Prognostic Implications of Early Prediction in Posttraumatic Epilepsy.

Posttraumatic epilepsy (PTE) is a complication of traumatic brain injury that can increase morbidity, but predicting which patients may develop PTE remains a challenge. Much work has been done to identify a variety of risk factors and biomarkers, or a combination thereof, for patients at highest risk of PTE. However, several issues have hampered progress toward fully adapted PTE models. Such issues include the need for models that are well-validated, cost-effective, and account for competing outcomes like death. Additionally, while an accurate PTE prediction model can provide quantitative prognostic information, how such information is communicated to inform shared decision-making and treatment strategies requires consideration of an individual patient's clinical trajectory and unique values, especially given the current absence of direct anti-epileptogenic treatments. Future work exploring approaches integrating individualized communication of prediction model results are needed.

Deep Learning Applications for Acute Stroke Management.

Brain imaging is essential to the clinical care of patients with stroke, a leading cause of disability and death worldwide. Whereas advanced neuroimaging techniques offer opportunities for aiding acute stroke management, several factors, including time delays, inter-clinician variability, and lack of systemic conglomeration of clinical information, hinder their maximal utility. Recent advances in deep machine learning (DL) offer new strategies for harnessing computational medical image analysis to inform decision making in acute stroke. We examine the current state of the field for DL models in stroke triage. First, we provide a brief, clinical practice-focused primer on DL. Next, we examine real-world examples of DL applications in pixel-wise labeling, volumetric lesion segmentation, stroke detection, and prediction of tissue fate postintervention. We evaluate recent deployments of deep neural networks and their ability to automatically select relevant clinical features for acute decision making, reduce inter-rater variability, and boost reliability in rapid neuroimaging assessments, and integrate neuroimaging with electronic medical record (EMR) data in order to support clinicians in routine and triage stroke management. Ultimately, we aim to provide a framework for critically evaluating existing automated approaches, thus equipping clinicians with the ability to understand and potentially apply DL approaches in order to address challenges in clinical practice. ANN NEUROL 2022;92:574-587.

Quantitative epileptiform burden and electroencephalography background features predict post-traumatic epilepsy.

BACKGROUND: Post-traumatic epilepsy (PTE) is a severe complication of traumatic brain injury (TBI). Electroencephalography aids early post-traumatic seizure diagnosis, but its optimal utility for PTE prediction remains unknown. We aim to evaluate the contribution of quantitative electroencephalograms to predict first-year PTE (PTE1). METHODS: We performed a multicentre, retrospective case-control study of patients with TBI. 63 PTE1 patients were matched with 63 non-PTE1 patients by admission Glasgow Coma Scale score, age and sex. We evaluated the association of quantitative electroencephalography features with PTE1 using logistic regressions and examined their predictive value relative to TBI mechanism and CT abnormalities. RESULTS: In the matched cohort (n=126), greater epileptiform burden, suppression burden and beta variability were associated with 4.6 times higher PTE1 risk based on multivariable logistic regression analysis (area under the receiver operating characteristic curve, AUC (95% CI) 0.69 (0.60 to 0.78)). Among 116 (92%) patients with available CT reports, adding quantitative electroencephalography features to a combined mechanism and CT model improved performance (AUC (95% CI), 0.71 (0.61 to 0.80) vs 0.61 (0.51 to 0.72)). CONCLUSIONS: Epileptiform and spectral characteristics enhance covariates identified on TBI admission and CT abnormalities in PTE1 prediction. Future trials should incorporate quantitative electroencephalography features to validate this enhancement of PTE risk stratification models.

Impact of Therapeutic Interventions on Cerebral Autoregulatory Function Following Severe Traumatic Brain Injury: A Secondary Analysis of the BOOST-II Study.

