Search

Background: The objective of this study was to define clinically meaningful phenotypes of intracerebral hemorrhage (ICH) using machine learning., Methods: We used patient data from two US medical centers and the Antihypertensive Treatment of Acute Cerebral Hemorrhage-II clinical trial. We used k-prototypes to partition patient admission data. We then used silhouette method calculations and elbow method heuristics to optimize the clusters. Associations between phenotypes, complications (e.g., seizures), and functional outcomes were assessed using the Kruskal-Wallis H-test or χ 2 test., Results: There were 916 patients; the mean age was 63.8 ± 14.1 years, and 426 patients were female (46.5%). Three distinct clinical phenotypes emerged: patients with small hematomas, elevated blood pressure, and Glasgow Coma Scale scores > 12 (n = 141, 26.6%); patients with hematoma expansion and elevated international normalized ratio (n = 204, 38.4%); and patients with median hematoma volumes of 24 (interquartile range 8.2-59.5) mL, who were more frequently Black or African American, and who were likely to have intraventricular hemorrhage (n = 186, 35.0%). There were associations between clinical phenotype and seizure (P = 0.024), length of stay (P = 0.001), discharge disposition (P < 0.001), and death or disability (modified Rankin Scale scores 4-6) at 3-months' follow-up (P < 0.001). We reproduced these three clinical phenotypes of ICH in an independent cohort (n = 385) for external validation., Conclusions: Machine learning identified three phenotypes of ICH that are clinically significant, associated with patient complications, and associated with functional outcomes. Cerebellar hematomas are an additional phenotype underrepresented in our data sources., Competing Interests: Conflict of interest: The authors declare no conflicts of interest. Ethical Approval/Informed Consent: A waiver of informed consent was obtained from the institutional review boards (Northwestern University STU00213824 and Johns Hopkins University) for this research because patients were not contacted, nor was their care changed., (© 2024. Springer Science+Business Media, LLC, part of Springer Nature and Neurocritical Care Society.)

Purpose To develop a highly generalizable weakly supervised model to automatically detect and localize image-level intracranial hemorrhage (ICH) by using study-level labels. Materials and Methods In this retrospective study, the proposed model was pretrained on the image-level Radiological Society of North America dataset and fine-tuned on a local dataset by using attention-based bidirectional long short-term memory networks. This local training dataset included 10 699 noncontrast head CT scans in 7469 patients, with ICH study-level labels extracted from radiology reports. Model performance was compared with that of two senior neuroradiologists on 100 random test scans using the McNemar test, and its generalizability was evaluated on an external independent dataset. Results The model achieved a positive predictive value (PPV) of 85.7% (95% CI: 84.0, 87.4) and an area under the receiver operating characteristic curve of 0.96 (95% CI: 0.96, 0.97) on the held-out local test set ( n = 7243, 3721 female) and 89.3% (95% CI: 87.8, 90.7) and 0.96 (95% CI: 0.96, 0.97), respectively, on the external test set ( n = 491, 178 female). For 100 randomly selected samples, the model achieved performance on par with two neuroradiologists, but with a significantly faster ( P < .05) diagnostic time of 5.04 seconds per scan (vs 86 seconds and 22.2 seconds for the two neuroradiologists, respectively). The model's attention weights and heatmaps visually aligned with neuroradiologists' interpretations. Conclusion The proposed model demonstrated high generalizability and high PPVs, offering a valuable tool for expedited ICH detection and prioritization while reducing false-positive interruptions in radiologists' workflows. Keywords: Computer-Aided Diagnosis (CAD), Brain/Brain Stem, Hemorrhage, Convolutional Neural Network (CNN), Transfer Learning Supplemental material is available for this article. © RSNA, 2024 See also the commentary by Akinci D'Antonoli and Rudie in this issue.

Objective: Hematoma expansion (HE) predicts disability and death after acute intracerebral hemorrhage (ICH). Aspirin and anticoagulants have been associated with HE. We tested the hypothesis that P2Y12 inhibitors predict subsequent HE in patients. We explored laboratory measures of P2Y12 inhibition and dual antiplatelet therapy with aspirin (DAPT)., Methods: We prospectively identified patients with ICH. Platelet activity was measured with the VerifyNow-P2Y12 assay. Hematoma volumes for initial and follow-up CTs were calculated using a validated semi-automated technique. HE was defined as the difference between hematoma volumes on the initial and follow-up CT scans. Nonparametric statistics were performed with Kruskal-Wallis H, and correction for multiple comparisons performed with Dunn's test., Results: In 194 patients, 15 (7.7%) were known to take a P2Y12 inhibitor (clopidogrel in all but one). Patients taking a P2Y12 inhibitor had more HE compared to patients not taking a P2Y12 inhibitor (3.5 [1.2-11.9] vs. 0.1 [-0.8-1.4] mL, p = 0.004). Patients taking DAPT experienced the most HE (7.2 [2.6-13.8] vs. 0.0 [-1.0-1.1] mL, p = 0.04). The use of P2Y12 inhibitors was associated with less P2Y12 activity (178 [149-203] vs. 288 [246-319] P2Y12 reaction units, p = 0.005)., Interpretation: Patients taking a P2Y12 inhibitor had more HE and less P2Y12 activity. The effect was most pronounced in patients on DAPT, suggesting a synergistic effect of P2Y12 inhibitors and aspirin with respect to HE. Acute reversal of P2Y12 inhibitors in acute ICH requires further study., (© 2024 The Authors. Annals of Clinical and Translational Neurology published by Wiley Periodicals LLC on behalf of American Neurological Association.)

Objectives: Four-factor prothrombin complex concentrate (4-PCC) is recommended for rapid reversal of vitamin K antagonists (VKAs) such as warfarin, yet optimal dosing remains uncertain., Data Sources: A systematic review was conducted of PubMed, Embase, and Ovid MEDLINE (Wolters Kluwer) databases from January 2000 to August 2023 for clinical studies comparing fixed- vs. variable-dose 4-PCC for emergent VKA reversal with at least one reported clinical outcome., Study Selection: Abstracts and full texts were assessed independently and in duplicate by two reviewers., Data Extraction: Data were extracted independently and in duplicate by two reviewers using predefined extraction forms., Data Synthesis: The analysis comprised three randomized trials and 16 cohort studies comprising a total of 323 participants in randomized trials (161 in fixed dosage and 162 in variable dosage) and 1912 patients in cohort studies (858 in fixed-dose and 1054 in variable dose). Extracranial bleeding was the predominant indication, while intracranial hemorrhage varied. Overall, a fixed-dose regimen may be associated with a lower dose of 4-PCC and results in a reduction in 4-PCC administration time compared with a variable-dose regimen. A fixed-dose regimen also likely results in increased clinical hemostasis. While there is no clear difference between the two regimens in terms of achieving a goal international normalized ratio (INR) less than 2, a fixed-dose regimen is less likely to achieve a goal INR less than 1.5. High certainty evidence indicates that the fixed-dose regimen reduces both mortality and the occurrence of thromboembolic events. Additional subgroup analyses provides exploratory data to guide future studies., Conclusions: A fixed-dose regimen for 4-PCC administration provides benefits over a variable-dose regimen in terms of dose reduction, faster administration time, improved clinical hemostasis, and reduced mortality and thromboembolic events. Further studies are warranted to better refine the optimal fixed-dose regimen., Competing Interests: Dr. Naidech’s institution received funding from the National Institute of Neurological Disorders; he received funding from the National Institutes of Health (NIH); he disclosed that they participated in a Society of Critical Care Medicine board review course; and he received support for article research from the NIH. Dr. Potts disclosed that he has stock in a biomedical device company. The remaining authors have disclosed that they do not have any potential conflicts of interest., (Copyright © 2024 The Author(s). Published by Wolters Kluwer Health, Inc. on behalf of the Society of Critical Care Medicine and Wolters Kluwer Health, Inc.)

During the first COVID surge, multiple changes in nurse staffing and workflows were made to support care delivery in a resource-constrained environment. We hypothesized that there was a higher rate of inpatient falls during the COVID surge. Furthermore, we predicted that an automated predictive analytic algorithm would perform as well as the Johns Hopkins Fall Risk Assessment. A retrospective review of falls for 3 months before and the first 3 months of the first COVID surge was conducted. We determined the total number of falls and the overall fall rate and examined the distribution of scores and accuracy of fall predictive models for both groups. There was a statistically significant increase in fall rate during the first 3 months of the COVID surge compared with the 3 prior months (2.48/1000 patient-days vs 1.89/1000 patient-days respectively; P = .041). The Johns Hopkins instrument had a greater sensitivity of 78.9% compared with 57.0% for the predictive analytic model. Specificity and accuracy of the predictive analytic model were higher than the Johns Hopkins instrument (71.3% vs 54.1% and 71.2% vs 54.3%, respectively). These findings suggest that the automated predictive analytic model could be used in a resource-constrained environment to accurately classify patients' risk of fall., (Copyright © 2023 Wolters Kluwer Health, Inc. All rights reserved.)

