Machine Learning Analysis of Matricellular Proteins and Clinical Variables for Early Prediction of Delayed Cerebral Ischemia After Aneurysmal Subarachnoid Hemorrhage. Mol Neurobiol. 2019;56:7128-7135. [PMID: 30989629 DOI: 10.1007/s12035-019-1601-7]

Impact Exploration of Spatiotemporal Feature Derivation and Selection on Machine Learning-Based Predictive Models for Post-Embolization Cerebral Aneurysm Recanalization

PURPOSE

To enhance the performance of machine learning (ML) models for the post-embolization recanalization of cerebral aneurysms, we evaluated the impact of hemodynamic feature derivation and selection method on six ML algorithms.

METHODS

We utilized computational fluid dynamics (CFD) to simulate hemodynamics in 66 cerebral aneurysms from 65 patients, including 57 stable and nine recanalized aneurysms. We derived a total of 107 features for each aneurysm, encompassing four clinical features, 12 morphological features, and 91 hemodynamic features. To investigate the influence of feature derivation and selection methods on the ML models, we employed two derivation methods, simplified and fully derived, in combination with four selection methods: all features, statistically significant analysis, stepwise multivariate logistic regression analysis (stepwise-LR), and recursive feature elimination (RFE). Model performance was assessed using the area under the receiver operating characteristic curve (AUROC) and precision-recall curve (AUPRC) on both the training and testing datasets.

RESULTS

The AUROC values on the testing dataset exhibited a wide-ranging spectrum, spanning from 0.373 to 0.863. Fully derived features and the RFE selection method demonstrated superior performance in intra-model comparisons. The multi-layer perceptron (MLP) model, trained with RFE-selected fully derived features, achieved the best performance on the testing dataset, with an AUROC value of 0.863 (95% CI: 0.684- 1.000).

CONCLUSION

Our study demonstrated the importance of feature derivation and selection in determining the performance of ML models. This enabled the development of accurate decision-making models without the need to invade the patient.

Galectin-3 modulates microglial activation and neuroinflammation in early brain injury after subarachnoid hemorrhage

BACKGROUND

Aneurysmal subarachnoid hemorrhage (SAH) is a devastating acute cerebrovascular event with high mortality and permanent disability rates. Higher galectin-3 levels on days 1-3 have been shown to predict the development of delayed cerebral infarction or adverse outcomes after SAH. Recent single-cell analysis of microglial transcriptomic diversity in SAH revealed that galectin could influence the development and course of neuroinflammation after SAH.

METHODS

This study aimed to investigate the role and mechanism of galectin-3 in SAH and to determine whether galectin-3 inhibition prevents early brain injury by reducing microglia polarization using a mouse model of SAH and oxyhemoglobin-treated activation of mouse BV2 cells in vitro.

RESULTS

We found that the expression of galectin-3 began to increase 12 h after SAH and continued to increase up to 72 h. Importantly, TD139-inhibited galectin-3 expression reduced the release of inflammatory factors in microglial cells. In the experimental SAH model, TD139 treatment alleviated neuroinflammatory damage after SAH and improved defects in neurological functions. Furthermore, we demonstrated that galectin-3 inhibition affected the activation and M1 polarization of microglial cells after SAH. TD139 treatment inhibited the expression of TLR4, p-NF-κB p65, and NF-κB p65 in microglia activated by oxyhemoglobin as well as eliminated the increased expression and phosphorylation of JAK2 and STAT3.

CONCLUSION

These findings suggest that regulating microglia polarization by galectin-3 after SAH to improve neuroinflammation may be a potential therapeutic target.

Machine learning predicts cerebral vasospasm in patients with subarachnoid haemorrhage

BACKGROUND

Cerebral vasospasm (CV) is a feared complication which occurs after 20-40% of subarachnoid haemorrhage (SAH). It is standard practice to admit patients with SAH to intensive care for an extended period of resource-intensive monitoring. We used machine learning to predict CV requiring verapamil (CVRV) in the largest and only multi-center study to date.

METHODS

Patients with SAH admitted to UCLA from 2013 to 2022 and a validation cohort from VUMC from 2018 to 2023 were included. For each patient, 172 unique intensive care unit (ICU) variables were extracted through the primary endpoint, namely first verapamil administration or no verapamil. At each institution, a light gradient boosting machine (LightGBM) was trained using five-fold cross validation to predict the primary endpoint at various hospitalization timepoints.

FINDINGS

A total of 1750 patients were included from UCLA, 125 receiving verapamil. LightGBM achieved an area under the ROC (AUC) of 0.88 > 1 week in advance and ruled out 8% of non-verapamil patients with zero false negatives. Our models predicted "no CVRV" vs "CVRV within three days" vs "CVRV after three days" with AUCs = 0.88, 0.83, and 0.88, respectively. From VUMC, 1654 patients were included, 75 receiving verapamil. VUMC predictions averaged within 0.01 AUC points of UCLA predictions.