BACKGROUND: The Brain Oxygen Optimization in Severe Traumatic Brain Injury Phase II randomized controlled trial used a tier-based management protocol based on brain tissue oxygen (PbtO2) and intracranial pressure (ICP) monitoring to reduce brain tissue hypoxia after severe traumatic brain injury. We performed a secondary analysis to explore the relationship between brain tissue hypoxia, blood pressure (BP), and interventions to improve cerebral perfusion pressure (CPP). We hypothesized that BP management below the lower limit of autoregulation would lead to cerebral hypoperfusion and brain tissue hypoxia that could be improved with hemodynamic augmentation. METHODS: Of the 119 patients enrolled in the Brain Oxygen Optimization in Severe Traumatic Brain Injury Phase II trial, 55 patients had simultaneous recordings of arterial BP, ICP, and PbtO2. Autoregulatory function was measured by interrogating changes in ICP and PbtO2 in response to fluctuations in CPP using time-correlation analysis. The resulting autoregulatory indices (pressure reactivity index and oxygen reactivity index) were used to identify the "optimal" CPP and limits of autoregulation for each patient. Autoregulatory function and percent time with CPP outside personalized limits of autoregulation were calculated before, during, and after all interventions directed to optimize CPP. RESULTS: Individualized limits of autoregulation were computed in 55 patients (mean age 38 years, mean monitoring time 92 h). We identified 35 episodes of brain tissue hypoxia (PbtO2 < 20 mm Hg) treated with CPP augmentation. Following each intervention, mean CPP increased from 73 ± 14 mm Hg to 79 ± 17 mm Hg (p = 0.15), and mean PbtO2 improved from 18.4 ± 5.6 mm Hg to 21.9 ± 5.6 mm Hg (p = 0.01), whereas autoregulatory function trended toward improvement (oxygen reactivity index 0.42 vs. 0.37, p = 0.14; pressure reactivity index 0.25 vs. 0.21, p = 0.2). Although optimal CPP and limits remained relatively unchanged, there was a significant decrease in the percent time with CPP below the lower limit of autoregulation in the 60 min after compared with before an intervention (11% vs. 23%, p = 0.05). CONCLUSIONS: Our analysis suggests that brain tissue hypoxia is associated with cerebral hypoperfusion characterized by increased time with CPP below the lower limit of autoregulation. Interventions to increase CPP appear to improve autoregulation. Further studies are needed to validate the importance of autoregulation as a modifiable variable with the potential to improve outcomes.

Electroencephalographic Abnormalities are Common in COVID-19 and are Associated with Outcomes.

OBJECTIVE: The aim was to determine the prevalence and risk factors for electrographic seizures and other electroencephalographic (EEG) patterns in patients with Coronavirus disease 2019 (COVID-19) undergoing clinically indicated continuous electroencephalogram (cEEG) monitoring and to assess whether EEG findings are associated with outcomes. METHODS: We identified 197 patients with COVID-19 referred for cEEG at 9 participating centers. Medical records and EEG reports were reviewed retrospectively to determine the incidence of and clinical risk factors for seizures and other epileptiform patterns. Multivariate Cox proportional hazards analysis assessed the relationship between EEG patterns and clinical outcomes. RESULTS: Electrographic seizures were detected in 19 (9.6%) patients, including nonconvulsive status epilepticus (NCSE) in 11 (5.6%). Epileptiform abnormalities (either ictal or interictal) were present in 96 (48.7%). Preceding clinical seizures during hospitalization were associated with both electrographic seizures (36.4% in those with vs 8.1% in those without prior clinical seizures, odds ratio [OR] 6.51, p = 0.01) and NCSE (27.3% vs 4.3%, OR 8.34, p = 0.01). A pre-existing intracranial lesion on neuroimaging was associated with NCSE (14.3% vs 3.7%; OR 4.33, p = 0.02). In multivariate analysis of outcomes, electrographic seizures were an independent predictor of in-hospital mortality (hazard ratio [HR] 4.07 [1.44-11.51], p < 0.01). In competing risks analysis, hospital length of stay increased in the presence of NCSE (30 day proportion discharged with vs without NCSE: HR 0.21 [0.03-0.33] vs 0.43 [0.36-0.49]). INTERPRETATION: This multicenter retrospective cohort study demonstrates that seizures and other epileptiform abnormalities are common in patients with COVID-19 undergoing clinically indicated cEEG and are associated with adverse clinical outcomes. ANN NEUROL 2021;89:872-883.

Antiseizure Medication Treatment and Outcomes in Patients with Subarachnoid Hemorrhage Undergoing Continuous EEG Monitoring.

