort of 123 spontaneous ICH patients admitted to a tertiary hospital (certified stroke center) in Singapore was recruited. Logistic recalibrations were performed to obtain updated calibration slopes and intercepts for all models. The discrimination (c-statistic), calibration (Hosmer-Lemeshow test, le Cessie-van Houwelingen-Copas-Hosmer test, Akaike information criterion), overall performance (Brier score, R2), and clinical usefulness (decision curve analysis) of the risk prediction models were examined. RESULTS: Overall, the recalibrated PREDICT performed best among the three models in our study cohort based on the novel matrix comprising of Akaike information criterion and c-statistic. The PREDICT model had the highest R2 (0.26) and lowest Brier score (0.14). Decision curve analyses showed that recalibrated PREDICT was more clinically useful than 9-point and BRAIN models over the greatest range of threshold probabilities. The two scores (PREDICT and 9-point) which incorporated computed tomography (CT) angiography spot sign outperformed the one without (BRAIN). CONCLUSIONS: To our knowledge, this is the first study to validate HE scores, namely PREDICT, 9-Point and BRAIN, in a multi-ethnic Asian ICH patient population. The PREDICT score was the best performing model in our study cohort, based on the performance metrics employed in this study. Our findings also showed support for CT angiography spot sign as a predictor of outcome after ICH. Although the models assessed are sufficient for risk stratification, the discrimination and calibration are at best moderate and could be improved.

Long-term recovery profile of patients with severe disability or in vegetative states following severe primary intracerebral hemorrhage.

PURPOSE: We conducted a single-center retrospective review to investigate the long-term recovery of patients who were severely disabled or vegetative secondary to primary intracerebral hemorrhage upon discharge from hospital from January 2009 to November 2013. METHODS: Patients were categorized into two groups based on their Glasgow outcome scale (GOS) scores at discharge, namely vegetative state (GOS 2; n = 91) and severely disabled (GOS 3; n = 278). Long-term outcomes at three years post discharge were defined as death, stable, deterioration and improvement from discharge to follow-up. RESULTS: Lower mortality (29% versus 69%) and higher neurological improvement rates at three years (33% versus 10%) were observed in the SD compared to VS group (both p = .0001). Age was a significant predictor of survival in the VS group (p = .03) and the SD group (p = .012). Age was also the only predictor of neurological improvement in the SD group (p = .01). CONCLUSIONS: Neurological status at discharge from hospital was not truly indicative of long-term prognosis for patients who were severely disabled or vegetative. Patients in both groups can potentially improve in the long term and may benefit from prolonged rehabilitation programmes to maximize their recovery potential.

Preclinical models of intracerebral hemorrhage: a translational perspective.

Intracerebral hemorrhage (ICH) is a devastating and relatively common disease affecting as many as 50,000 people annually in the United States alone. ICH remains associated with poor outcome, and approximately 40-50% of afflicted patients will die within 30 days. In reports from the NIH and AHA, the importance of developing clinically relevant models of ICH that will extend our understanding of the pathophysiology of the disease and target new therapeutic approaches was emphasized. Traditionally, preclinical ICH research has most commonly utilized two paradigms: clostridial collagenase-induced hemorrhage and autologous blood injection. In this article, the use of various species is examined in the context of the different model types for ICH, and a mechanistic approach is considered in evaluating the numerous breakthroughs in our current fund of knowledge. Each of the model types has its inherent strengths and weaknesses and has the potential to further our understanding of the pathophysiology and treatment of ICH. In particular, transgenic rodent models may be helpful in addressing genetic influences on recovery from ICH.