Predicting Delayed Cerebral Ischemia with Quantified Aneurysmal Subarachnoid Blood Volume

Integrating Clinical Data and Radiomics and Deep Learning Features for End-to-End Delayed Cerebral Ischemia Prediction on Noncontrast CT

BACKGROUND AND PURPOSE

Delayed cerebral ischemia is hard to diagnose early due to gradual, symptomless development. This study aimed to develop an automated model for predicting delayed cerebral ischemia following aneurysmal SAH on NCCT.

MATERIALS AND METHODS

This retrospective study included 400 patients with aneurysmal SAH (156 with delayed cerebral ischemia) who underwent NCCT. The study used ATT-Deeplabv3+ for automatically segmenting hemorrhagic regions using semisupervised learning. Principal component analysis was used for reducing the dimensionality of deep learning features extracted from the average pooling layer of ATT-DeepLabv3+. The classification model integrated clinical data, radiomics, and deep learning features to predict delayed cerebral ischemia. Feature selection involved Pearson correlation coefficients, least absolute shrinkage, and selection operator regression. We developed models based on clinical features, clinical-radiomics, and a combination of clinical, radiomics, and deep learning. The study selected logistic regression, Naive Bayes, Adaptive Boosting (AdaBoost), and multilayer perceptron as classifiers. The performance of segmentation and classification models was evaluated on their testing sets using the Dice similarity coefficient for segmentation, and the area under the receiver operating characteristic curve (AUC) and calibration curves for classification.

RESULTS

The segmentation process achieved a Dice similarity coefficient of 0.91 and the average time of 0.037 s/image. Seventeen features were selected to calculate the radiomics score. The clinical-radiomics-deep learning model with multilayer perceptron achieved the highest AUC of 0.84 (95% CI, 0.72-0.97), which outperformed the clinical-radiomics model (P = .002) and the clinical features model (P = .001) with multilayer perceptron. The performance of clinical-radiomics-deep learning model using AdaBoost was significantly superior to its clinical-radiomics model (P = .027). The performance of the clinical-radiomics-deep learning model and the clinical-radiomics model with logistic regression notably exceeded that of the model based solely on clinical features (P = .028; P = .046). The AUC of the clinical-radiomics-deep learning model with multilayer perceptron (P < .001) and the clinical-radiomics model with logistic regression (P = .046) were significantly higher than the clinical model with logistic regression. Of all models, the clinical-radiomics-deep learning model with multilayer perceptron showed best calibration.

CONCLUSIONS

The proposed 2-stage end-to-end model not only achieves rapid and accurate segmentation but also demonstrates superior diagnostic performance with high AUC values and good calibration in the clinical-radiomics-deep learning model, suggesting its potential to enhance delayed cerebral ischemia detection and treatment strategies.

Early localization of tissue at risk for delayed cerebral ischemia after aneurysmal subarachnoid hemorrhage: blood distribution on initial imaging vs early CT perfusion

OBJECTIVE

Delayed cerebral ischemia (DCI) is a potentially reversible adverse event after aneurysmal subarachnoid hemorrhage (aSAH), when early detected and treated. Computer tomography perfusion (CTP) is used to identify the tissue at risk for DCI. In this study, the predictive power of early CTP was compared with that of blood distribution on initial CT for localization of tissue at risk for DCI.

METHODS

A consecutive patient cohort with aSAH treated between 2012 and 2020 was retrospectively analyzed. Blood distribution on CT was semi-quantitatively assessed with the Hijdra-score. The vessel territory with the most surrounding blood and the one with perfusion deficits on CTP performed on day 3 after ictus were considered to be at risk for DCI, respectively.

RESULTS

A total of 324 patients were included. Delayed infarction occurred in 17% (56/324) of patients. Early perfusion deficits were detected in 82% (46/56) of patients, 85% (39/46) of them developed infarction within the predicted vessel territory at risk. In 46% (25/56) a vessel territory at risk was reliably determined by the blood distribution. For the prediction of DCI, blood amount/distribution was inferior to CTP. Concerning the identification of "tissue at risk" for DCI, a combination of both methods resulted in an increase of sensitivity to 64%, positive predictive value to 58%, and negative predictive value to 92%.