BACKGROUND: Patients with aneurysmal subarachnoid hemorrhage (aSAH) with electroencephalographic epileptiform activity (seizures, periodic and rhythmic patterns, and sporadic discharges) are frequently treated with antiseizure medications (ASMs). However, the safety and effectiveness of ASM treatment for epileptiform activity has not been established. We used observational data to investigate the effectiveness of ASM treatment in patients with aSAH undergoing continuous electroencephalography (cEEG) to develop a causal hypothesis for testing in prospective trials. METHODS: This was a retrospective single-center cohort study of patients with aSAH admitted between 2011 and 2016. Patients underwent ≥ 24 h of cEEG within 4 days of admission. All patients received primary ASM prophylaxis until aneurysm treatment (typically within 24 h of admission). Treatment exposure was defined as reinitiation of ASMs after aneurysm treatment and cEEG initiation. We excluded patients with non-cEEG indications for ASMs (e.g., epilepsy, acute symptomatic seizures). Outcomes measures were 90-day mortality and good functional outcome (modified Rankin Scale scores 0-3). Propensity scores were used to adjust for baseline covariates and disease severity. RESULTS: Ninety-four patients were eligible (40 continued ASM treatment; 54 received prophylaxis only). ASM continuation was not significantly associated with higher 90-day mortality (propensity-adjusted hazard ratio [HR] = 2.01 [95% confidence interval (CI) 0.57-7.02]). ASM continuation was associated with lower likelihood for 90-day good functional outcome (propensity-adjusted HR = 0.39 [95% CI 0.18-0.81]). In a secondary analysis, low-intensity treatment (low-dose single ASM) was not significantly associated with mortality (propensity-adjusted HR = 0.60 [95% CI 0.10-3.59]), although it was associated with a lower likelihood of good outcome (propensity-adjusted HR = 0.37 [95% CI 0.15-0.91]), compared with prophylaxis. High-intensity treatment (high-dose single ASM, multiple ASMs, or anesthetics) was associated with higher mortality (propensity-adjusted HR = 6.80 [95% CI 1.67-27.65]) and lower likelihood for good outcomes (propensity-adjusted HR = 0.30 [95% CI 0.10-0.94]) compared with prophylaxis only. CONCLUSIONS: Our findings suggest the testable hypothesis that continuing ASMs in patients with aSAH with cEEG abnormalities does not improve functional outcomes. This hypothesis should be tested in prospective randomized studies.

Hospital Revisits for Post-Ischemic Stroke Epilepsy after Acute Stroke Interventions.

OBJECTIVES: Improvements in acute stroke care have led to an increase in ischemic stroke survivors, who are at risk for development of post-ischemic stroke epilepsy (PISE). The impact of therapies such as thrombectomy and thrombolysis on risk of hospital revisits for PISE is unclear. We utilized administrative data to investigate the association between stroke treatment and PISE-related visits. MATERIALS AND METHODS: Using claims data from California, New York, and Florida, we performed a retrospective analysis of adult survivors of acute ischemic strokes. Patients with history of epilepsy, trauma, infections, or tumors were excluded. Included patients were followed for a primary outcome of revisits for seizures or epilepsy. Cox proportional hazards regression was used to identify covariates associated with PISE. RESULTS: In 595,545 included patients (median age 74 [IQR 21], 52% female), the 6-year cumulative rate of PISE-related revisit was 2.20% (95% CI 2.16-2.24). In multivariable models adjusting for demographics, comorbidities, and indicators of stroke severity, IV-tPA (HR 1.42, 95% CI 1.31-1.54, p<0.001) but not MT (HR 1.62, 95% CI 0.90-1.50, p=0.2) was associated with PISE-related revisit. Patients who underwent decompressive craniectomy experienced a 2-fold increase in odds for returning with PISE (HR 2.35, 95% CI 1.69-3.26, p<0.001). In-hospital seizures (HR 4.06, 95% CI 3.76-4.39, p<0.001) also elevated risk for PISE. SIGNIFICANCE: We demonstrate that ischemic stroke survivors who received IV-tPA, underwent decompressive craniectomy, or experienced acute seizures were at increased risk PISE-related revisit. Close attention should be paid to these patients with increased potential for long-term development of and re-hospitalization for PISE.

A model of metabolic supply-demand mismatch leading to secondary brain injury.