INTERPRETATION

We present an accurate and early predictor of CVRV using machine learning with multi-center validation. This represents a significant step towards optimized clinical management and resource allocation in patients with SAH.

FUNDING

Robert E. Freundlich is supported by National Center for Advancing Translational Sciences federal grant UL1TR002243 and National Heart, Lung, and Blood Institute federal grant K23HL148640; these funders did not play any role in this study. The National Institutes of Health supports Vanderbilt University Medical Center which indirectly supported these research efforts. Neither this study nor any other authors personally received financial support for the research presented in this manuscript. No support from pharmaceutical companies was received.

Machine Learning Algorithms to Predict Delayed Cerebral Ischemia After Subarachnoid Hemorrhage: A Systematic Review and Meta-analysis

Delayed cerebral ischemia (DCI) is a common and severe complication after subarachnoid hemorrhage (SAH). Logistic regression (LR) is the primary method to predict DCI, but it has low accuracy. This study assessed whether other machine learning (ML) models can predict DCI after SAH more accurately than conventional LR. PubMed, Embase, and Web of Science were systematically searched for studies directly comparing LR and other ML algorithms to forecast DCI in patients with SAH. Our main outcome was the accuracy measurement, represented by sensitivity, specificity, and area under the receiver operating characteristic. In the six studies included, comprising 1828 patients, about 28% (519) developed DCI. For LR models, the pooled sensitivity was 0.71 (95% confidence interval [CI] 0.57-0.84; p < 0.01) and the pooled specificity was 0.63 (95% CI 0.42-0.85; p < 0.01). For ML models, the pooled sensitivity was 0.74 (95% CI 0.61-0.86; p < 0.01) and the pooled specificity was 0.78 (95% CI 0.71-0.86; p = 0.02). Our results suggest that ML algorithms performed better than conventional LR at predicting DCI.Trial Registration: PROSPERO (International Prospective Register of Systematic Reviews) CRD42023441586; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=441586.

Predicting who has delayed cerebral ischemia after aneurysmal subarachnoid hemorrhage using machine learning approach: a multicenter, retrospective cohort study

BACKGROUND

Early prediction of delayed cerebral ischemia (DCI) is critical to improving the prognosis of aneurysmal subarachnoid hemorrhage (aSAH). Machine learning (ML) algorithms can learn from intricate information unbiasedly and facilitate the early identification of clinical outcomes. This study aimed to construct and compare the ability of different ML models to predict DCI after aSAH. Then, we identified and analyzed the essential risk of DCI occurrence by preoperative clinical scores and postoperative laboratory test results.

METHODS

This was a multicenter, retrospective cohort study. A total of 1039 post-operation patients with aSAH were finally included from three hospitals in China. The training group contained 919 patients, and the test group comprised 120 patients. We used five popular machine-learning algorithms to construct the models. The area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, precision, and f1 score were used to evaluate and compare the five models. Finally, we performed a Shapley Additive exPlanations analysis for the model with the best performance and significance analysis for each feature.

RESULTS

A total of 239 patients with aSAH (23.003%) developed DCI after the operation. Our results showed that in the test cohort, Random Forest (RF) had an AUC of 0.79, which was better than other models. The five most important features for predicting DCI in the RF model were the admitted modified Rankin Scale, D-Dimer, intracranial parenchymal hematoma, neutrophil/lymphocyte ratio, and Fisher score. Interestingly, clamping or embolization for the aneurysm treatment was the fourth button-down risk factor in the ML model.

CONCLUSIONS

In this multicenter study, we compared five ML methods, among which RF performed the best in DCI prediction. In addition, the essential risks were identified to help clinicians monitor the patients at high risk for DCI more precisely and facilitate timely intervention.

Advances in biomarkers for vasospasm - Towards a future blood-based diagnostic test

Objective

Cerebral vasospasm and the resultant delayed cerebral infarction is a significant source of mortality following aneurysmal SAH. Vasospasm is currently detected using invasive or expensive imaging at regular intervals in patients following SAH, thus posing a risk of complications following the procedure and financial burden on these patients. Currently, there is no blood-based test to detect vasospasm.

Methods

PubMed, Web of Science, and Embase databases were systematically searched to retrieve studies related to cerebral vasospasm, aneurysm rupture, and biomarkers. The study search dated from 1997 to 2022. Data from eligible studies was extracted and then summarized.

Results

Out of the 632 citations screened, only 217 abstracts were selected for further review. Out of those, only 59 full text articles met eligibility and another 13 were excluded.

Conclusions

We summarize the current literature on the mechanism of cerebral vasospasm and delayed cerebral ischemia, specifically studies relating to inflammation, and provide a rationale and commentary on a hypothetical future bloodbased test to detect vasospasm. Efforts should be focused on clinical-translational approaches to create such a test to improve treatment timing and prediction of vasospasm to reduce the incidence of delayed cerebral infarction.