Background: Acute blood pressure (BP) reduction is standard of care after acute intracerebral haemorrhage (ICH). More acute BP reduction is associated with acute kidney injury (AKI). It is not known if the choice of antihypertensive medications affects the risk of AKI., Methods: We analysed data from the ATACH-II clinical trial. AKI was defined by the Kidney Disease: Improving Global Outcomes criteria. We analysed antihypertensive medication from two sources. The first was a case report form that specified the use of labetalol, diltiazem, urapidil or other. We tested the hypothesis that the secondary medication was associated with AKI with χ 2 test. Second, we tested the hypotheses the dosage of diltiazem was associated with AKI using Mann-Whitney U test., Results: AKI occurred in 109 of 1000 patients (10.9%). A higher proportion of patients with AKI received diltiazem after nicardipine (12 (29%) vs 21 (12%), p=0.03). The 95%ile (90%-99% ile) of administered diltiazem was 18 (0-130) mg in patients with AKI vs 0 (0-30) mg in patients without AKI (p=0.002). There was no apparent confounding by indication for diltiazem use., Conclusions: The use of diltiazem, and more diltiazem, was associated with AKI in patients with acute ICH., Competing Interests: Competing interests: None declared., (© Author(s) (or their employer(s)) 2023. Re-use permitted under CC BY-NC. No commercial re-use. See rights and permissions. Published by BMJ.)

The last decade has seen significant advances in the accumulation of medical data, the computational techniques to analyze that data, and corresponding improvements in management. Interventions such as thrombolytics and mechanical thrombectomy improve patient outcomes after stroke in selected patients; however, significant gaps remain in our ability to select patients, predict complications, and understand outcomes. Big data and the computational methods needed to analyze it can address these gaps. For example, automated analysis of neuroimaging to estimate the volume of brain tissue that is ischemic and salvageable can help triage patients for acute interventions. Data-intensive computational techniques can perform complex risk calculations that are too cumbersome to be completed by humans, resulting in more accurate and timely prediction of which patients require increased vigilance for adverse events such as treatment complications. To handle the accumulation of complex medical data, a variety of advanced computational techniques referred to as machine learning and artificial intelligence now routinely complement traditional statistical inference. In this narrative review, we explore data-intensive techniques in stroke research, how it has informed the management of stroke patients, and how current work could shape clinical practice in the future., (© 2023. The American Society for Experimental Neurotherapeutics, Inc.)

Randomized clinical trials of acute stroke have led to major advances in acute stroke therapy over the past decade. Despite these successes, recruitment in acute trials is often difficult. We outline challenges in recruitment for acute stroke trials and present potential solutions, which can increase the speed and decrease the cost of identifying new treatments for acute stroke. One of the largest opportunities to increase the speed of enrollment and make trials more generalizable is expansion of inclusion criteria whose impact on expected recruitment can be assessed by epidemiologic and registry databases. Another barrier to recruitment besides the number of eligible patients is availability of study investigators limited to business hours, which may be helped by financial support for after-hours call. The wider use of telemedicine has accelerated quicker stroke treatment at many hospitals and has the potential to accelerate research enrollment but requires training of clinical investigators who are often inexperienced with this approach. Other potential solutions to enhance recruitment include rapid prehospital notification of clinical investigators of potential patients, use of mobile stroke units, advances in the process of emergency informed consent, storage of study medication in the emergency department, simplification of study treatments and data collection, education of physicians to improve equipoise and enthusiasm for randomization of patients within a trial, and clear recruitment plans, and even potentially coenrollment, when there are competing trials at sites. Without successful recruitment, scientific advances and clinical benefit for acute stroke patients will lag.

Introduction: Intracerebral hemorrhage is the deadliest form of stroke. Hematoma expansion, growth of the hematoma between the baseline computed tomography scan and a follow-up computed tomography scan at 24 ± 6 h, predicts long-term disability or death. Recombinant factor VIIa (rFVIIa) has reduced hematoma expansion in previous clinical trials with a variable effect on clinical outcomes, with the greatest impact on hematoma expansion and potential benefit when administered within 2 h of symptom onset., Methods: Factor VIIa for Hemorrhagic Stroke Treatment at Earliest Possible Time (FASTEST, NCT03496883) is a randomized controlled trial that will enroll 860 patients at ∼100 emergency departments and mobile stroke units in five countries. Patients are eligible for enrollment if they have acute intracerebral hemorrhage within 2 h of symptom onset confirmed by computed tomography, a hematoma volume of 2 to 60 mL, no or small volumes of intraventricular hemorrhage, do not take anticoagulant medications or concurrent heparin/heparinoids (antiplatelet medications are permissible), and are not deeply comatose. Enrolled patients will receive rFVIIa 80 µg/kg or placebo intravenously over 2 min. The primary outcome measure is the distribution of the ordinal modified Rankin Scale at 180 days. FASTEST is monitored by a Data Safety Monitoring Board. Safety endpoints include thrombotic events (e.g. myocardial infarction). Human subjects research is monitored by an external Institutional Review Board in participating countries., Discussion: In the US, FASTEST will be first NIH StrokeNet Trial with an Exception from Informed Consent which allows enrollment of non-communicative patients without an immediately identifiable proxy.

Background: Seizures are a harmful complication of acute intracerebral hemorrhage (ICH). "Early" seizures in the first week after ICH are a risk factor for deterioration, later seizures, and herniation. Ideally, seizure medications after ICH would only be administered to patients with a high likelihood to have seizures. We developed and validated machine learning (ML) models to predict early seizures after ICH., Methods: We used two large datasets to train and then validate our models in an entirely independent test set. The first model ("CAV") predicted early seizures from a subset of variables of the CAVE score (a prediction rule for later seizures)-cortical hematoma location, age less than 65 years, and hematoma volume greater than 10 mL-whereas early seizure was the dependent variable. We attempted to improve on the "CAV" model by adding anticoagulant use, antiplatelet use, Glasgow Coma Scale, international normalized ratio, and systolic blood pressure ("CAV + "). For each model we used logistic regression, lasso regression, support vector machines, boosted trees (Xgboost), and random forest models. Final model performance was reported as the area under the receiver operating characteristic curve (AUC) using receiver operating characteristic models for the test data. The setting of the study was two large academic institutions: institution 1, 634 patients; institution 2, 230 patients. There were no interventions., Results: Early seizures were predicted across the ML models by the CAV score in test data, (AUC 0.72, 95% confidence interval 0.62-0.82). The ML model that predicted early seizure better in the test data was Xgboost (AUC 0.79, 95% confidence interval 0.71-0.87, p = 0.04) compared with the CAV model AUC., Conclusions: Early seizures after ICH are predictable. Models using cortical hematoma location, age less than 65 years, and hematoma volume greater than 10 mL had a good accuracy rate, and performance improved with more independent variables. Additional methods to predict seizures could improve patient selection for monitoring and prophylactic seizure medications., (© 2022. Springer Science+Business Media, LLC, part of Springer Nature and Neurocritical Care Society.)

Background: To test the hypothesis that appearances of intracranial hematomas on diagnostic computed tomography (CT) are not idiosyncratic and reflect a biologically plausible mechanism, we evaluated the association between hematoma appearance on CT, biomarkers of platelet activity, and antiplatelet or anticoagulant medication use prior to admission., Methods: We studied 330 consecutively identified patients from 2006 to 2019. Biomarkers of platelet activity (platelet aspirin assay) and medication history (aspirin, clopidogrel) were prospectively recorded on admission. A blinded interpreter recorded the presence of hematoma appearances from the diagnostic scan. Associations were tested with parametric or nonparametric statistics, as appropriate., Results: The black hole sign (101, 30%) was most prevalent, followed by the island sign (57, 17%) and blend sign (32, 10%). There was reduced platelet activity in patients with a black hole sign (511 [430-610] vs. 562 [472-628] aspirin reaction units, P = 0.01) or island sign (505 [434-574] vs. 559 [462-629] aspirin reaction units, P = 0.004). Clopidogrel use prior to admission was associated with the black hole sign (odds ratio 2.25, 95% confidence interval 1.02-4.98, P = 0.04)., Conclusions: In patients with acute intracerebral hemorrhage, hematoma appearances on CT are associated with biomarkers of platelet activity and clopidogrel use prior to admission. Appearances of intracranial hematomas on CT may reflect reduced hemostasis from antiplatelet medication use., (© 2021. Springer Science+Business Media, LLC, part of Springer Nature and Neurocritical Care Society.)

Background and Purpose: Prioritizing reading of noncontrast head CT examinations through an automated triage system may improve time to care for patients with acute neuroradiologic findings. We present a natural language-processing approach for labeling findings in noncontrast head CT reports, which permits creation of a large, labeled dataset of head CT images for development of emergent-finding detection and reading-prioritization algorithms., Materials and Methods: In this retrospective study, 1002 clinical radiology reports from noncontrast head CTs collected between 2008 and 2013 were manually labeled across 12 common neuroradiologic finding categories. Each report was then encoded using an n-gram model of unigrams, bigrams, and trigrams. A logistic regression model was then trained to label each report for every common finding. Models were trained and assessed using a combination of L2 regularization and 5-fold cross-validation., Results: Model performance was strongest for the fracture, hemorrhage, herniation, mass effect, pneumocephalus, postoperative status, and volume loss models in which the area under the receiver operating characteristic curve exceeded 0.95. Performance was relatively weaker for the edema, hydrocephalus, infarct, tumor, and white-matter disease models (area under the receiver operating characteristic curve > 0.85). Analysis of coefficients revealed finding-specific words among the top coefficients in each model. Class output probabilities were found to be a useful indicator of predictive error on individual report examples in higher-performing models., Conclusions: Combining logistic regression with n-gram encoding is a robust approach to labeling common findings in noncontrast head CT reports., (© 2022 by American Journal of Neuroradiology.)