Secondary brain injury (SBI) is defined as new or worsening injury to the brain after an initial neurologic insult, such as hemorrhage, trauma, ischemic stroke, or infection. It is a common and potentially preventable complication following many types of primary brain injury (PBI). However, mechanistic details about how PBI leads to additional brain injury and evolves into SBI are poorly characterized. In this work, we propose a mechanistic model for the metabolic supply demand mismatch hypothesis (MSDMH) of SBI. Our model, based on the Hodgkin-Huxley model, supplemented with additional dynamics for extracellular potassium, oxygen concentration, and excitotoxity, provides a high-level unified explanation for why patients with acute brain injury frequently develop SBI. We investigate how decreased oxygen, increased extracellular potassium, excitotoxicity, and seizures can induce SBI and suggest three underlying paths for how events following PBI may lead to SBI. The proposed model also helps explain several important empirical observations, including the common association of acute brain injury with seizures, the association of seizures with tissue hypoxia and so on. In contrast to current practices which assume that ischemia plays the predominant role in SBI, our model suggests that metabolic crisis involved in SBI can also be nonischemic. Our findings offer a more comprehensive understanding of the complex interrelationship among potassium, oxygen, excitotoxicity, seizures, and SBI.NEW & NOTEWORTHY We present a novel mechanistic model for the metabolic supply demand mismatch hypothesis (MSDMH), which attempts to explain why patients with acute brain injury frequently develop seizure activity and secondary brain injury (SBI). Specifically, we investigate how decreased oxygen, increased extracellular potassium, excitotoxicity, seizures, all common sequalae of primary brain injury (PBI), can induce SBI and suggest three underlying paths for how events following PBI may lead to SBI.

Admission computed tomography radiomic signatures outperform hematoma volume in predicting baseline clinical severity and functional outcome in the ATACH-2 trial intracerebral hemorrhage population.

BACKGROUND AND PURPOSE: Radiomics provides a framework for automated extraction of high-dimensional feature sets from medical images. We aimed to determine radiomics signature correlates of admission clinical severity and medium-term outcome from intracerebral hemorrhage (ICH) lesions on baseline head computed tomography (CT). METHODS: We used the ATACH-2 (Antihypertensive Treatment of Acute Cerebral Hemorrhage II) trial dataset. Patients included in this analysis (n = 895) were randomly allocated to discovery (n = 448) and independent validation (n = 447) cohorts. We extracted 1130 radiomics features from hematoma lesions on baseline noncontrast head CT scans and generated radiomics signatures associated with admission Glasgow Coma Scale (GCS), admission National Institutes of Health Stroke Scale (NIHSS), and 3-month modified Rankin Scale (mRS) scores. Spearman's correlation between radiomics signatures and corresponding target variables was compared with hematoma volume. RESULTS: In the discovery cohort, radiomics signatures, compared to ICH volume, had a significantly stronger association with admission GCS (0.47 vs. 0.44, p = 0.008), admission NIHSS (0.69 vs. 0.57, p < 0.001), and 3-month mRS scores (0.44 vs. 0.32, p < 0.001). Similarly, in independent validation, radiomics signatures, compared to ICH volume, had a significantly stronger association with admission GCS (0.43 vs. 0.41, p = 0.02), NIHSS (0.64 vs. 0.56, p < 0.001), and 3-month mRS scores (0.43 vs. 0.33, p < 0.001). In multiple regression analysis adjusted for known predictors of ICH outcome, the radiomics signature was an independent predictor of 3-month mRS in both cohorts. CONCLUSIONS: Limited by the enrollment criteria of the ATACH-2 trial, we showed that radiomics features quantifying hematoma texture, density, and shape on baseline CT can provide imaging correlates for clinical presentation and 3-month outcome. These findings couldtrigger a paradigm shift where imaging biomarkers may improve current modelsfor prognostication, risk-stratification, and treatment triage of ICH patients.

Electroencephalography, Hospital Complications, and Longitudinal Outcomes After Subarachnoid Hemorrhage.