Anti-Apoptotic Effects of AMPA Receptor Antagonist Perampanel in Early Brain Injury After Subarachnoid Hemorrhage in Mice

This study was aimed to investigate if acute neuronal apoptosis is induced by activation of AMPA (α-amino-3-hydroxy-5-methyl-4-isoxazole propionate) receptors (AMPARs) and inhibited by a clinically available selective AMPAR antagonist and antiepileptic drug perampanel (PER) in subarachnoid hemorrhage (SAH), and if the mechanisms include upregulation of an inflammation-related matricellular protein periostin. Sham-operated and endovascular perforation SAH mice randomly received an administration of 3 mg/kg PER or the vehicle intraperitoneally. Post-SAH neurological impairments and increased caspase-dependent neuronal apoptosis were associated with activation of AMPAR subunits GluA1 and GluA2, and upregulation of periostin and proinflammatory cytokines interleukins-1β and -6, all of which were suppressed by PER. PER also inhibited post-SAH convulsion-unrelated increases in the total spectral power on video electroencephalogram (EEG) monitoring. Intracerebroventricularly injected recombinant periostin blocked PER's anti-apoptotic effects on neurons. An intracerebroventricular injection of a selective agonist for GluA1 and GluA2 aggravated neurological impairment, neuronal apoptosis as well as periostin upregulation, but did not increase the EEG total spectral power after SAH. A higher dosage (10 mg/kg) of PER had even more anti-apoptotic effects compared with 3 mg/kg PER. Thus, this study first showed that AMPAR activation causes post-SAH neuronal apoptosis at least partly via periostin upregulation. A clinically available AMPAR antagonist PER appears to be neuroprotective against post-SAH early brain injury through the anti-inflammatory and anti-apoptotic effects, independent of the antiepileptic action, and deserves further study.

Machine Learning Predicts Cerebral Vasospasm in Subarachnoid Hemorrhage Patients

Background

Cerebral vasospasm (CV) is a feared complication occurring in 20-40% of patients following subarachnoid hemorrhage (SAH) and is known to contribute to delayed cerebral ischemia. It is standard practice to admit SAH patients to intensive care for an extended period of vigilant, resource-intensive, clinical monitoring. We used machine learning to predict CV requiring verapamil (CVRV) in the largest and only multi-center study to date.

Methods

SAH patients admitted to UCLA from 2013-2022 and a validation cohort from VUMC from 2018-2023 were included. For each patient, 172 unique intensive care unit (ICU) variables were extracted through the primary endpoint, namely first verapamil administration or ICU downgrade. At each institution, a light gradient boosting machine (LightGBM) was trained using five- fold cross validation to predict the primary endpoint at various timepoints during hospital admission. Receiver-operator curves (ROC) and precision-recall (PR) curves were generated.

Results

A total of 1,750 patients were included from UCLA, 125 receiving verapamil. LightGBM achieved an area under the ROC (AUC) of 0.88 an average of over one week in advance, and successfully ruled out 8% of non-verapamil patients with zero false negatives. Minimum leukocyte count, maximum platelet count, and maximum intracranial pressure were the variables with highest predictive accuracy. Our models predicted "no CVRV" vs "CVRV within three days" vs "CVRV after three days" with AUCs=0.88, 0.83, and 0.88, respectively. For external validation at VUMC, 1,654 patients were included, 75 receiving verapamil. Predictive models at VUMC performed very similarly to those at UCLA, averaging 0.01 AUC points lower.

Conclusions

We present an accurate (AUC=0.88) and early (>1 week prior) predictor of CVRV using machine learning over two large cohorts of subarachnoid hemorrhage patients at separate institutions. This represents a significant step towards optimized clinical management and improved resource allocation in the intensive care setting of subarachnoid hemorrhage patients.

Accurately predicting the risk of unfavorable outcomes after endovascular coil therapy in patients with aneurysmal subarachnoid hemorrhage: an interpretable machine learning model

BACKGROUND

Despite endovascular coiling as a valid modality in treatment of aneurysmal subarachnoid hemorrhage (aSAH), there is a risk of poor prognosis. However, the clinical utility of previously proposed early prediction tools remains limited. We aimed to develop a clinically generalizable machine learning (ML) models for accurately predicting unfavorable outcomes in aSAH patients after endovascular coiling.

METHODS

Functional outcomes at 6 months after endovascular coiling were assessed via the modified Rankin Scale (mRS) and unfavorable outcomes were defined as mRS 3-6. Five ML algorithms (logistic regression, random forest, support vector machine, deep neural network, and extreme gradient boosting) were used for model development. The area under precision-recall curve (AUPRC) and receiver operating characteristic curve (AUROC) was used as main indices of model evaluation. SHapley Additive exPlanations (SHAP) method was applied to interpret the best-performing ML model.

RESULTS

A total of 371 patients were eventually included into this study, and 85.4% of them had favorable outcomes. Among the five models, the DNN model had a better performance with AUPRC of 0.645 (AUROC of 0.905). Postoperative GCS score, size of aneurysm, and age were the top three powerful predictors. The further analysis of five random cases presented the good interpretability of the DNN model.