Background: Intracerebral hemorrhage (ICH) is the deadliest form of stroke. In observational studies, lower serum magnesium has been linked to more hematoma expansion (HE) and intracranial hemorrhage, implying that supplemental magnesium sulfate is a potential acute treatment for patients with ICH and could reduce HE. FAST-MAG (Field Administration of Stroke Therapy - Magnesium) was a clinical trial of magnesium sulfate started prehospital in patients with acute stroke within 2 hours of last known well enrolled. CT was not required prior to enrollment, and several hundred patients with acute ICH were enrolled. In this ancillary analysis, we assessed the effect of magnesium sulfate treatment upon HE in patients with acute ICH., Methods: We retrospectively analyzed data that were prospectively collected in the FAST-MAG study. Patients received intravenous magnesium sulfate or matched placebo within 2 hours of onset. We compared HE among patients allocated to intravenous magnesium sulfate or placebo with a Mann-Whitney U . We used the same method to compare neurological deficit severity (National Institutes of Health Stroke Scale) and global disability (modified Rankin Scale) at 3 months., Results: Among 268 patients with ICH meeting study entry criteria, mean 65.4±13/4 years, 33% were female, and 211 (79%) had a history of hypertension. Initial deficit severities were median (interquartile range) of 4 (3-5) on the Los Angeles Motor Scale in the field and National Institutes of Health Stroke Scale score of 16 (9.5-25.5) early after hospital arrival. Follow-up brain imaging was performed a median of 17.1 (11.3-22.7) hours after first scan. The magnesium and placebo groups did not statistically differ in hematoma volume on arrival, 10.1 (5.6-28.7) versus 12.4 (5.6-28.7) mL ( P =0.6), or HE, 2.0 (0.1-7.4) versus 1.5 (-0.2 to 8) mL ( P =0.5). There was no difference in functional outcomes (modified Rankin Scale score of 3-6), 59% versus 50% ( P =0.5)., Conclusions: Magnesium sulfate did not reduce HE or improve functional outcomes at 90 days. A benefit for patients with initial hypomagnesemia was not addressed., Registration: URL: https://www., Clinicaltrials: gov; Unique identifier: NCT00059332.

Background: Fall prevention is a patient safety and economic priority for health care organizations. An automated model within the electronic medical record (EMR) that accurately predicts risk for falling would be valuable for mitigation of inpatient falls. The aim of this study was to validate the reliability of an EMR-based computerized predictive model (ROF Model) for inpatient falls. The hypothesis was that the ROF Model would be similar to the Johns Hopkins Fall Risk Assessment Tool (JHFRAT) in predicting fall events in the inpatient setting at a large academic medical center., Methods: This observational study compared the falls predicted by each model against actual falls over an eight-month period in a single institution. Descriptive statistics were used to compare the distribution of scores and accuracy of fall risk categorization for each model immediately preceding a fall., Results: For 35,709 inpatient encounters, the total fall rate was 0.92%. Of the 329 patients who fell, 60.8% were high risk by ROF Model (fall rate 1.82%), and 75.4% were high risk by JHFRAT (fall rate 1.39%). The ROF Model had a better specificity than the JHFRAT (69.7% vs. 49.2%) but a similar C-statistic (0.717 vs. 0.702) and a lower sensitivity (60.8% vs. 79.3%)., Conclusion: The performance of the ROF Model was similar to that of the JHFRAT in predicting inpatient falls. This comparison provides evidence to support a transition to a more automated process. Future studies will determine prospectively if implementation of the ROF Model will reduce falls in the inpatient setting., (Copyright © 2021. Published by Elsevier Inc.)

Damage to specific brain circuits can cause specific neuropsychiatric symptoms. Therapeutic stimulation to these same circuits may modulate these symptoms. To determine whether these circuits converge, we studied depression severity after brain lesions (n = 461, five datasets), transcranial magnetic stimulation (n = 151, four datasets) and deep brain stimulation (n = 101, five datasets). Lesions and stimulation sites most associated with depression severity were connected to a similar brain circuit across all 14 datasets (P < 0.001). Circuits derived from lesions, deep brain stimulation and transcranial magnetic stimulation were similar (P < 0.0005), as were circuits derived from patients with major depression versus other diagnoses (P < 0.001). Connectivity to this circuit predicted out-of-sample antidepressant efficacy of transcranial magnetic stimulation and deep brain stimulation sites (P < 0.0001). In an independent analysis, 29 lesions and 95 stimulation sites converged on a distinct circuit for motor symptoms of Parkinson's disease (P < 0.05). We conclude that lesions, transcranial magnetic stimulation and DBS converge on common brain circuitry that may represent improved neurostimulation targets for depression and other disorders., (© 2021. The Author(s), under exclusive licence to Springer Nature Limited.)

Background: Intracranial hemorrhage (ICH) is a devastating complication for patients with ventricular assist devices (VADs). The safety of emergent anticoagulation reversal with four-factor prothrombin complex concentrate (PCC) and optimal timing of anticoagulation resumption are not clear. In addition, lactate dehydrogenase (LDH) is used as a biomarker for thromboembolic risk, but its utility in guiding anticoagulation management after reversal with PCC has not be described., Methods: We retrospectively reviewed a consecutive series of patients with VADs presenting with ICH between 2014 and 2020 who received four-factor PCC for rapid anticoagulation reversal. We collected the timing of PCC administration, timing of resumption of anticoagulation, survival, occurrence of thromboembolic events, and LDH levels throughout hospitalization., Results: We identified 16 ICH events in 14 patients with VADs treated with rapid anticoagulation reversal using four-factor PCC (11 intraparenchymal, 4 subdural, 1 subarachnoid hemorrhage). PCC was administered at a mean of 3.3 ± 0.3 h after imaging diagnosis of ICH. Overall mortality was 63%. Survivors had higher presenting Glasgow Coma Scale (median 15, interquartile range [IQR] 15-15 versus 14, IQR 8-14.7, P = 0.041). In all six instances where the patient survived, anticoagulation was resumed on average 9.16 ± 1.62 days after reversal. There were no thromboembolic events prior to resumption of anticoagulation. Three events occurred after anticoagulation resumption and within 3 months of reversal: VAD thrombosis in a patient with thrombosis at the time of reversal, ischemic stroke, and readmission for elevated LDH in the setting of subtherapeutic international normalized ratio., Conclusions: Our limited series found no thromboembolic complications immediately following anticoagulation reversal with PCC prior to resumption of anticoagulation. LDH trends may be useful to monitor thromboembolic risk after reversal., (© 2021. Springer Science+Business Media, LLC, part of Springer Nature and Neurocritical Care Society.)

Patients with aneurysmal subarachnoid hemorrhage (ruptured brain aneurysm) often have reduced health-related quality of life at follow-up in multiple domains (e.g., cognitive function and social function). We tested the hypothesis that there are distinct patterns of patient outcomes across domains of health-related quality of life, "complex patient outcomes," in survivors of subarachnoid hemorrhage., Design: Patients with subarachnoid hemorrhage were prospectively identified. Clinical data were prospectively recorded. Health-related quality of life was prospectively assessed at 3-month follow-up using the National Institutes of Health Patient Reported Outcomes Measurement Information System and neuro-quality of life in the domains of mobility, cognitive function, satisfaction with social roles, and depression. We used k-means clustering to analyze prospectively recorded health-related quality of life data, identifying clusters of complex patient outcomes. Decision tree analysis identified index hospital stay factors predictive of a patient having a particular complex patient outcome at follow-up., Setting: Academic medical center., Patients: One hundred three survivors of subarachnoid hemorrhage., Interventions: None., Measurements and Main Results: We analyzed 103 patients, of whom 75 (72.8%) were female, and mean age was 53.6 ± 13.4 years. There were three complex patient outcomes: health-related quality of life greater than 1 sd better than the U.S. mean across all domains ( n = 23, 22.3%), health-related quality of life greater than 1 sd worse than U.S. mean across all domains ( n = 26, 25.2%), and satisfaction with social roles greater than 0.5 sd worse than U.S. mean with cognitive function, depression, and mobility scores near the U.S. mean ( n = 54, 52.4%). In decision tree analysis, hospital disposition and Hunt and Hess Grade were associated with complex patient outcome., Conclusions: Complex patient outcomes across multiple domains of health-related quality of life at follow-up after subarachnoid hemorrhage are distinct and may be predictable., Competing Interests: Ms. Murphy reports funding from T32 LM012203, Ms. Wang reports funding from UL1 TR001422, Dr. Luo reports funding from R01 LM013337 and GM105688, and Dr. Naidech reports funding from National Institutes of Health R01 NS110779 and U01 NS110772. The remaining authors have disclosed that they do not have any potential conflicts of interest., (Copyright © 2021 The Authors. Published by Wolters Kluwer Health, Inc. on behalf of the Society of Critical Care Medicine.)