BACKGROUND: Following non-traumatic subarachnoid hemorrhage (SAH), in-hospital delayed cerebral ischemia is predicted by two chief events on continuous EEG (cEEG): new or worsening epileptiform abnormalities (EAs) and deterioration of cEEG background frequencies. We evaluated the association between longitudinal outcomes and these cEEG biomarkers. We additionally evaluated the association between longitudinal outcomes and other in-hospital complications. METHODS: Patients with nontraumatic SAH undergoing ≥ 3 days of cEEG monitoring were enrolled in a prospective study evaluating longitudinal outcomes. Modified Rankin Scale (mRS) was assessed at discharge, and at 3- and 6-month follow-up time points. Adjusting for baseline severity in a cumulative proportional odds model, we modeled the mRS ordinally and measured the association between mRS and two forms of in-hospital cEEG deterioration: (1) cEEG evidence of new or worsening epileptiform abnormalities and (2) cEEG evidence of new background deterioration. We compared the magnitude of these associations at each time point with the association between mRS and other in-hospital complications: (1) delayed cerebral ischemia (DCI), (2) hospital-acquired infections (HAI), and (3) hydrocephalus. In a secondary analysis, we employed a linear mixed effects model to examine the association of mRS over time (dichotomized as 0-3 vs. 4-6) with both biomarkers of cEEG deterioration and with other in-hospital complications. RESULTS: In total, 175 mRS assessments were performed in 59 patients. New or worsening EAs developed in 23 (39%) patients, and new background deterioration developed in 24 (41%). Among cEEG biomarkers, new or worsening EAs were independently associated with mRS at discharge, 3, and 6 months, respectively (adjusted cumulative proportional odds 4.99, 95% CI 1.60-15.6; 3.28, 95% CI 1.14-9.5; and 2.71, 95% CI 0.95-7.76), but cEEG background deterioration lacked an association. Among hospital complications, DCI was associated with discharge, 3-, and 6-month outcomes (adjusted cumulative proportional odds 4.75, 95% CI 1.64-13.8; 3.4; 95% CI 1.24-9.01; and 2.45, 95% CI 0.94-6.6), but HAI and hydrocephalus lacked an association. The mixed effects model demonstrated that these associations were sustained over longitudinal assessments without an interaction with time. CONCLUSION: Although new or worsening EAs and cEEG background deterioration have both been shown to predict DCI, only new or worsening EAs are associated with a sustained impairment in functional outcome. This novel finding raises the potential for identifying therapeutic targets that may also influence outcomes.

Soluble ST2 Is Associated With New Epileptiform Abnormalities Following Nontraumatic Subarachnoid Hemorrhage.

Background and Purpose- We evaluated the association between 2 types of predictors of delayed cerebral ischemia after nontraumatic subarachnoid hemorrhage, including biomarkers of the innate immune response and neurophysiologic changes on continuous electroencephalography. Methods- We studied subarachnoid hemorrhage patients that had at least 72 hours of continuous electroencephalography and blood samples collected within the first 5 days of symptom onset. We measured inflammatory biomarkers previously associated with delayed cerebral ischemia and functional outcome, including soluble ST2 (sST2), IL-6 (interleukin-6), and CRP (C-reactive protein). Serial plasma samples and cerebrospinal fluid sST2 levels were available in a subgroup of patients. Neurophysiologic changes were categorized into new or worsening epileptiform abnormalities (EAs) or new background deterioration. The association of biomarkers with neurophysiologic changes were evaluated using the Wilcoxon rank-sum test. Plasma and cerebrospinal fluid sST2 were further examined longitudinally using repeated measures mixed-effects models. Results- Forty-six patients met inclusion criteria. Seventeen (37%) patients developed new or worsening EAs, 21 (46%) developed new background deterioration, and 8 (17%) developed neither. Early (day, 0-5) plasma sST2 levels were higher among patients with new or worsening EAs (median 115 ng/mL [interquartile range, 73.8-197]) versus those without (74.7 ng/mL [interquartile range, 44.8-102]; P=0.024). Plasma sST2 levels were similar between patients with or without new background deterioration. Repeated measures mixed-effects modeling that adjusted for admission risk factors showed that the association with new or worsening EAs remained independent for both plasma sST2 (ß=0.41 [95% CI, 0.09-0.73]; P=0.01) and cerebrospinal fluid sST2 (ß=0.97 [95% CI, 0.14-1.8]; P=0.021). IL-6 and CRP were not associated with new background deterioration or with new or worsening EAs. Conclusions- In patients admitted with subarachnoid hemorrhage, sST2 level was associated with new or worsening EAs but not new background deterioration. This association may identify a link between a specific innate immune response pathway and continuous electroencephalography abnormalities in the pathogenesis of secondary brain injury after subarachnoid hemorrhage.

Detecting Seizures and Epileptiform Abnormalities in Acute Brain Injury.