CONCLUSION

Interpretable clinical prediction models based on different ML algorithms have been successfully constructed and validated, which would serve as reliable tools in optimizing the treatment decision-making of aSAH. Our DNN model had better performance to predict the unfavorable outcomes at 6 months in aSAH patients compared with Yan's nomogram model.

Fluid dynamic analysis in predicting the recanalization of intracranial aneurysms after coil embolization - A study of spatiotemporal characteristics

Purpose

Hemodynamics play a key role in the management of cerebral aneurysm recanalization after coil embolization; however, the most reliable hemodynamic parameter remains unknown. Previous studies have explored the use of both spatiotemporally averaged and maximal definitions for hemodynamic parameters, based on computational fluid dynamics (CFD) analysis, to build predictive models for aneurysmal recanalization. In this study, we aimed to assess the influence of different spatiotemporal characteristics of hemodynamic parameters on predictive performance.

Methods

Hemodynamics were simulated using CFD for 66 cerebral aneurysms from 65 patients. We evaluated 14 types of spatiotemporal definitions for two hemodynamic parameters in the pre-coiling model and five in virtual post-coiling model (VM) created by cutting the aneurysm from the pre-coiling model. A total of 91 spatiotemporal hemodynamic features were derived and utilized to develop univariate predictor (UP) and multivariate logistic regression (LR) models. The model's performance was assessed using two metrics: the area under the receiver operating characteristic curve (AUROC) and the area under the precision-recall curve (AUPRC).

Results

Different spatiotemporal hemodynamic features exhibited a wide range of AUROC values ranging from 0.224 to 0.747, with 22 feature pairs showing a significant difference in AUROC value (P-value <0.05), despite being derived from the same hemodynamic parameter. PDave,q1 was identified as the strongest UP with AUROC/AUPRC values of 0.747/0.385, yielding sensitivity and specificity value of 0.889 and 0.614 at the optimal cut-off value, respectively. The LR model further improved the prediction performance, having AUROC/AUPRC values of 0.890/0.903. At the optimal cut-off value, the LR model achieved a specificity of 0.877, sensitivity of 0.719, outperforming the UP model.

Conclusion

Our research indicated that the characteristics of hemodynamic parameters in terms of space and time had a significant impact on the development of predictive model. Our findings suggest that LR model based on spatiotemporal hemodynamic features could be clinically useful in predicting recanalization after coil embolization in patients, without the need for invasive procedures.

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.

Effect of Cilostazol on Delayed Cerebral Infarction in Aneurysmal Subarachnoid Hemorrhage Using Explainable Predictive Modeling

The studies interpreting DCI, a complication of SAH, and identifying correlations are very limited. This study aimed to investigate the effect of cilostazol on ACV and DCI after coil embolization for ruptured aneurysms (n = 432). A multivariate analysis was performed and explainable artificial intelligence approaches were used to analyze the contribution of cilostazol as a risk factor on the development of ACV and DCI with respect to global and local interpretation. The cilonimo group was significantly lower than the nimo group in ACV (13.5% vs. 29.3; p = 0.003) and DCI (7.9% vs. 20.7%; p = 0.006), respectively. In a multivariate logistic regression, the odds ratio for DCI for the cilonimo group, female sex, and aneurysm size was 0.556 (95% confidence interval (CI), 0.351-0.879; p = 0.012), 3.713 (95% CI, 1.683-8.191; p = 0.001), and 1.106 (95% CI, 1.008-1.214; p = 0.034). The risk of a DCI occurrence was significantly increased with an aneurysm size greater than 10 mm (max 80%). The mean AUC of the XGBoost and logistic regression models was 0.94 ± 0.03 and 0.95 ± 0.04, respectively. Cilostazol treatment combined with nimodipine could decrease the prevalence of ACV (13.5%) and DCI (7.9%) in patients with aSAH.

Crossing the AI Chasm in Neurocritical Care

Despite the growing interest in possible applications of computer science and artificial intelligence (AI) in the field of neurocritical care (neuro-ICU), widespread clinical applications are still missing. In neuro-ICU, the collection and analysis in real time of large datasets can play a crucial role in advancing this medical field and improving personalized patient care. For example, AI algorithms can detect subtle changes in brain activity or vital signs, alerting clinicians to potentially life-threatening conditions and facilitating rapid intervention. Consequently, data-driven AI and predictive analytics can greatly enhance medical decision making, diagnosis, and treatment, ultimately leading to better outcomes for patients. Nevertheless, there is a significant disparity between the current capabilities of AI systems and the potential benefits and applications that could be achieved with more advanced AI technologies. This gap is usually indicated as the AI chasm. In this paper, the underlying causes of the AI chasm in neuro-ICU are analyzed, along with proposed recommendations for utilizing AI to attain a competitive edge, foster innovation, and enhance patient outcomes. To bridge the AI divide in neurocritical care, it is crucial to foster collaboration among researchers, clinicians, and policymakers, with a focus on specific use cases. Additionally, strategic investments in AI technology, education and training, and infrastructure are needed to unlock the potential of AI technology. Before implementing a technology in patient care, it is essential to conduct thorough studies and establish clinical validation in real-world environments to ensure its effectiveness and safety. Finally, the development of ethical and regulatory frameworks is mandatory to ensure the secure and efficient deployment of AI technology throughout the process.