Background and Purpose: This study aims to determine whether machine learning (ML) and natural language processing (NLP) from electronic health records (EHR) improve the prediction of 30-day readmission after stroke. Methods: Among index stroke admissions between 2011 and 2016 at an academic medical center, we abstracted discrete data from the EHR on demographics, risk factors, medications, hospital complications, and discharge destination and unstructured textual data from clinician notes. Readmission was defined as any unplanned hospital admission within 30 days of discharge. We developed models to predict two separate outcomes, as follows: (1) 30-day all-cause readmission and (2) 30-day stroke readmission. We compared the performance of logistic regression with advanced ML algorithms. We used several NLP methods to generate additional features from unstructured textual reports. We evaluated the performance of prediction models using a five-fold validation and tested the best model in a held-out test dataset. Areas under the curve (AUCs) were used to compare discrimination of each model. Results: In a held-out test dataset, advanced ML methods along with NLP features out performed logistic regression for all-cause readmission (AUC, 0.64 vs. 0.58; p < 0.001) and stroke readmission prediction (AUC, 0.62 vs. 0.52; p < 0.001). Conclusion: NLP-enhanced machine learning models potentially advance our ability to predict readmission after stroke. However, further improvement is necessary before being implemented in clinical practice given the weak discrimination., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2021 Lineback, Garg, Oh, Naidech, Holl and Prabhakaran.)

Penetrating brain injury (PBI) is the most devastating type of traumatic brain injury. Development of coagulopathy in the acute setting of PBI, though common, remains of unclear significance as does its reversal. The aim of this study is to investigate the relationship between coagulopathy and clinical presentation, radiographical features, and outcome in civilian patients with PBI. Eighty-nine adult patients with PBI at a Level I trauma center in Chicago, Illinois who survived acute resuscitation and with available coagulation profile were analyzed. Coagulopathy was defined as international normalized ratio [INR] >1.3, platelet count <100,000 /μL, or partial thromboplastin time >37 sec. Median age (interquartile range; IQR) of our cohort was 27 (21-35) years, and 74 (83%) were male. The intent was assault in 74 cases (83%). The mechanism of PBI was gunshot wound in all patients. Forty patients (45%) were coagulopathic at presentation. In a multiple regression model, coagulopathy was associated with lower Glasgow Coma Scale (GCS)-Motor score (odds ratio [OR], 0.67; confidence interval [CI], 0.48-0.94; p  = 0.02) and transfusion of blood products (OR, 3.91; CI, 1.2-12.5; p  = 0.02). Effacement of basal cisterns was the only significant radiographical features associated with coagulopathy (OR, 3.34; CI, 1.08-10.37; p  = 0.04). Mortality was found to be significantly more common in coagulopathic patients (73% vs. 25%; p  < 0.001). However, in our limited sample, reversal of coagulopathy at 24 h was not associated with a statistically significant improvement in outcome. The triad of coagulopathy, low post-resuscitation GCS, and radiographical effacement of basal cisterns identify a particularly ominous phenotype of PBI. The role, and potential reversal of, coagulopathy in this group warrants further investigation.

Objectives: Early seizures are a common complication of intracerebral hemorrhage, occurring in ~10% of patients. However, the independent effect of early seizures on patient outcomes, particularly health-related quality of life, is unclear. Without a potential benefit to patient outcomes, the widespread use (~40%) of prophylactic seizure medications has no reasonable chance of improving patient outcomes. We tested the hypothesis that health-related quality of life at follow-up is different between patients with and without early seizures (and secondarily, with nonconvulsive status epilepticus) after intracerebral hemorrhage., Design: Patients with intracerebral hemorrhage were enrolled in an observational cohort study that prospectively collected clinical data and health-related quality of life at follow-up., Setting: Academic medical center., Patients: One-hundred thirty-three patients whose health-related quality of life was assessed 3 months after intracerebral hemorrhage onset., Measurements and Main Results: Health-related quality of life was obtained at 3 months after intracerebral hemorrhage onset. T Scores of health-related quality of life were modeled with multivariable linear models accounting for severity with the intracerebral hemorrhage Score and hematoma location. Health-related quality of life was measured with National Institutes of Health Patient Reported Outcomes Measurement Information System/Neuroquality of life, expressed in T Scores (U.S. normal 50 ± 10). The modified Rankin Scale (a global measure) was a secondary outcome. There were 12 patients (9%) with early seizures. T Scores of health-related quality of life at follow-up were lower (worse) in patients with early seizure compared with patients without an early seizure (44 [32.75-51.85] vs 30.25 [18.9-39.15]; p = 0.04); results for other domains of health-related quality of life were similar. The association persisted in multivariable models. There was no association between early seizures and prophylactic seizure medications (p = 0.4). Results for patients with nonconvulsive status epilepticus were similar. There was no association between early seizures and the modified Rankin Scale at 3 months., Conclusions: Early seizures and nonconvulsive status epilepticus were associated with lower health-related quality of life at follow-up in survivors of intracerebral hemorrhage., (Copyright © 2021 by the Society of Critical Care Medicine and Wolters Kluwer Health, Inc. All Rights Reserved.)

This invited special report is based on an award presentation at the World Stroke Organization/European Stroke Organization Conference in November of 2020 outlining progress in the acute management of intracerebral hemorrhage (ICH) over the past 35 years. ICH is the second most common and the deadliest type of stroke for which there is no scientifically proven medical or surgical treatment. Prospective studies from the 1990s onward have demonstrated that most growth of spontaneous ICH occurs within the first 2 to 3 hours and that growth of ICH and resulting volumes of ICH and intraventricular hemorrhage are modifiable factors that can improve outcome. Trials focusing on early treatment of elevated blood pressure have suggested a target systolic blood pressure of 140 mm Hg, but none of the trials were positive by their primary end point. Hemostatic agents to decrease bleeding in spontaneous ICH have included desmopressin, tranexamic acid, and rFVIIa (recombinant factor VIIa) without clear benefit, and platelet infusions which were associated with harm. Hemostatic agents delivered within the first several hours have the greatest impact on growth of ICH and potentially on outcome. No large Phase III surgical ICH trial has been positive by primary end point, but pooled analyses suggest that earlier ICH removal is more likely to be beneficial. Recent trials emphasize maximization of clot removal and minimizing brain injury from the surgical approach. The future of ICH therapy must focus on delivery of medical and surgical therapies as soon as possible if we are to improve outcomes.

Background/objective: Demonstrating a benefit of acute treatment to patients with intracerebral hemorrhage (ICH) requires identifying which patients have a potentially modifiable outcome, where treatment could favorably shift a patient's expected outcome. A decision rule for which patients have a modifiable outcome could improve the targeting of treatments. We sought to determine which patients with ICH have a modifiable outcome., Methods: Patients with ICH were prospectively identified at two institutions. Data on hematoma volumes, medication histories, and other variables of interest were collected. ICH outcomes were evaluated using the modified Rankin Scale (mRS), assessed at 14 days and 3 months after ICH, with "good outcome" defined as 0-3 (independence or better) and "poor outcome" defined as 4-6 (dependence or worse). Supervised machine learning models identified the best predictors of good versus poor outcomes at Institution 1. Models were validated using repeated fivefold cross-validation as well as testing on the entirely independent sample at Institution 2. Model fit was assessed with area under the ROC curve (AUC)., Results: Model performance at Institution 1 was strong for both 14-day (AUC of 0.79 [0.77, 0.81] for decision tree, 0.85 [0.84, 0.87] for random forest) and 3 month (AUC of 0.75 [0.73, 0.77] for decision tree, 0.82 [0.80, 0.84] for random forest) outcomes. Independent predictors of functional outcome selected by the algorithms as important included hematoma volume at hospital admission, hematoma expansion, intraventricular hemorrhage, overall ICH Score, and Glasgow Coma Scale. Hematoma expansion was the only potentially modifiable independent predictor of outcome and was compatible with "good" or "poor" outcome in a subset of patients with low hematoma volumes, good Glasgow Coma scale and premorbid modified Rankin Scale scores. Models trained on harmonized data also predicted patient outcomes well at Institution 2 using decision tree (AUC 0.69 [0.63, 0.75]) and random forests (AUC 0.78 [0.72, 0.84])., Conclusions: Patient outcomes are predictable to a high level in patients with ICH, and hematoma expansion is the sole-modifiable predictor of these outcomes across two outcome types and modeling approaches. According to decision tree analyses predicting outcome at 3 months, patients with a high Glasgow Coma Scale score, less than 44.5 mL hematoma volume at admission, and relatively low premorbid modified Rankin Score in particular have a modifiable outcome and appear to be candidates for future interventions to improve outcomes after ICH.