PURPOSE OF REVIEW: Acute brain injury (ABI) is a broad category of pathologies, including traumatic brain injury, and is commonly complicated by seizures. Electroencephalogram (EEG) studies are used to detect seizures or other epileptiform patterns. This review seeks to clarify EEG findings relevant to ABI, explore practical barriers limiting EEG implementation, discuss strategies to leverage EEG monitoring in various clinical settings, and suggest an approach to utilize EEG for triage. RECENT FINDINGS: Current literature suggests there is an increased morbidity and mortality risk associated with seizures or patterns on the ictal-interictal continuum (IIC) due to ABI. Further, increased use of EEG is associated with better clinical outcomes. However, there are many logistical barriers to successful EEG implementation that prohibit its ubiquitous use. Solutions to these limitations include the use of rapid EEG systems, non-expert EEG analysis, machine learning algorithms, and the incorporation of EEG data into prognostic models.

Epileptiform activity in traumatic brain injury predicts post-traumatic epilepsy.

We hypothesize that epileptiform abnormalities (EAs) in the electroencephalogram (EEG) during the acute period following traumatic brain injury (TBI) independently predict first-year post-traumatic epilepsy (PTE1 ). We analyze PTE1 risk factors in two cohorts matched for TBI severity and age (n = 50). EAs independently predict risk for PTE1 (odds ratio [OR], 3.16 [0.99, 11.68]); subdural hematoma is another independent risk factor (OR, 4.13 [1.18, 39.33]). Differences in EA rates are apparent within 5 days following TBI. Our results suggest that increased EA prevalence identifies patients at increased risk for PTE1 , and that EAs acutely post-TBI can identify patients most likely to benefit from antiepileptogenesis drug trials. Ann Neurol 2018;83:858-862.

Reverse Locked-In Syndrome.

BACKGROUND: Basilar artery occlusion can cause locked-in syndrome, which is characterized by quadriplegia, anarthria, and limited communication via eye movements. Here, we describe an uncommon stroke syndrome associated with endovascular recanalization of the top of the basilar artery: "reverse locked-in syndrome." METHODS: We report the case of a patient with atypical neurological deficits caused by acute ischemic stroke of the midbrain tegmentum. We perform neuroanatomic localization of the patient's infarcts by mapping the magnetic resonance imaging (MRI) data onto a brainstem atlas. RESULTS: A 61-year-old man presented with acute coma and quadriplegia due to top of the basilar artery occlusion. He underwent emergent endovascular thrombectomy, with successful recanalization of the basilar artery at 4 h and 43 min post-ictus. The patient regained consciousness and purposeful movement in all four extremities, but the post-procedure neurological examination demonstrated bilateral ptosis with complete pupillary and oculomotor paralysis. MRI revealed infarction of the bilateral oculomotor nuclei in the midbrain tegmentum. At 9-month follow-up, he had anisocoria and dysconjugate gaze, but was living at home and required minimal assistance in performing all activities of daily living. CONCLUSIONS: Since the patient's deficits were the exact opposite of those described in locked-in syndrome, we propose the term "reverse locked-in syndrome" to describe this neurological entity characterized by bilateral ptosis, non-reactive pupils, and ophthalmoplegia with preservation of consciousness and extremity motor function.

Emergent external ventricular drain placement in patients with factor Xa inhibitor-associated intracerebral hemorrhage after reversal with andexanet alfa.

BACKGROUND: Andexanet alfa (AA), a factor Xa-inhibitor (FXi) reversal agent, is given as a bolus followed by a 2-hour infusion. This long administration time can delay EVD placement in intracerebral hemorrhage (ICH) patients. We sought to evaluate the safety of EVD placement immediately post-AA bolus compared to post-AA infusion. METHODS: We conducted a retrospective study that included adult patients admitted with FXi-associated ICH who received AA and underwent EVD placement The primary outcome was the occurrence of a new hemorrhage (tract, extra-axial, or intraventricular hemorrhage). Secondary outcomes included mortality, intensive care unit and hospital length of stay, and discharge modified Rankin Score. The primary safety outcome was documented thrombotic events. RESULTS: Twelve patients with FXi related ICH were included (EVD placement post-AA bolus, N = 8; EVD placement post-AA infusion, N = 4). Each arm included one patient with bilateral EVD placed. There was no difference in the incidence of new hemorrhages, with one post-AA bolus patient had small, focal, nonoperative extra-axial hemorrhage. Morbidity and mortality were higher in post-AA infusion patients (mRS, post-AA bolus, 4 [4-6] vs. post-AA infusion 6 [5,6], p = 0.24 and post-AA bolus, 3 (37.5 %) vs. post-AA infusion, 3 (75 %), p = 0.54, respectively). One patient in the post-AA bolus group had thrombotic event. There was no difference in hospital LOS (post-AA bolus, 19 days [12-26] vs. post-AA infusion, 14 days [9-22], p = 0.55) and ICU LOS (post-AA bolus, 10 days [6-13] vs. post-AA infusion, 11 days [5-21], p = 0.86). CONCLUSION: We report no differences in the incidence of tract hemorrhage, extra-axial hemorrhage, or intraventricular hemorrhage post-AA bolus versus post-AA infusion. Larger prospective studies to validate these results are warranted.