Plasma SPARC Elevation in Delayed Cerebral Ischemia After Aneurysmal Subarachnoid Hemorrhage

Matricellular proteins have been implicated in pathologies after subarachnoid hemorrhage (SAH). To find a new therapeutic molecular target, the present study aimed to clarify the relationships between serially measured plasma levels of a matricellular protein, secreted protein acidic and rich in cysteine (SPARC), and delayed cerebral ischemia (DCI) in 117 consecutive aneurysmal SAH patients with admission World Federation of Neurological Surgeons (WFNS) grades I-III. DCI developed in 25 patients with higher incidences of past history of hypertension and dyslipidemia, preoperative WFNS grade III, modified Fisher grade 4, spinal drainage, and angiographic vasospasm. Plasma SPARC levels were increased after SAH, and significantly higher in patients with than without DCI at days 7-9, and in patients with VASOGRADE-Yellow compared with VASOGRADE-Green at days 1-3 and 7-9. However, there were no relationships between plasma SPARC levels and angiographic vasospasm. Receiver-operating characteristic curves differentiating DCI from no DCI determined the cut-off value of plasma SPARC ≥ 82.1 ng/ml at days 7 - 9 (sensitivity, 0.800; specificity, 0.533; and area under the curve, 0.708), which was found to be an independent determinant of DCI development in multivariate analyses. This is the first study to show that SPARC is upregulated in peripheral blood after SAH, and that SPARC may be involved in the development of DCI without angiographic vasospasm in a clinical setting.

Artificial Intelligence for Neurosurgery : Current State and Future Directions

Artificial intelligence (AI) is a field of computer science that equips machines with human-like intelligence and enables them to learn, reason, and solve problems when presented with data in various formats. Neurosurgery is often at the forefront of innovative and disruptive technologies, which have similarly altered the course of acute and chronic diseases. In diagnostic imaging, such as X-rays, computed tomography, and magnetic resonance imaging, AI is used to analyze images. The use of robots in the field of neurosurgery is also increasing. In neurointensive care units, AI is used to analyze data and provide care to critically ill patients. Moreover, AI can be used to predict a patient's prognosis. Several AI applications have already been introduced in the field of neurosurgery, and many more are expected in the near future. Ultimately, it is our responsibility to keep pace with this evolution to provide meaningful outcomes and personalize each patient's care. Rather than blindly relying on AI in the future, neurosurgeons should gain a thorough understanding of it and use it to enhance their patient care.

Machine learning prediction of hematoma expansion in acute intracerebral hemorrhage

To examine whether machine learning (ML) approach can be used to predict hematoma expansion in acute intracerebral hemorrhage (ICH) with accuracy and widespread applicability, we applied ML algorithms to multicenter clinical data and CT findings on admission. Patients with acute ICH from three hospitals (n = 351) and those from another hospital (n = 71) were retrospectively assigned to the development and validation cohorts, respectively. To develop ML predictive models, the k-nearest neighbors (k-NN) algorithm, logistic regression, support vector machines (SVMs), random forests, and XGBoost were applied to the patient data in the development cohort. The models were evaluated for their performance on the patient data in the validation cohort, which was compared with previous scoring methods, the BAT, BRAIN, and 9-point scores. The k-NN algorithm achieved the highest area under the receiver operating characteristic curve (AUC) of 0.790 among all ML models, and the sensitivity, specificity, and accuracy were 0.846, 0.733, and 0.775, respectively. The BRAIN score achieved the highest AUC of 0.676 among all previous scoring methods, which was lower than the k-NN algorithm (p = 0.016). We developed and validated ML predictive models of hematoma expansion in acute ICH. The models demonstrated good predictive ability, showing better performance than the previous scoring methods.

The Utility of Quantitative EEG in Detecting Delayed Cerebral Ischemia After Aneurysmal Subarachnoid Hemorrhage

SUMMARY

In this review, we discuss the utility of quantitative EEG parameters for the detection of delayed cerebral ischemia (DCI) after aneurysmal subarachnoid hemorrhage in the context of the complex pathophysiology of DCI and the limitations of current diagnostic methods. Because of the multifactorial pathophysiology of DCI, methodologies solely assessing blood vessel narrowing (vasospasm) are insufficient to detect all DCI. Quantitative EEG has facilitated the exploration of EEG as a diagnostic modality of DCI. Multiple quantitative EEG parameters such as alpha power, relative alpha variability, and alpha/delta ratio show reliable detection of DCI in multiple studies. Recent studies on epileptiform abnormalities suggest that their potential for the detection of DCI. Quantitative EEG is a promising, continuous, noninvasive, monitoring modality of DCI implementable in daily practice. Future work should validate these parameters in larger populations, facilitated by the development of automated detection algorithms and multimodal data integration.