Allergy mention normalization is challenging because of the wide range of possible allergens including medications, foods, plants, animals, and consumer products. This paper describes the process of mapping free-text allergy information from an electronic health record (EHR) system in a university hospital to standard terminologies and migration of those data into an enterprise EHR system. The review, mapping, and migration revealed interesting issues and challenges with the free-text allergy information and the mapping in preparation for implementation in the new EHR system. These findings provide insights that can form the basis of guidelines for future mapping and migration efforts involving free-text allergy data. As part of this process, we generate and make freely available AllergyMap, a mapping between free-text entered allergy medication to standard non-proprietary ontologies. To our knowledge, this is the first such mapping available and could serve as a public resource for allergy mention normalization and system evaluation., (©2020 AMIA - All rights reserved.)

Objective: Learning healthcare systems use routinely collected data to generate new evidence that informs future practice. While implementing an electronic health record (EHR) system can facilitate this goal for individual institutions, meaningfully aggregating data from multiple institutions can be more empowering. Cosmos is a cross-institution, single EHR vendor-facilitated data aggregation tool. This work aims to describe the initiative and illustrate its potential utility through several use cases., Methods: Cosmos is designed to scale rapidly by leveraging preexisting agreements, clinical health information exchange networks, and data standards. Data are stored centrally as a limited dataset, but the customer facing query tool limits results to prevent patient reidentification., Results: In 2 years, Cosmos grew to contain EHR data of more than 60 million patients. We present practical examples illustrating how Cosmos could further efforts in chronic disease surveillance (asthma and obesity), syndromic surveillance (seasonal influenza and the 2019 novel coronavirus), immunization adherence and adverse event reporting (human papilloma virus and measles, mumps, rubella, and varicella vaccination), and health services research (antibiotic usage for upper respiratory infection)., Discussion: A low barrier of entry for Cosmos allows for the rapid accumulation of multi-institutional and mostly de-duplicated EHR data to power research and quality improvement queries characteristic of learning healthcare systems. Limitations are being vendor-specific, an "all or none" contribution model, and the lack of control over queries run on an institution's healthcare data., Conclusion: Cosmos provides a model for within-vendor data standardization and aggregation and a steppingstone for broader intervendor interoperability., Competing Interests: Conflict of Interest C.H., A.F., and S.H. reports other from Epic during the conduct of the study; employed by this company and developed the tool described as part of the role in this corporation. A.M.N. reports grants from NIH, from null, during the conduct of the study; other from Bedside Intelligence, LLC, from null, outside the submitted work.

Background: An association between spontaneous hyperventilation, delayed cerebral ischemia, and poor clinical outcomes has been reported in subarachnoid hemorrhage. We evaluated the relationship between early pCO 2 changes, ischemic lesions and outcomes in patients with intracerebral hemorrhage (ICH)., Methods: Consecutive patients with spontaneous ICH were enrolled in an observational cohort study conducted between 2006 and 2019. Patient characteristics and discharge outcome were prospectively recorded. Arterial blood gas (ABG) measurements and mechanical ventilation settings in the first 72 h of admission were retrospectively collected. MRI images were adjudicated for diffusion-restricted lesions consistent with ischemia and distant from the hematoma. We examined the associations between pCO 2 changes, ischemic lesions, and discharge outcomes by univariate and adjusted analyses., Results: ABG data were available for 220 patients. Hyperventilation occurred in 52 (28%) cases and was not associated with clinical severity. Lower initial pCO 2 was associated with greater risk of in-hospital death (OR 0.94 per mmHg, 95%CI [0.89, 0.996], p = 0.042) after adjustment for ICH Score, pneumonia and mechanical ventilation requirements. MRI data were available for 33 patients. Lower pCO 2 was associated with a higher risk of ischemic lesions, except in patients with low initial systolic blood pressure (p < 0.05 for main and blood pressure interaction effects), after adjustment for other predictors., Conclusions: In ICH patients with spontaneous ventilation, lower pCO 2 was independently associated with greater risk of in-hospital death. In patients with elevated initial blood pressure, who undergo blood pressure reduction per guideline recommendations, lower pCO 2 was associated with increased risk to develop ischemic lesions., (Copyright © 2020 Elsevier B.V. All rights reserved.)

Randomized Controlled Trials (RCTs) are considered the gold standard for measuring the efficacy of medical interventions. However, RCTs are expensive, and use a limited population. Techniques to estimate the effects of stroke interventions from observational data that minimize confounding would be useful. We used regression discontinuity design (RDD), a technique well-established in economics, on the Get With The Guidelines-Stroke (GWTG-Stroke) data set. RDD, based on regression, measures the occurrence of a discontinuity in an outcome (e.g., odds of home discharge) as a function of an intervention (e.g., alteplase) that becomes significantly more likely when crossing the threshold of a continuous variable that determines that intervention (e.g., time from symptom onset, since alteplase is only given if symptom onset is less than e.g., 3 h). The technique assumes that patients near either side of a threshold (e.g., 2.99 and 3.01 h from symptom onset) are indistinguishable other than the use of the treatment. We compared outcomes of patients whose estimated onset to treatment time fell on either side of the treatment threshold for three cohorts of patients in the GWTG-Stroke data set. This data set spanned three different treatment thresholds for alteplase (3 h, 2003-2007, N = 1,869; 3 h, 2009-2016, N = 13,086, and 4.5 h, 2009-2016, N = 6,550). Patient demographic characteristics were overall similar across the treatment thresholds. We did not find evidence of a discontinuity in clinical outcome at any treatment threshold attributable to alteplase. Potential reasons for failing to find an effect include violation of some RDD assumptions in clinical care, large sample sizes required, or already-well-chosen treatment threshold., (Copyright © 2020 Naidech, Lawlor, Xu, Fonarow, Xian, Smith, Schwamm, Matsouaka, Prabhakaran, Marinescu and Kording.)

Background and Purpose: Hemorrhages are a serious complication of brain surgery, and magnesium has shown hemostatic properties in hemorrhagic stroke and non-neurological surgeries. External ventricular drain (EVD) insertion is an advantageous model of emergency neurosurgical hemorrhage risk because it is common, standardized, and the operator is blinded to the outcome during the procedure. We tested the hypothesis that low magnesium is associated with risk of hemorrhagic complications from EVD insertion., Methods: Patients with spontaneous intracerebral hemorrhage and aneurysmal subarachnoid hemorrhage were enrolled in a prospective, observational study. Demographic and clinical variables were prospectively recorded, including serum magnesium measurements. Catheter tract hemorrhage (CTH) was measured on postoperative head computed tomography within 48 hours of EVD insertion., Results: We observed 50 CTH among 327 EVD procedures (15.3%) distributed similarly among intracerebral hemorrhage (21/116 [18.1%]) and subarachnoid hemorrhage (29/211 [13.7%]). Magnesium was lower in patients with CTH compared with those without (median 1.8 versus 2.0 mg/dL, P <0.0001). Higher magnesium was associated with lower odds of CTH (odds ratio 0.67 per 0.1 mg/dL magnesium [95% CI, 0.56-0.78], P <0.0001) after adjustment for other risk factors, with similar effect in the intracerebral hemorrhage and subarachnoid hemorrhage subgroups. Preprocedural increase in magnesium (odds ratio 0.68 [0.52-0.85]) and dose of preprocedural magnesium sulfate (odds ratio 0.67 [0.40-0.97]) were associated with reduced CTH risk after adjustment for initial magnesium and other risk factors., Conclusions: Lower magnesium at the time of EVD insertion was an independent predictor of hemorrhagic complications. Baseline risk was attenuated by preprocedural increases in magnesium, suggesting a therapeutic opportunity.

Objectives: The circadian system modulates many important physiologic processes, synchronizing tissue-specific functions throughout the body. We sought to characterize acute alterations of circadian rhythms in critically ill patients and to evaluate associations between brain dysfunction, systemic multiple organ dysfunction, environmental stimuli that entrain the circadian rhythm (zeitgebers), rest-activity rhythms, and the central circadian rhythm-controlled melatonin secretion profile., Design: Prospective study observing a cohort for 24-48 hours beginning within the first day of ICU admission., Setting: Multiple specialized ICUs within an academic medical center., Patients: Patients presenting from the community with acute onset of either intracerebral hemorrhage as a representative neurologic critical illness or sepsis as a representative systemic critical illness. Healthy control patients were studied in using modified constant routine in a clinical research unit., Interventions: None., Measurements and Main Results: Light, feeding, activity, medications, and other treatment exposures were evaluated along with validated measures of encephalopathy (Glasgow Coma Scale), multiple organ system function (Sequential Organ Failure Assessment score), and circadian rhythms (profiles of serum melatonin and its urinary metabolite 6-sulphatoxymelatonin). We studied 112 critically ill patients, including 53 with sepsis and 59 with intracerebral hemorrhage. Environmental exposures were abnormal, including light (dim), nutritional intake (reduced or absent and mistimed), and arousal stimuli (increased and mistimed). Melatonin amplitude and acrophase timing were generally preserved in awake patients but dampened and delayed with increasing encephalopathy severity. Melatonin hypersecretion was observed in patients exposed to catecholamine vasopressor infusions, but unaffected by sedatives. Change in vasopressor exposure was the only factor associated with changes in melatonin rhythms between days 1 and 2., Conclusions: Encephalopathy severity and adrenergic agonist medication exposure were the primary factors contributing to abnormal melatonin rhythms. Improvements in encephalopathy and medical stabilization did not rapidly normalize rhythms. Urinary 6-sulphatoxymelatonin is not a reliable measure of the central circadian rhythm in critically ill patients.