Polygenic Risk of Epilepsy and Post-Stroke Epilepsy.

Background and Aims: Epilepsy is highly heritable, with numerous known genetic risk loci. However, the genetic predisposition's role in post-acute brain injury epilepsy remains understudied. This study assesses whether a higher genetic predisposition to epilepsy raises post-stroke or Transient Ischemic Attack (TIA) survivor's risk of Post-Stroke Epilepsy (PSE). Methods: We conducted a three-stage genetic analysis. First, we identified independent epilepsy-associated ( p <5x10 -8 ) genetic variants from public data. Second, we estimated PSE-specific variant weights in stroke/TIA survivors from the UK Biobank. Third, we tested for an association between a polygenic risk score (PRS) and PSE risk in stroke/TIA survivors from the All of Us Research Program. Primary analysis included all ancestries, while a secondary analysis was restricted to European ancestry only. A sensitivity analysis excluded TIA survivors. Association testing was conducted via multivariable logistic regression, adjusting for age, sex, and genetic ancestry. Results: Among 19,708 UK Biobank participants with stroke/TIA, 805 (4.1%) developed PSE. Likewise, among 12,251 All of Us participants with stroke/TIA, 394 (3.2%) developed PSE. After establishing PSE-specific weights for 39 epilepsy-linked genetic variants in the UK Biobank, the resultant PRS was associated with elevated odds of PSE development in All of Us (OR:1.16[1.02-1.32]). A similar result was obtained when restricting to participants of European ancestry (OR:1.23[1.02-1.49]) and when excluding participants with a TIA history (OR:1.18[1.02-1.38]). Conclusions: Our findings suggest that akin to other forms of epilepsy, genetic predisposition plays an essential role in PSE. Because the PSE data were sparse, our results should be interpreted cautiously.

Development of Expert-Level Classification of Seizures and Rhythmic and Periodic Patterns During EEG Interpretation.

BACKGROUND AND OBJECTIVES: Seizures (SZs) and other SZ-like patterns of brain activity can harm the brain and contribute to in-hospital death, particularly when prolonged. However, experts qualified to interpret EEG data are scarce. Prior attempts to automate this task have been limited by small or inadequately labeled samples and have not convincingly demonstrated generalizable expert-level performance. There exists a critical unmet need for an automated method to classify SZs and other SZ-like events with expert-level reliability. This study was conducted to develop and validate a computer algorithm that matches the reliability and accuracy of experts in identifying SZs and SZ-like events, known as "ictal-interictal-injury continuum" (IIIC) patterns on EEG, including SZs, lateralized and generalized periodic discharges (LPD, GPD), and lateralized and generalized rhythmic delta activity (LRDA, GRDA), and in differentiating these patterns from non-IIIC patterns. METHODS: We used 6,095 scalp EEGs from 2,711 patients with and without IIIC events to train a deep neural network, SPaRCNet, to perform IIIC event classification. Independent training and test data sets were generated from 50,697 EEG segments, independently annotated by 20 fellowship-trained neurophysiologists. We assessed whether SPaRCNet performs at or above the sensitivity, specificity, precision, and calibration of fellowship-trained neurophysiologists for identifying IIIC events. Statistical performance was assessed by the calibration index and by the percentage of experts whose operating points were below the model's receiver operating characteristic curves (ROCs) and precision recall curves (PRCs) for the 6 pattern classes. RESULTS: SPaRCNet matches or exceeds most experts in classifying IIIC events based on both calibration and discrimination metrics. For SZ, LPD, GPD, LRDA, GRDA, and "other" classes, SPaRCNet exceeds the following percentages of 20 experts-ROC: 45%, 20%, 50%, 75%, 55%, and 40%; PRC: 50%, 35%, 50%, 90%, 70%, and 45%; and calibration: 95%, 100%, 95%, 100%, 100%, and 80%, respectively. DISCUSSION: SPaRCNet is the first algorithm to match expert performance in detecting SZs and other SZ-like events in a representative sample of EEGs. With further development, SPaRCNet may thus be a valuable tool for an expedited review of EEGs. CLASSIFICATION OF EVIDENCE: This study provides Class II evidence that among patients with epilepsy or critical illness undergoing EEG monitoring, SPaRCNet can differentiate (IIIC) patterns from non-IIIC events and expert neurophysiologists.