External Validation of a Neural Network Model in Aneurysmal Subarachnoid Hemorrhage: A Comparison With Conventional Logistic Regression Models

BACKGROUND

Interest in machine learning (ML)-based predictive modeling has led to the development of models predicting outcomes after aneurysmal subarachnoid hemorrhage (aSAH), including the Nijmegen acute subarachnoid hemorrhage calculator (Nutshell). Generalizability of such models to external data remains unclear.

OBJECTIVE

To externally validate the performance of the Nutshell tool while comparing it with the conventional Subarachnoid Hemorrhage International Trialists (SAHIT) models and to review the ML literature on outcome prediction after aSAH and aneurysm treatment.

METHODS

A prospectively maintained database of patients with aSAH presenting consecutively to our institution in the 2013 to 2018 period was used. The web-based Nutshell and SAHIT calculators were used to derive the risks of poor long-term (12-18 months) outcomes and 30-day mortality. Discrimination was evaluated using the area under the curve (AUC), and calibration was investigated using calibration plots. The literature on relevant ML models was surveyed for a synopsis.

RESULTS

In 269 patients with aSAH, the SAHIT models outperformed the Nutshell tool (AUC: 0.786 vs 0.689, P = .025) in predicting long-term functional outcomes. A logistic regression model of the Nutshell variables derived from our data achieved adequate discrimination (AUC = 0.759) of poor outcomes. The SAHIT models outperformed the Nutshell tool in predicting 30-day mortality (AUC: 0.810 vs 0.636, P < .001). Calibration properties were more favorable for the SAHIT models. Most published aneurysm-related ML-based outcome models lack external validation and usable testing platforms.

CONCLUSION

The Nutshell tool demonstrated limited performance on external validation in comparison with the SAHIT models. External validation and the dissemination of testing platforms for ML models must be emphasized.

Machine learning analysis of heart rate variability to detect delayed cerebral ischemia in subarachnoid hemorrhage

OBJECTIVES

Approximately 30% of patients with aneurysmal subarachnoid hemorrhage (aSAH) develop delayed cerebral ischemia (DCI). DCI is associated with increased mortality and persistent neurological deficits. This study aimed to analyze heart rate variability (HRV) data from patients with aSAH using machine learning to evaluate whether specific patterns could be found in patients developing DCI.

MATERIAL & METHODS

This is an extended, in-depth analysis of all HRV data from a previous study wherein HRV data were collected prospectively from a cohort of 64 patients with aSAH admitted to Sahlgrenska University Hospital, Gothenburg, Sweden, from 2015 to 2016. The method used for analyzing HRV is based on several data processing steps combined with the random forest supervised machine learning algorithm.

RESULTS

HRV data were available in 55 patients, but since data quality was significantly low in 19 patients, these were excluded. Twelve patients developed DCI. The machine learning process identified 71% of all DCI cases. However, the results also demonstrated a tendency to identify DCI in non-DCI patients, resulting in a specificity of 57%.

CONCLUSIONS

These data suggest that machine learning applied to HRV data might help identify patients with DCI in the future; however, whereas the sensitivity in the present study was acceptable, the specificity was low. Possible confounders such as severity of illness and therapy may have affected the result. Future studies should focus on developing a robust method for detecting DCI using real-time HRV data and explore the limits of this technology in terms of its reliability and accuracy.

Machine Learning in Action: Stroke Diagnosis and Outcome Prediction

The application of machine learning has rapidly evolved in medicine over the past decade. In stroke, commercially available machine learning algorithms have already been incorporated into clinical application for rapid diagnosis. The creation and advancement of deep learning techniques have greatly improved clinical utilization of machine learning tools and new algorithms continue to emerge with improved accuracy in stroke diagnosis and outcome prediction. Although imaging-based feature recognition and segmentation have significantly facilitated rapid stroke diagnosis and triaging, stroke prognostication is dependent on a multitude of patient specific as well as clinical factors and hence accurate outcome prediction remains challenging. Despite its vital role in stroke diagnosis and prognostication, it is important to recognize that machine learning output is only as good as the input data and the appropriateness of algorithm applied to any specific data set. Additionally, many studies on machine learning tend to be limited by small sample size and hence concerted efforts to collate data could improve evaluation of future machine learning tools in stroke. In the present state, machine learning technology serves as a helpful and efficient tool for rapid clinical decision making while oversight from clinical experts is still required to address specific aspects not accounted for in an automated algorithm. This article provides an overview of machine learning technology and a tabulated review of pertinent machine learning studies related to stroke diagnosis and outcome prediction.