CONCLUSIONS

Regarding the DCI-prediction, early CTP was superior to blood amount/distribution, while a consideration of subarachnoid blood distribution may help identify the vessel territories at risk for DCI in patients without early perfusion deficits.

Sex-Related Differences in Mortality, Delayed Cerebral Ischemia, and Functional Outcomes in Patients with Aneurysmal Subarachnoid Hemorrhage: A Systematic Review and Meta-Analysis

Background/Objective: Sex-related differences among patients with aneurysmal subarachnoid hemorrhage (aSAH) and their potential clinical implications have been insufficiently investigated. To address this knowledge gap, we conduct a comprehensive systematic review and meta-analysis. Methods: Sex-specific differences in patients with aSAH, including mortality, delayed cerebral ischemia (DCI), and functional outcomes were assessed. The functional outcome was dichotomized into favorable or unfavorable based on the modified Rankin Scale (mRS), Glasgow Outcome Scale (GOS), and Glasgow Outcome Scale Extended (GOSE). Results: Overall, 2823 studies were identified in EMBASE, MEDLINE, PubMed, and by manual search on 14 February 2024. After an initial assessment, 74 studies were included in the meta-analysis. In the analysis of mortality, including 18,534 aSAH patients, no statistically significant differences could be detected (risk ratio (RR) 0.99; 95% CI, 0.90-1.09; p = 0.91). In contrast, the risk analysis for DCI, including 23,864 aSAH patients, showed an 11% relative risk reduction in DCI in males versus females (RR, 0.89; 95% CI, 0.81-0.97; p = 0.01). The functional outcome analysis (favorable vs. unfavorable), including 7739 aSAH patients, showed a tendency towards better functional outcomes in men than women; however, this did not reach statistical significance (RR, 1.02; 95% CI, 0.98-1.07; p = 0.34). Conclusions: In conclusion, the available data suggest that sex/gender may play a significant role in the risk of DCI in patients with aSAH, emphasizing the need for sex-specific management strategies.

Pharmacological Prevention of Delayed Cerebral Ischemia in Aneurysmal Subarachnoid Hemorrhage

BACKGROUND

Causes of morbidity and mortality following aneurysmal subarachnoid hemorrhage (aSAH) include early brain injury and delayed neurologic deterioration, which may result from delayed cerebral ischemia (DCI). Complex pathophysiological mechanisms underlie DCI, which often includes angiographic vasospasm (aVSP) of cerebral arteries.

METHODS

Despite the study of many pharmacological therapies for the prevention of DCI in aSAH, nimodipine-a dihydropyridine calcium channel blocker-remains the only drug recommended universally in this patient population. A common theme in the research of preventative therapies is the use of promising drugs that have been shown to reduce the occurrence of aVSP but ultimately did not improve functional outcomes in large, randomized studies. An example of this is the endothelin antagonist clazosentan, although this agent was recently approved in Japan.

RESULTS

The use of the only approved drug, nimodipine, is limited in practice by hypotension. The administration of nimodipine and its counterpart nicardipine by alternative routes, such as intrathecally or formulated as prolonged release implants, continues to be a rational area of study. Additional agents approved in other parts of the world include fasudil and tirilazad.

CONCLUSIONS

We provide a brief overview of agents currently being studied for prevention of aVSP and DCI after aSAH. Future studies may need to identify subpopulations of patients who can benefit from these drugs and perhaps redefine acceptable outcomes to demonstrate impact.

Proposed imaging assessment score for aneurysmal subarachnoid hemorrhage correlated with prognosis: Shinshu Aneurysmal subarachnoid hemorrhage score

BACKGROUND

Aneurysmal subarachnoid hemorrhage (aSAH) imaging has been shown to correlate with prognosis. However, no numerical index of bleeding severity has been established. This study aimed to propose a new simple scoring system for computed tomography imaging of aSAH and to confirm its effectiveness in retrospective and prospective studies.