Background: Seizures are a morbid complication of intracerebral hemorrhage (ICH) and increase the risk for herniation, status epilepticus, and worse patient outcomes. Prophylactic levetiracetam is administered to approximately 40% of patients with ICH. It is unclear which patients are consciously selected for treatment by physicians. We sought to determine how patients are selected for treatment with prophylactic levetiracetam after ICH., Methods: We administered an adaptive conjoint analysis using decision making software to an NIH Stroke Trials Network Working Group. The adaptive conjoint analysis determines the most influential attributes for making a decision in an iterative, algorithm-driven process. We asked respondents which would most influence a decision to administer prophylactic levetiracetam. The attributes and their levels were taken from published phenotypes associated with prophylactic seizure medications and the likelihood of seizures after ICH: hematoma location (lobar or basal ganglia), hematoma volume (<=10 mL or >10 mL), level of consciousness (Glasgow Coma Scale 5-12 or Glasgow Coma Scale 13-15), age (<65 or ≥65 years), and race (White or Caucasian or Black/African American). The algorithm terminated when the attributes were ranked from most to least influential., Results: The study sample included 27 respondents who completed the adaptive conjoint analysis out of 42 who responded to the survey with a mean age of 43.4 ± 9.4 years. The attribute with the greatest weight was hematoma location (30%), followed by reduced level of consciousness (24%), hematoma volume (19%), race (14%), and age (13%). Ranks of attributes were different (P < .001)., Conclusions: The decision to administer prophylactic levetiracetam to patients with ICH is driven by lobar hematoma location and depressed level of consciousness. Future research on prophylactic seizure medication could focus on patients most likely to receive it., (Copyright © 2019 Elsevier Inc. All rights reserved.)

Background/objective: Subarachnoid hemorrhage (SAH) is a devastating neurologic event for which markers to assess poor outcome are needed. Elevated cerebrospinal fluid (CSF) protein may result from inflammation and blood-brain barrier (BBB) disruption that occurs during SAH. We sought to determine if CSF protein level is associated with functional outcome after SAH., Methods: We prospectively collected single-center demographic and clinical data for consecutive patients admitted with spontaneous SAH. Inclusion required an external ventricular drain and daily CSF protein and cellular counts starting within 48 hours of symptom onset and extending through 7 days after onset. Seven-day average CSF protein was determined from daily measured values after correcting for contemporaneous CSF red blood cell (RBC) count. Three-month functional outcome was assessed by telephone interview with good outcome defined as modified Rankin score 0-3. Variables univariately associated with outcome at P less than .25 and measures of hemorrhage volume were included for binary logistic regression model development., Results: The study included 130 patients (88% aneurysmal SAH, 69% female, 54.8 ± 14.8 years, Glasgow Coma Scale [GCS] 14 [7-15]). Three-month outcome assessment was complete in 112 (86%) patients with good functional outcome in 74 (66%). CSF protein was lower in good outcome (35.3 [20.4-49.7] versus 80.5 [40.5-115.5] mg/dL; P < .001). CSF protein was not associated with cerebral vasospasm, but delayed radiographic infarction on 3 to 12-month neuroimaging was associated with higher CSF protein (46.3 [32.0-75.0] versus 30.2 [20.4-47.8] mg/dL; P = .023). Good 3-month outcome was independently associated with lower CSF protein (odds ratios [OR] .39 [.23-.70] for 75th versus 25th percentile of protein; P = .001) and higher admission GCS (OR 1.23 [1.10-1.37] for good outcome per GCS point increase; P < .001). Parenchymal hematoma predicted worse outcome (OR 6.31 [1.58-25.25]; P = .009). Results were similar after excluding nonaneurysmal SAH and after including CSF RBC count, CT score, and intraventricular hemorrhage volume in models., Conclusions: Elevated average CSF protein is associated with poor outcome after spontaneous SAH. Further research should investigate if elevated CSF protein identifies patients in whom mechanisms such as BBB disruption contribute to poor outcome., (Copyright © 2019 Elsevier Inc. All rights reserved.)

Objective: To assess the risk of subsequent stroke among older patients discharged from an emergency department (ED) without a diagnosis of TIA or stroke., Methods: Using electronic health record data from a large urban, university hospital and a community-based hospital, we analyzed patients aged 60-89 years discharged to home from the ED without an International Statistical Classification of Diseases and Related Health Problems, 9th or 10th Revision diagnosis of TIA or stroke. Based on the presence/absence of a head CT and the presence/absence of a chief complaint suggestive of TIA or stroke ("symptoms") during the index ED visit, we created 4 mutually exclusive groups (group 1, reference: head CT no, symptoms no; group 2: head CT no, symptoms yes; group 3: head CT yes, symptoms no; and group 4: head CT yes, symptoms yes). We calculated rates of stroke in the 30, 90, and 365 days after the index visit and used multivariable logistic regression to estimate odds ratios (ORs) for subsequent stroke., Results: Among 35,622 patients (mean age 70 years, 59% women, and 16% African American), unadjusted rates of stroke in 365 days were as follows: group 4: 2.5%; group 3: 1.1%; group 2: 0.69%; and group 1: 0.54%. The adjusted OR for stroke was 3.30 (95% confidence interval [CI], 1.61-6.76) in group 4, 1.56 (95% CI, 1.16-2.09) in group 3, and 0.61 (95% CI, 0.22-1.67) in group 2., Conclusions: Among patients discharged from the ED without a diagnosis of TIA or stroke, the occurrence of a head CT and/or specific neurologic symptoms established a clinically meaningful risk gradient for subsequent stroke., (© 2019 American Academy of Neurology.)

Introduction: Spontaneous intracerebral hemorrhage is a disabling form of stroke, and some patients will require nutritional interventions for dysphagia. We sought to determine if socioeconomic status indicators mediate whether minorities undergo gastrostomy tube placement., Materials and Methods: Patients with spontaneous intracerebral hemorrhage were enrolled in a single center, observational cohort study from 2010 to 2017. A socioeconomic index score was imputed using neighborhood characteristics by patients' ZIP code, according to an established method utilizing 6 indicators of wealth/income, education, and occupation. Multivariable logistic regression models were generated and stratified by racial/ethnic groups to determine the association of socioeconomic status with gastrostomy tube placement., Results: Among 512 patients, 93 (18.2%) underwent gastrostomy tube placement. There were 245 Whites, 220 Blacks, and 47 Hispanic. Blacks underwent the highest percentage of gastrostomy placement (22.7%), and Whites had the lowest percentage (13.5%). Among patients with gastrostomy, Blacks and Hispanics had lowest median socioeconomic index (-2.1 [IQR: -3.0, .7]; .7 [IQR: -1.6, 2.9], respectively, P < .001). Increasing intracerebral hemorrhage score was correlated with higher odds of gastrostomy across all groups (P values ≤ .01) but only Hispanics had reduced adjusted odds of gastrostomy with increasing socioeconomic index (OR .56; 95% .33-.84; P = .01)., Discussion: Racial/ethnic minorities had lower socioeconomic index and underwent more gastrostomy placement. Socioeconomic index was independently associated with gastrostomy only in Hispanics, in whom the odds of gastrostomy decreased with increasing socioeconomic index. Summary & Conclusion: Differences in utilization of gastrostomy were evident among minorities, and socioeconomic status may mediate this relationship among Hispanics., (Copyright © 2019 Elsevier Inc. All rights reserved.)

Background and Aim: Performance measures have been extensively studied for acute ischemic stroke, leading to guideline-established benchmarks. Factors influencing care efficiency for intracerebral hemorrhage (ICH) are not well delineated. We sought to identify factors associated with early recognition of ICH and to assess the association between early recognition and completion of emergency care tasks., Methods: Consecutive patients with spontaneous ICH were enrolled in an observational cohort study conducted from 2009 to 2017 at an urban comprehensive stroke center, excluding patient transferred from other hospitals. We used stroke team activation as the indicator of early recognition and measured completion times for multiple ICH-relevant performance metrics including door to computed tomography (CT) acquisition and door to hemostatic medication initiation., Results: We studied 204 cases. All stroke-related performance times were faster in patients managed with stroke team activation compared to no activation, including quicker door to CT acquisition (median 24 versus 48 minutes, P < .001) and door to hemostatic medication initiation (63 versus 99 minutes, P = .005). These associations were confirmed in adjusted models. Stroke codes were activated in 43% of cases and were more likely in patients with shorter onset-to-arrival times, higher National Institutes of Health Stroke Scale scores, and higher Glasgow Coma Scale scores., Conclusions: Stroke team activation was associated with more rapid diagnostic and therapeutic interventions for patients with ICH, but activation did not occur in the majority of cases, implying absence of early recognition. A stroke team activation process improves care performance, but leveraging the advantages of existing systems will require improved triage tools to identify ICH in the acute setting., (Copyright © 2019 Elsevier Inc. All rights reserved.)