Machine Learning and Intracranial Aneurysms: From Detection to Outcome Prediction

Machine learning (ML) is a rapidly rising research tool in biomedical sciences whose applications include segmentation, classification, disease detection, and outcome prediction. With respect to traditional statistical methods, ML algorithms have the potential to learn and improve their predictive performance when fed with large data sets without the need of being specifically programmed. In recent years, this technology has been increasingly applied for tackling clinical issues in intracranial aneurysm (IA) research. Several studies attempted to provide reliable models for enhanced aneurysm detection. Convolutional neural networks trained with variable degrees of human interaction on data from diverse imaging modalities showed high sensitivity in aneurysm detection tasks, also outperforming expert image analysis. Algorithms were also shown to differentiate ruptured from unruptured IAs, with however limited clinical relevance. For prediction of rupture and stability assessment, ML was preliminarily shown to achieve better performance compared to conventional statistical methods and existing risk scores. ML-based complication and functional outcome prediction in the event of SAH have been more extensively reported, in contrast with periprocedural outcome investigation in unruptured IA patients. ML has the potential to be a game changer in IA patient management. Currently clinical translation of experimental results is limited.

Predictive modeling in neurocritical care using causal artificial intelligence

Artificial intelligence (AI) and digital twin models of various systems have long been used in industry to test products quickly and efficiently. Use of digital twins in clinical medicine caught attention with the development of Archimedes, an AI model of diabetes, in 2003. More recently, AI models have been applied to the fields of cardiology, endocrinology, and undergraduate medical education. The use of digital twins and AI thus far has focused mainly on chronic disease management, their application in the field of critical care medicine remains much less explored. In neurocritical care, current AI technology focuses on interpreting electroencephalography, monitoring intracranial pressure, and prognosticating outcomes. AI models have been developed to interpret electroencephalograms by helping to annotate the tracings, detecting seizures, and identifying brain activation in unresponsive patients. In this mini-review we describe the challenges and opportunities in building an actionable AI model pertinent to neurocritical care that can be used to educate the newer generation of clinicians and augment clinical decision making.

Clarithromycin Ameliorates Early Brain Injury After Subarachnoid Hemorrhage via Suppressing Periostin-Related Pathways in Mice

Subarachnoid hemorrhage (SAH) remains a life-threatening disease, and early brain injury (EBI) is an important cause of poor outcomes. The authors have reported that periostin, a matricellular protein, is one of key factors of post-SAH EBI. Clarithromycin (CAM) is a worldwide antibiotic that can inhibit periostin expression. This study aimed to investigate whether CAM suppressed EBI after experimental SAH, focusing on blood-brain barrier (BBB) disruption, an important pathology of EBI. C57BL/6 male adult mice underwent endovascular perforation SAH modeling (n = 139) or sham operation (n = 30). Different dosages (25, 50, or 100 mg/kg) of CAM or the vehicle (n = 16, 52, 13, and 58, respectively) were randomly administered by an intramuscular injection 5 min after SAH induction. Post-SAH 50 mg/kg CAM treatment most effectively improved neurological scores and brain water content at 24 and 48 h and reduced immunoglobulin G extravasation at 24 h compared with vehicle-treated SAH mice (p < 0.01). Western blotting showed that post-SAH BBB disruption was associated with increased expressions of periostin, phosphorylated signal transducer and activator of transcription 1 and 3, matrix metalloproteinase-9, and the consequent degradation of zonula occludens-1, which were suppressed by 50 mg/kg CAM treatment (p < 0.05, respectively, versus vehicle-treated SAH mice). Periostin and its related molecules were upregulated in capillary endothelial cells and neurons after SAH. An intracerebroventricular injection of recombinant periostin blocked the neuroprotective effects of CAM in SAH mice (n = 6, respectively; p < 0.05). In conclusion, this study first demonstrated that CAM improved post-SAH EBI in terms of BBB disruption at least partly via the suppression of periostin-related pathways.

Machine Learning Applications in the Neuro ICU: A Solution to Big Data Mayhem?

The neurological ICU (neuro ICU) often suffers from significant limitations due to scarce resource availability for their neurocritical care patients. Neuro ICU patients require frequent neurological evaluations, continuous monitoring of various physiological parameters, frequent imaging, and routine lab testing. This amasses large amounts of data specific to each patient. Neuro ICU teams are often overburdened by the resulting complexity of data for each patient. Machine Learning algorithms (ML), are uniquely capable of interpreting high-dimensional datasets that are too difficult for humans to comprehend. Therefore, the application of ML in the neuro ICU could alleviate the burden of analyzing big datasets for each patient. This review serves to (1) briefly summarize ML and compare the different types of MLs, (2) review recent ML applications to improve neuro ICU management and (3) describe the future implications of ML to neuro ICU management.

Cerebrovascular pathophysiology of delayed cerebral ischemia after aneurysmal subarachnoid hemorrhage