METHODS

We devised an image evaluation system as an objective index. This system was established by scoring six items, with a maximum total of 19 points. Using this score, named the Shinshu Aneurysmal Subarachnoid Hemorrhage Score (S-score), we performed a retrospective study of 210 patients with aSAH at a single institution to confirm its efficacy. Age and World Federation of Neurosurgical Societies grades were adopted as other verification items, and the modified Rankin Scale was used for prognostic evaluation. A multicenter prospective study was then conducted to examine the function of the score by examining 214 patients with aSAH.

RESULTS

In the retrospective study, the threshold of the S-score between good and poor prognoses was 9/19 points. The area under the curve by receiver operating characteristic analysis of the S-score was 0.819, suggesting efficacy, with an odds ratio (OR) of 1.291 (1.077-1.547). In the prospective study, the judgment capability of the S-score was evaluated with a sensitivity of 0.674, specificity of 0.881, positive predictive value of 0.789, negative predictive value of 0.804, false-positive ratio of 0.119, false-negative ratio of 0.325, positive likelihood ratio of 6.072, and negative likelihood ratio of 1.369. S-score showed a significant difference in prognosis. The OR was 1.183 (1.009-1.388).

CONCLUSIONS

The scoring system could contribute to patient prognosis assessment. S-score and its prognostic formulas may serve as an objective source of information in the development of clinical medicine.

Artificial intelligence and machine learning in aneurysmal subarachnoid hemorrhage: Future promises, perils, and practicalities

INTRODUCTION

Aneurysmal subarachnoid hemorrhage (SAH) is a subtype of hemorrhagic stroke with thirty-day mortality as high as 40%. Given the expansion of Machine Learning (ML) and Artificial intelligence (AI) methods in health care, SAH patients desperately need an integrated AI system that detects, segments, and supports clinical decisions based on presentation and severity.

OBJECTIVES

This review aims to synthesize the current state of the art of AI and ML tools for the management of SAH patients alongside providing an up-to-date account of future horizons in patient care.

METHODS

We performed a systematic review through various databases such as Cochrane Central Register of Controlled Trials, MEDLINE, Scopus, Cochrane Database of Systematic Reviews, and Embase.

RESULTS

A total of 507 articles were identified. Following extensive revision, only 21 articles were relevant. Two studies reported improved mortality prediction using Glasgow Coma Scale and biomarkers such as Neutrophil to Lymphocyte Ratio and glucose. One study reported that ffANN is equal to the SAHIT and VASOGRADE scores. One study reported that metabolic biomarkers Ornithine, Symmetric Dimethylarginine, and Dimethylguanidine Valeric acid were associated with poor outcomes. Nine studies reported improved prediction of complications and reduction in latency until intervention using clinical scores and imaging. Four studies reported accurate prediction of aneurysmal rupture based on size, shape, and CNN. One study reported AI-assisted Robotic Transcranial Doppler as a substitute for clinicians.

CONCLUSION

AI/ML technologies possess tremendous potential in accelerating SAH systems-of-care. Keeping abreast of developments is vital in advancing timely interventions for critical diseases.

Comparison of Conventional Logistic Regression and Machine Learning Methods for Predicting Delayed Cerebral Ischemia After Aneurysmal Subarachnoid Hemorrhage: A Multicentric Observational Cohort Study

Background

Timely and accurate prediction of delayed cerebral ischemia is critical for improving the prognosis of patients with aneurysmal subarachnoid hemorrhage. Machine learning (ML) algorithms are increasingly regarded as having a higher prediction power than conventional logistic regression (LR). This study aims to construct LR and ML models and compare their prediction power on delayed cerebral ischemia (DCI) after aneurysmal subarachnoid hemorrhage (aSAH).

Methods

This was a multicenter, retrospective, observational cohort study that enrolled patients with aneurysmal subarachnoid hemorrhage from five hospitals in China. A total of 404 aSAH patients were prospectively enrolled. We randomly divided the patients into training (N = 303) and validation cohorts (N = 101) according to a ratio of 75–25%. One LR and six popular ML algorithms were used to construct models. The area under the receiver operating characteristic curve (AUC), accuracy, balanced accuracy, confusion matrix, sensitivity, specificity, calibration curve, and Hosmer–Lemeshow test were used to assess and compare the model performance. Finally, we calculated each feature of importance.

