Predicting outcome after aneurysmal subarachnoid hemorrhage by exploitation of signal complexity: a prospective two-center cohort study.

BACKGROUND: Signal complexity (i.e. entropy) describes the level of order within a system. Low physiological signal complexity predicts unfavorable outcome in a variety of diseases and is assumed to reflect increased rigidity of the cardio/cerebrovascular system leading to (or reflecting) autoregulation failure. Aneurysmal subarachnoid hemorrhage (aSAH) is followed by a cascade of complex systemic and cerebral sequelae. In aSAH, the value of entropy has not been established yet. METHODS: aSAH patients from 2 prospective cohorts (Zurich-derivation cohort, Aachen-validation cohort) were included. Multiscale Entropy (MSE) was estimated for arterial blood pressure, intracranial pressure, heart rate, and their derivatives, and compared to dichotomized (1-4 vs. 5-8) or ordinal outcome (GOSE-extended Glasgow Outcome Scale) at 12 months using uni- and multivariable (adjusted for age, World Federation of Neurological Surgeons grade, modified Fisher (mFisher) grade, delayed cerebral infarction), and ordinal methods (proportional odds logistic regression/sliding dichotomy). The multivariable logistic regression models were validated internally using bootstrapping and externally by assessing the calibration and discrimination. RESULTS: A total of 330 (derivation: 241, validation: 89) aSAH patients were analyzed. Decreasing MSE was associated with a higher likelihood of unfavorable outcome independent of covariates and analysis method. The multivariable adjusted logistic regression models were well calibrated and only showed a slight decrease in discrimination when assessed in the validation cohort. The ordinal analysis revealed its effect to be linear. MSE remained valid when adjusting the outcome definition against the initial severity. CONCLUSIONS: MSE metrics and thereby complexity of physiological signals are independent, internally and externally valid predictors of 12-month outcome. Incorporating high-frequency physiological data as part of clinical outcome prediction may enable precise, individualized outcome prediction. The results of this study warrant further investigation into the cause of the resulting complexity as well as its association to important and potentially preventable complications including vasospasm and delayed cerebral ischemia.

Delayed Cerebral Infarction After Aneurysmal Subarachnoid Hemorrhage: Location, Distribution Patterns, Infarct Load, and Effect on Outcome.

BACKGROUND AND OBJECTIVES: Delayed cerebral ischemia (DCI) is one of the main contributing factors to poor clinical outcome after aneurysmal subarachnoid hemorrhage (SAH). Unsuccessful treatment can cause irreversible brain injury in the form of DCI-related infarction. We aimed to assess the association between the location, distribution, and size of DCI-related infarction in relation to clinical outcome. METHODS: Consecutive patients with SAH treated at 2 university hospitals between 2014 and 2019 (Helsinki, Finland) and between 2006 and 2020 (Aachen, Germany) were included. Size of DCI-related infarction was quantitatively measured as absolute volume (in milliliters). In a semiquantitative fashion, infarction in 14 regions of interest (ROIs) according to a modified Alberta Stroke Program Early CT Score (ASPECTS) was noted. The association of infarction in these ROIs along predefined regions of eloquent brain, with clinical outcome, was assessed. For this purpose, 1-year outcome was measured by the Glasgow Outcome Scale (GOS) and dichotomized into favorable (GOS 4-5) and unfavorable (GOS 1-3). RESULTS: Of 1,190 consecutive patients with SAH, 155 (13%) developed DCI-related infarction. One-year outcome data were available for 148 (96%) patients. A median overall infarct volume of 103 mL (interquartile range 31-237) was measured. DCI-related infarction was significantly associated with 1-year unfavorable outcome (odds ratio [OR] 4.89, 95% CI 3.36-7.34, p < 0.001). In patients with 1-year unfavorable outcome, vascular territories more frequently affected were left middle cerebral artery (affected in 49% of patients with unfavorable outcome vs in 30% of patients with favorable outcome; p = 0.029), as well as left (44% vs 18%; p = 0.003) and right (52% vs 14%; p < 0.001) anterior cerebral artery supply areas. According to the ASPECTS model, the right M3 (OR 8.52, 95% CI 1.41-51.34, p = 0.013) and right A2 (OR 7.84, 95% CI 1.97-31.15, p = 0.003) regions were independently associated with unfavorable outcome. DISCUSSION: DCI-related infarction was associated with a 5-fold increase in the odds of unfavorable outcome, after 1 year. Ischemic lesions in specific anatomical regions are more likely to contribute to unfavorable outcome. TRIAL REGISTRATION INFORMATION: Data collection in Aachen was registered in the German Clinical Trial Register (DRKS00030505); on January 3, 2023.

Intra-arterial nimodipine for the treatment of refractory delayed cerebral ischemia after aneurysmal subarachnoid hemorrhage.

BACKGROUND: Delayed cerebral ischemia (DCI) is one of the main contributors to poor clinical outcome after aneurysmal subarachnoid hemorrhage (SAH). Endovascular spasmolysis with intra-arterial nimodipine (IAN) may resolve angiographic vasospasm, but its effect on infarct prevention and clinical outcome is still unclear. We report the effect of IAN on infarction rates and functional outcome in a consecutive series of SAH patients. METHODS: To assess the effectiveness of IAN, we collected functional outcome data of all SAH patients referred to a single tertiary center since its availability (2011-2020). IAN was primarily reserved as a last tier option for DCI refractory to induced hypertension (iHTN). Functional outcome was assessed after 12 months according to the Glasgow Outcome Scale (GOS, favorable outcome = GOS4-5). RESULTS: Out of 376 consecutive SAH patients, 186 (49.5%) developed DCI. Thereof, a total of 96 (25.5%) patients remained unresponsive to iHTN and received IAN. DCI-related infarction was observed in 44 (45.8%) of IAN-treated patients with a median infarct volume of 111.6 mL (Q1: 51.6 to Q3: 245.7). Clinical outcome was available for 84 IAN-treated patients. Of those, a total of 40 (47.6%) patients reached a favorable outcome after 1 year. Interventional complications were observed in 9 (9.4%) of the IAN-treated patients. CONCLUSION: Intra-arterial spasmolysis using nimodipine infusion was associated with low treatment specific complications. Despite presenting a subgroup of severely affected SAH patients, almost half of IAN-treated patients were able to lead an independent life after 1 year of follow-up. TRIAL REGISTRATION NUMBER: German Clinical Trial Register DRKS00030505.

A generalizable physiological model for detection of Delayed Cerebral Ischemia using Federated Learning.

Delayed cerebral ischemia (DCI) is a complication seen in patients with subarachnoid hemorrhage stroke. It is a major predictor of poor outcomes and is detected late. Machine learning models are shown to be useful for early detection, however training such models suffers from small sample sizes due to rarity of the condition. Here we propose a Federated Learning approach to train a DCI classifier across three institutions to overcome challenges of sharing data across hospitals. We developed a framework for federated feature selection and built a federated ensemble classifier. We compared the performance of FL model to that obtained by training separate models at each site. FL significantly improved performance at only two sites. We found that this was due to feature distribution differences across sites. FL improves performance in sites with similar feature distributions, however, FL can worsen performance in sites with heterogeneous distributions. The results highlight both the benefit of FL and the need to assess dataset distribution similarity before conducting FL.