Interrater Reliability of Expert Electroencephalographers Identifying Seizures and Rhythmic and Periodic Patterns in EEGs.

BACKGROUND AND OBJECTIVES: The validity of brain monitoring using electroencephalography (EEG), particularly to guide care in patients with acute or critical illness, requires that experts can reliably identify seizures and other potentially harmful rhythmic and periodic brain activity, collectively referred to as "ictal-interictal-injury continuum" (IIIC). Previous interrater reliability (IRR) studies are limited by small samples and selection bias. This study was conducted to assess the reliability of experts in identifying IIIC. METHODS: This prospective analysis included 30 experts with subspecialty clinical neurophysiology training from 18 institutions. Experts independently scored varying numbers of ten-second EEG segments as "seizure (SZ)," "lateralized periodic discharges (LPDs)," "generalized periodic discharges (GPDs)," "lateralized rhythmic delta activity (LRDA)," "generalized rhythmic delta activity (GRDA)," or "other." EEGs were performed for clinical indications at Massachusetts General Hospital between 2006 and 2020. Primary outcome measures were pairwise IRR (average percent agreement [PA] between pairs of experts) and majority IRR (average PA with group consensus) for each class and beyond chance agreement (κ). Secondary outcomes were calibration of expert scoring to group consensus, and latent trait analysis to investigate contributions of bias and noise to scoring variability. RESULTS: Among 2,711 EEGs, 49% were from women, and the median (IQR) age was 55 (41) years. In total, experts scored 50,697 EEG segments; the median [range] number scored by each expert was 6,287.5 [1,002, 45,267]. Overall pairwise IRR was moderate (PA 52%, κ 42%), and majority IRR was substantial (PA 65%, κ 61%). Noise-bias analysis demonstrated that a single underlying receiver operating curve can account for most variation in experts' false-positive vs true-positive characteristics (median [range] of variance explained ([Formula: see text]): 95 [93, 98]%) and for most variation in experts' precision vs sensitivity characteristics ([Formula: see text]: 75 [59, 89]%). Thus, variation between experts is mostly attributable not to differences in expertise but rather to variation in decision thresholds. DISCUSSION: Our results provide precise estimates of expert reliability from a large and diverse sample and a parsimonious theory to explain the origin of disagreements between experts. The results also establish a standard for how well an automated IIIC classifier must perform to match experts. CLASSIFICATION OF EVIDENCE: This study provides Class II evidence that an independent expert review reliably identifies ictal-interictal injury continuum patterns on EEG compared with expert consensus.

Automated EEG-based prediction of delayed cerebral ischemia after subarachnoid hemorrhage.

OBJECTIVE: Delayed cerebral ischemia (DCI) is a leading complication of aneurysmal subarachnoid hemorrhage (SAH) and electroencephalography (EEG) is increasingly used to evaluate DCI risk. Our goal is to develop an automated DCI prediction algorithm integrating multiple EEG features over time. METHODS: We assess 113 moderate to severe grade SAH patients to develop a machine learning model that predicts DCI risk using multiple EEG features. RESULTS: Multiple EEG features discriminate between DCI and non-DCI patients when aligned either to SAH time or to DCI onset. DCI and non-DCI patients have significant differences in alpha-delta ratio (0.08 vs 0.05, p < 0.05) and percent alpha variability (0.06 vs 0.04, p < 0.05), Shannon entropy (p < 0.05) and epileptiform discharge burden (205 vs 91 discharges per hour, p < 0.05) based on whole brain and vascular territory averaging. Our model improves predictions by emphasizing the most informative features at a given time with an area under the receiver-operator curve of 0.73, by day 5 after SAH and good calibration between 48-72 hours (calibration error 0.13). CONCLUSIONS: Our proposed model obtains good performance in DCI prediction. SIGNIFICANCE: We leverage machine learning to enable rapid, automated, multi-featured EEG assessment and has the potential to increase the utility of EEG for DCI prediction.