Objectives: We tested the hypothesis that admission serum magnesium levels are associated with extent of hemorrhage in patients with aneurysmal subarachnoid hemorrhage., Design: Single-center prospective observational study., Setting: Tertiary hospital neurologic ICU., Patients: Patients with aneurysmal subarachnoid hemorrhage., Interventions: Clinically indicated CT scans and serum laboratory studies., Measurements and Main Results: Demographic, clinical, laboratory, and radiographic data were analyzed. Extent of initial hemorrhage was graded semi-quantitatively on admission CT scans using the modified Fisher scale (grades: 0, no radiographic hemorrhage; 1, thin [< 1 mm in depth] subarachnoid hemorrhage; 2, thin subarachnoid hemorrhage with intraventricular hemorrhage; 3, thick [≥ 1 mm] subarachnoid hemorrhage; 4, thick subarachnoid hemorrhage with intraventricular hemorrhage). We used both ordinal (modified Fisher scale) and dichotomized (thick vs thin subarachnoid hemorrhage) univariate and adjusted logistic regression models to assess associations between serum magnesium and radiographic subarachnoid hemorrhage severity. Data from 354 patients (mean age 55 ± 14 yr, 28.5% male, median admission Glasgow Coma Scale 14 [10-15]) were analyzed. Mean magnesium was lower in patients with thick versus thin subarachnoid hemorrhage (1.92 vs 1.99 mg/dL; p = 0.022). A monotonic trend across categories of modified Fisher scale was found using analysis of variance and Spearman rank correlation (p = 0.015 and p = 0.008, respectively). In adjusted ordinal and binary regression models, lower magnesium levels were associated with higher modified Fisher scale (odds ratio 0.33 per 1 mg/dL increase; 95% CI, 0.14-0.77; p = 0.011) and with thick subarachnoid hemorrhage (odds ratio 0.29 per 1 mg/dL increase; 95% CI, 0.10-0.78; p = 0.015)., Conclusions: These data support the hypothesis that magnesium influences hemorrhage severity in patients with aneurysmal subarachnoid hemorrhage, potentially through a hemostatic mechanism.

Background: Focal brain lesions can lend insight into the causal neuroanatomical substrate of depression in the human brain. However, studies of lesion location have led to inconsistent results., Methods: Five independent datasets with different lesion etiologies and measures of postlesion depression were collated (N = 461). Each 3-dimensional lesion location was mapped to a common brain atlas. We used voxel lesion symptom mapping to test for associations between depression and lesion locations. Next, we computed the network of regions functionally connected to each lesion location using a large normative connectome dataset (N = 1000). We used these lesion network maps to test for associations between depression and connected brain circuits. Reproducibility was assessed using a rigorous leave-one-dataset-out validation. Finally, we tested whether lesion locations associated with depression fell within the same circuit as brain stimulation sites that were effective for improving poststroke depression., Results: Lesion locations associated with depression were highly heterogeneous, and no single brain region was consistently implicated. However, these same lesion locations mapped to a connected brain circuit, centered on the left dorsolateral prefrontal cortex. Results were robust to leave-one-dataset-out cross-validation. Finally, our depression circuit derived from brain lesions aligned with brain stimulation sites that were effective for improving poststroke depression., Conclusions: Lesion locations associated with depression fail to map to a specific brain region but do map to a specific brain circuit. This circuit may have prognostic utility in identifying patients at risk for poststroke depression and therapeutic utility in refining brain stimulation targets., (Copyright © 2019 Society of Biological Psychiatry. Published by Elsevier Inc. All rights reserved.)

Objective: Cognitive impairment, detected in up to 80% of patients with liver cirrhosis, is associated with negative health outcomes but is underdiagnosed in the clinical setting due to the lack of practical testing method. This single-center prospective observational study aimed to test the feasibility and prognostic utility of in-clinic cognitive assessment of patients with liver cirrhosis using the NIH Toolbox cognition battery (NIHTB)., Methods: Patients recruited from a hepatology/transplant clinic underwent cognitive assessments using West-Haven Grade (WHG) and NIHTB between November 2016 and August 2018 and were prospectively followed until December 2018. The primary outcome was a composite end point of hospitalization related to overt hepatic encephalopathy (OHE) and all-cause mortality during follow-up, evaluated by a Cox proportional hazards regression model that adjusted for a priori covariates (age and MELD-Na)., Results: Among 127 patients (median age 60 years, 48 [38%] women) assessed, cognitive performance was significantly impaired in 82 [78%] patients with WHG 0 and 22 [100%] patients with WHG 1 and 2. Over a median of 347 days follow-up, 18 OHE and 8 deaths were observed. Lower cognitive performance was associated with an increased risk of OHE/death adjusting for age and MELD-Na. Subclinical cognitive impairment detected by NIH Toolbox in WHG 0 patients was significantly associated with greater mortality. Median time to complete the two prognostically informative NIH Toolbox tests was 9.4 min., Interpretation: NIH Toolbox may enable a rapid cognitive screening in the outpatient setting and identify patients at high risk for death and hospitalization for severe encephalopathy., (© 2019 The Authors. Annals of Clinical and Translational Neurology published by Wiley Periodicals, Inc on behalf of American Neurological Association.)

Objective: To compare the clinical characteristics and outcomes of primary intracerebral hemorrhage (ICH) with and without methamphetamine exposure., Methods: We performed a retrospective analysis of patients diagnosed with spontaneous, nontraumatic ICH over a 3-year period between January 2013 and December 2016. Demographics, clinical measures, and outcomes were compared between ICH patients with positive methamphetamine toxicology tests vs those with negative methamphetamine toxicology tests., Results: Methamphetamine-positive ICH patients were younger than methamphetamine-negative ICH patients (52 vs 67 years, p < 0.001). Patients with methamphetamine-positive ICH had higher diastolic blood pressure (115 vs 101, p = 0.003), higher mean arterial pressure (144 vs 129, p = 0.01), longer lengths of hospital (18 vs 8 days, p < 0.001) and intensive care unit (ICU) stay (10 vs 5 days, p < 0.001), required more days of IV antihypertensive medications (5 vs 3 days, p = 0.02), and had more subcortical hemorrhages (63% vs 46%, p = 0.05). The methamphetamine-positive group had better premorbid modified Rankin Scale (mRS) scores ( p < 0.001) and a greater change in functional ability as measured by mRS at the time of hospital discharge ( p = 0.001). In multivariate analyses, methamphetamine use predicted both hospital length of stay (risk ratio [RR] 1.54, confidence interval [CI] 1.39-1.70, p < 0.001) and ICU length of stay (RR 1.36, CI 1.18-1.56, p < 0.001), but did not predict poor outcome (mRS 4-6)., Conclusions: Methamphetamine use is associated with earlier age at onset of ICH, longer hospital stays, and greater change in functional ability, but did not predict outcome., (© 2019 American Academy of Neurology.)

Background: Fever is associated with worse outcome after intracerebral hemorrhage (ICH). Autonomic dysfunction, commonly seen after brain injury, results in reduced heart rate variability (HRV). We sought to investigate whether HRV was associated with the development of fever in patients with ICH., Methods: We prospectively enrolled consecutive patients with spontaneous ICH in a single-center observational study. We included patients who presented directly to our emergency department after symptom onset, had a 10-second electrocardiogram (EKG) performed within 24 h of admission, and were in sinus rhythm. Patient temperature was recorded every 1-4 h. We defined being febrile as having a temperature of ≥ 38 °C within the first 14 days, and fever burden as the number of febrile days. HRV was defined by the standard deviation of the R-R interval (SDNN) measured on the admission EKG. Univariate associations were determined by Fisher's exact, Mann-Whitney U, or Spearman's rho correlation tests. Variables associated with fever at p ≤ 0.2 were entered in a logistic regression model of being febrile within 14 days., Results: There were 248 patients (median age 63 [54-74] years, 125 [50.4%] female, median ICH Score 1 [0-2]) who met the inclusion criteria. Febrile patients had lower HRV (median SDNN: 1.72 [1.08-3.60] vs. 2.55 [1.58-5.72] msec, p = 0.001). Lower HRV was associated with more febrile days (R = - 0.22, p < 0.001). After adjustment, lower HRV was independently associated with greater odds of fever occurrence (OR 0.92 [95% CI 0.87-0.97] with each msec increase in SDNN, p = 0.002)., Conclusions: HRV measured on 10-second EKGs is a potential early marker of parasympathetic nervous system dysfunction and is associated with subsequent fever occurrence after ICH. Detecting early parasympathetic dysfunction may afford opportunities to improve ICH outcome by targeting therapies at fever prevention.