Results

A total of 112 (27.7%) patients developed DCI. Our results showed that conventional LR with an AUC value of 0.824 (95%CI: 0.73–0.91) in the validation cohort outperformed k-nearest neighbor, decision tree, support vector machine, and extreme gradient boosting model with the AUCs of 0.792 (95%CI: 0.68–0.9, P = 0.46), 0.675 (95%CI: 0.56–0.79, P < 0.01), 0.677 (95%CI: 0.57–0.77, P < 0.01), and 0.78 (95%CI: 0.68–0.87, P = 0.50). However, random forest (RF) and artificial neural network model with the same AUC (0.858, 95%CI: 0.78–0.93, P = 0.26) were better than the LR. The accuracy and the balanced accuracy of the RF were 20.8% and 11% higher than the latter, and the RF also showed good calibration in the validation cohort (Hosmer-Lemeshow: P = 0.203). We found that the CT value of subarachnoid hemorrhage, WBC count, neutrophil count, CT value of cerebral edema, and monocyte count were the five most important features for DCI prediction in the RF model. We then developed an online prediction tool (https://dynamic-nomogram.shinyapps.io/DynNomapp-DCI/) based on important features to calculate DCI risk precisely.

Conclusions

In this multicenter study, we found that several ML methods, particularly RF, outperformed conventional LR. Furthermore, an online prediction tool based on the RF model was developed to identify patients at high risk for DCI after SAH and facilitate timely interventions.

Clinical Trial Registration

http://www.chictr.org.cn, Unique identifier: ChiCTR2100044448.

The influence of aneurysm morphology on the volume of hemorrhage after rupture

OBJECTIVE

Factors determining the risk of rupture of intracranial aneurysms have been extensively studied; however, little attention is paid to variables influencing the volume of bleeding after rupture. In this study the authors aimed to evaluate the impact of aneurysm morphological variables on the amount of hemorrhage.

METHODS

This was a retrospective cohort analysis of a prospectively collected data set of 116 patients presenting at a single center with subarachnoid hemorrhage due to aneurysmal rupture. A volumetric assessment of the total hemorrhage volume was performed from the initial noncontrast CT. Aneurysms were segmented and reproduced from the initial CT angiography study, and morphology indexes were calculated with a computer-assisted approach. Clinical and demographic characteristics of the patients were included in the study. Factors influencing the volume of hemorrhage were explored with univariate correlations, multiple linear regression analysis, and graphical probabilistic modeling.

RESULTS

The univariate analysis demonstrated that several of the morphological variables but only the patient's age from the clinical-demographic variables correlated (p < 0.05) with the volume of bleeding. Nine morphological variables correlated positively (absolute height, perpendicular height, maximum width, sac surface area, sac volume, size ratio, bottleneck factor, neck-to-vessel ratio, and width-to-vessel ratio) and two correlated negatively (parent vessel average diameter and the aneurysm angle). After multivariate analysis, only the aneurysm size ratio (p < 0.001) and the patient's age (p = 0.023) remained statistically significant. The graphical probabilistic model confirmed the size ratio and the patient's age as the variables most related to the total hemorrhage volume.

CONCLUSIONS

A greater aneurysm size ratio and an older patient age are likely to entail a greater volume of bleeding after subarachnoid hemorrhage.

Lessons from the CONSCIOUS-1 Study

After years of research on treatment of aneurysmal subarachnoid hemorrhage (aSAH), including randomized clinical trials, few treatments have been shown to be efficacious. Nevertheless, reductions in morbidity and mortality have occurred over the last decades. Reasons for the improved outcomes remain unclear. One randomized clinical trial that has been examined in detail with these questions in mind is Clazosentan to Overcome Neurological Ischemia and Infarction Occurring After Subarachnoid Hemorrhage (CONSCIOUS-1). This was a phase-2 trial testing the effect of clazosentan on angiographic vasospasm (aVSP) in patients with aSAH. Clazosentan decreased moderate to severe aVSP. There was no statistically significant effect on the extended Glasgow outcome score (GOS), although the study was not powered for this endpoint. Data from the approximately 400 patients in the study were detailed, rigorously collected and documented and were generously made available to one investigator. Post-hoc analyses were conducted which have expanded our knowledge of the management of aSAH. We review those analyses here.