Aneurysmal subarachnoid hemorrhage (SAH) remains a serious cerebrovascular disease. Even if SAH patients survive the initial insults, delayed cerebral ischemia (DCI) may occur at 4 days or later post-SAH. DCI is characteristics of SAH, and is considered to develop by blood breakdown products and inflammatory reactions, or secondary to early brain injury, acute pathophysiological events that occur in the brain within the first 72 hours of aneurysmal SAH. The pathology underlying DCI may involve large artery vasospasm and/or microcirculatory disturbances by microvasospasm, microthrombosis, dysfunction of venous outflow and compression of microvasculature by vasogenic or cytotoxic tissue edema. Recent clinical evidence has shown that large artery vasospasm is not the only cause of DCI, and that both large artery vasospasm-dependent and -independent cerebral infarction causes poor outcome. Animal studies suggest that mechanisms of vasospasm may differ between large artery and arterioles or capillaries, and that many kinds of cells in the vascular wall and brain parenchyma may be involved in the pathogenesis of microcirculatory disturbances. The impairment of the paravascular and glymphatic systems also may play important roles in the development of DCI. As pathological mediators for DCI, glutamate and several matricellular proteins have been investigated in addition to inflammatory molecules. Glutamate is involved in excitotoxicity contributing to cortical spreading ischemia and epileptic activity-related events. Microvascular dysfunction is an attractive mechanism to explain the cause of poor outcomes independently of large cerebral artery vasospasm, but needs more studies to clarify the pathophysiologies or mechanisms and to develop a novel therapeutic strategy.

A systematic review of machine learning models for predicting outcomes of stroke with structured data

Background and purpose

Machine learning (ML) has attracted much attention with the hope that it could make use of large, routinely collected datasets and deliver accurate personalised prognosis. The aim of this systematic review is to identify and critically appraise the reporting and developing of ML models for predicting outcomes after stroke.

Methods

We searched PubMed and Web of Science from 1990 to March 2019, using previously published search filters for stroke, ML, and prediction models. We focused on structured clinical data, excluding image and text analysis. This review was registered with PROSPERO (CRD42019127154).

Results

Eighteen studies were eligible for inclusion. Most studies reported less than half of the terms in the reporting quality checklist. The most frequently predicted stroke outcomes were mortality (7 studies) and functional outcome (5 studies). The most commonly used ML methods were random forests (9 studies), support vector machines (8 studies), decision trees (6 studies), and neural networks (6 studies). The median sample size was 475 (range 70–3184), with a median of 22 predictors (range 4–152) considered. All studies evaluated discrimination with thirteen using area under the ROC curve whilst calibration was assessed in three. Two studies performed external validation. None described the final model sufficiently well to reproduce it.

Conclusions

The use of ML for predicting stroke outcomes is increasing. However, few met basic reporting standards for clinical prediction tools and none made their models available in a way which could be used or evaluated. Major improvements in ML study conduct and reporting are needed before it can meaningfully be considered for practice.

Artificial Intelligence in the Management of Intracranial Aneurysms: Current Status and Future Perspectives

Intracranial aneurysms with subarachnoid hemorrhage lead to high morbidity and mortality. It is of critical importance to detect aneurysms, identify risk factors of rupture, and predict treatment response of aneurysms to guide clinical interventions. Artificial intelligence has received worldwide attention for its impressive performance in image-based tasks. Artificial intelligence serves as an adjunct to physicians in a series of clinical settings, which substantially improves diagnostic accuracy while reducing physicians' workload. Computer-assisted diagnosis systems of aneurysms based on MRA and CTA using deep learning have been evaluated, and excellent performances have been reported. Artificial intelligence has also been used in automated morphologic calculation, rupture risk stratification, and outcomes prediction with the implementation of machine learning methods, which have exhibited incremental value. This review summarizes current advances of artificial intelligence in the management of aneurysms, including detection and prediction. The challenges and future directions of clinical implementations of artificial intelligence are briefly discussed.

Mechanisms of neuroinflammation and inflammatory mediators involved in brain injury following subarachnoid hemorrhage

Subarachnoid hemorrhage (SAH) is a devastating cerebrovascular disorder. Neuroinflammation is a critical cause of brain injury following SAH in both acute and chronic phases. While accumulating evidence has shown that therapies targeting neuroinflammation exerted beneficial effects in experimental SAH, there is little clinical evidence. One of the factors making neuroinflammation complicated is that inflammatory signaling pathways and mediators act as protective or detrimental responses at different phases. In addition, biomarkers to detect neuroinflammation are little known in clinical settings. In this review, first, we discuss how the inflammatory signaling pathways contribute to brain injury and other secondary pathophysiological changes in SAH. Damage-associated molecular patterns arising from mechanical stress, transient global cerebral ischemia, red blood cell breakdown and delayed cerebral ischemia following SAH trigger to activate pattern recognition receptors (PRRs) such as Toll-like receptors, nucleotide-binding oligomerization domain-like receptors, and receptors for advanced glycation end products. Most of PRRs activate common downstream signaling transcriptional factor nuclear factor-κΒ and mitogen-activated protein kinases, releasing pro-inflammatory mediators and cytokines. Next, we focus on how pro-inflammatory substances play a role during the course of SAH. Finally, we highlight an important inducer of neuroinflammation, matricellular protein (MCP). MCPs are a component of extracellular matrix and exert beneficial and harmful effects through binding to receptors, other matrix proteins, growth factors, and cytokines. Treatment targeting MCPs is being proved efficacious in pre-clinical models for preventing brain injury including neuroinflammation in SAH. In addition, MCPs may be a candidate of biomarkers predicting brain injury following SAH in clinical settings.