Introduction: There is practice variability in the treatment of patients with minor ischemic stroke with thrombolysis. We sought to determine which clinical factors physicians prioritize in thrombolysis decision-making for minor stroke using adaptive conjoint analysis., Methods: We conducted our conjoint analysis using the Potentially All Pairwise RanKings of all possible Alternatives methodology via the 1000Minds platform to design an online preference survey and circulated it to US physicians involved in stroke care. We evaluated 6 clinical attributes: language/speech deficits, motor deficits, other neurological deficits, history suggestive of increased risk of complication from thrombolysis, age, and premorbid disability. Survey participants were asked to choose between pairs of treatment scenarios with various clinical attributes; scenarios automatically adapted based on participants' prior responses. Preference weights representing the relative importance of each attribute were compared using unadjusted paired t tests. Statistical significance was set at α = .05., Results: Fifty-four participants completed the survey; 61% were vascular neurologists and 93% worked in academic centers. All neurological deficits were ranked higher than age, premorbid status, or potential contraindications to thrombolysis. Differences between each successive mean preference weight were significant: motor (31.7%, standard deviation [SD]: 9.5), language/speech (24.1%, SD: 9.6), other neurological deficits (16.6%, SD: 6.4), premorbid status (12.9%, SD: 6.6), age (10.1%, SD: 6.3), and potential thrombolysis contraindication (4.7%, SD: 4.4)., Conclusion: In a conjoint analysis, surveyed US physicians in academic practice assigned greater weight to motor and speech/language deficits than other neurological deficits, patient age, relative contraindications to thrombolysis, and premorbid disability when deciding to thrombolyse patients with minor stroke., Competing Interests: Declaration of Conflicting Interests: The authors declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article.

Background: Gastrostomy placement after intracerebral hemorrhage indicates the need for continued medical care and predicts patient dependence. Our objective was to determine the optimal machine learning technique to predict gastrostomy., Methods: We included 531 patients in a derivation cohort and 189 patients from another institution for testing. We derived and tested predictions of the likelihood of gastrostomy placement with logistic regression using the GRAVo score (composed of Glasgow Coma Scale ≤12, age >50 years, black race, and hematoma volume >30 mL), compared to other machine learning techniques (kth nearest neighbor, support vector machines, random forests, extreme gradient boosting, gradient boosting machine, stacking). Receiver Operating Curves (Area Under the Curve, [AUC]) between logistic regression (the technique used in GRAVo score development) and other machine learning techniques were compared. Another institution provided an external test data set., Results: In the external test data set, logistic regression using the GRAVo score components predicted gastrostomy (P < 0.001), however, with a lower AUC (0.66) than kth nearest neighbors (AUC 0.73), random forests (AUC 0.74), Gradient boosting machine (AUC 0.77), extreme gradient boosting (AUC 0.77), (P < 0.01 for all compared to logistic regression). Results from the internal test set were similar., Conclusions: Machine learning techniques other than logistic regression (eg, random forests, extreme gradient boost, and kth nearest neighbors) were significantly more accurate for predicting gastrostomy using the same independent variables. Machine learning techniques may assist clinicians in identifying patients likely to need interventions., (Copyright © 2018. Published by Elsevier Inc.)

Introduction: Depressive symptoms in patients with intracerebral hemorrhage (ICH) are common and are associated with worse outcomes. It is not well described how often depressive symptoms are ascertained and treated in large unselected cohorts of patients, and whether depressive symptoms would be a potential target for improving outcomes., Methods: Data were electronically retrieved from a multi-center EHR repository in Chicago, IL, from 2006 to 2012 ("multicenter cohort"). In the multicenter cohort, we retrieved diagnostic codes and medication data from four university health systems across Chicago. In the single center cohort, we prospectively screened for depressive symptoms (NIH Patient Reported Outcomes Measurement Information System, PROMIS, T Score ≥ 60), at one, three and twelve months after ICH onset. It should be noted that not all depressive symptoms are optimally characterized through diagnostic codes., Results: Diagnostic codes for depressive symptoms up to three months after ICH onset were recorded in 132 of 3422 (3.8%) of the multicenter cohort; fewer than 10% of patients received a typical medication to treat depressive symptoms, and < 2% one month later. In the single-center cohort, PROMIS assessments were indicative of depressive symptoms in 26 of 116 (22.4%), and depressive symptoms were more likely to be found with screening (OR 7.20, 95% CI 4.5-11.5, P < 0.0001). Results were similar up to 12 months after ICH., Conclusions: Depressive symptoms in patients with ICH are more common than medication treatment or a coded diagnosis in a multi-center cohort, and are a potential opportunity for additional treatment to improve outcomes. There are currently no AHA/ASA treatment guidelines for depression screening of patients with ICH.

Objectives: The Society of Critical Care Medicine recommends routine delirium monitoring, based on data in critically ill patients without primary neurologic injury. We sought to answer whether there are valid and reliable tools to monitor delirium in neurocritically ill patients and whether delirium is associated with relevant clinical outcomes (e.g., survival, length of stay, functional independence, cognition) in this population., Data Sources: We systematically reviewed Cumulative Index to Nursing and Allied Health Literature, Web of Science, and PubMed., Study Selection and Data Extraction: Inclusion criteria allowed any study design investigating delirium monitoring in neurocritically ill patients (e.g., neurotrauma, ischemic, and/or hemorrhagic stroke) of any age. We extracted data relevant to delirium tool sensitivity, specificity, negative predictive value, positive predictive value, interrater reliability, and associated clinical outcomes., Data Synthesis: Among seven prospective cohort studies and a total of 1,173 patients, delirium was assessed in neurocritically patients using validated delirium tools after considering primary neurologic diagnoses and associated complications, finding a pooled prevalence rate of 12-43%. When able to compare against a common reference standard, Diagnostic and Statistical Manual of Mental Disorders, Fourth Edition, the test characteristics showed a sensitivity of 62-76%, specificity of 74-98%, positive predictive value of 63-91%, negative predictive value of 70-94%, and reliability kappa of 0.64-0.94. Among four studies reporting multivariable analyses, delirium in neurocritically patients was associated with increased hospital length of stay (n = 3) and ICU length of stay (n = 1), as well as worse functional independence (n = 1) and cognition (n = 2), but not survival., Conclusions: These data from studies of neurocritically ill patients demonstrate that patients with primary neurologic diagnoses can meet diagnostic criteria for delirium and that delirious features may predict relevant untoward clinical outcomes. There is a need for ongoing investigations regarding delirium in these complicated neurocritically ill patients.

Background: Fever is associated with worse functional outcomes after intracerebral hemorrhage (ICH); however, there are few prospective data to quantify the relationship with health-related quality of life (HRQoL). We tested the hypothesis that increased burden of fever is independently associated with decreased HRQoL at follow-up., Methods: In this prospective observational cohort study of 106 ICH patients admitted to a tertiary care hospital between 2011 and 2015, we recorded the highest core temperature each calendar day for 14 days after ICH onset. Fever burden was defined as the number of days with a fever ≥ 100.4 °F (38 °C). HRQoL outcomes were measured with Neuro-QoL domains of Cognitive Function and Mobility at 28 days, 3 months, and 1 year. Results were analyzed using mixed effects regression analysis., Results: Each additional day with a fever was independently associated with lower Mobility HRQoL (T-score - 0.9, [- 1.6 to - 0.2]; p = 0.01) and Cognitive Function HRQoL (T-score - 1.3 [- 2.0 to - 0.6]; p = 0.001) after correction for National Institutes of Health Stroke Scale score on admission, age, and time to follow-up., Conclusions: Each additional day with a fever was predictive of worse HRQoL domains of Cognitive Function and Mobility after ICH up to 1 year. These data extend previous evidence on the negative association of fever and functional outcomes to the domains of Cognitive Function and Mobility HRQoL. HRQoL outcomes may be a sensitive and powerful way to measure the efficacy of fever control in future research.

Objectives: Incorporation of a single daily assessment by a clinical pharmacist to improve adherence with a sedation protocol is associated with reduced duration of mechanical ventilation and intensive care unit (ICU) length of stay (LOS). We test the feasibility of incorporating a clinical pharmacist into more frequent sedation assessments and observed whether there are any potential differences in the sedatives administered., Methods: Prospective, quasi-experimental, pilot study of patients admitted to the medical ICU. Patients were included in the analysis if ≥18 years of age within the first 24 hours of initiation of mechanical ventilation. Our primary intent was to test the clinical feasibility surrounding more frequent sedation assessments by a clinical pharmacist by evaluating potential differences in time in target sedation range and sedative administration. Exploratory efficacy end points included time in target sedation range (0 to -2) using the Richmond Agitation Sedation Scale (RASS) and sedative exposure. Patients were assigned to receive either 3 assessments with a clinical pharmacist per day (intervention) or a single assessment by a clinical pharmacist per day (standard of care). During the assessments, clinical pharmacists participated in the RASS administration and made dosing adjustments according to an established sedation protocol., Main Results: Seventeen patients were enrolled (n = 6 intervention group, n = 11 standard of care). Duration of mechanical ventilation was similar in the 2 groups (intervention 100.0 hours [52.5-197.5] vs control 76.0 hours [46.0-201.0], P = .95), but patients in the intervention group exhibited a greater percentage time in the target RASS range (intervention 76.0% [53.7-81.5%] vs control 45.2% [35.3-67.0], P = .11) that was not statistically significant. Patients in the intervention group received less fentanyl per day (820.9 µg [227.3-1579.4] vs 1997 µg [1648.2-2477.2], P = .02) than in the control group., Conclusion: Incorporating a clinical pharmacist into more frequent daily sedation assessments was associated with a reduction in fentanyl administration. There were no observed differences in time in target sedation range or reduction in duration of mechanical ventilation.