Improving the Robustness of Deep-Learning Models in Predicting Hematoma Expansion from Admission Head CT.

Background And Purpose: Robustness against input data perturbations is essential for deploying deep-learning models in clinical practice. Adversarial attacks involve subtle, voxel-level manipulations of scans to increase deep-learning models' prediction errors. Testing deep-learning model performance on examples of adversarial images provides a measure of robustness, and including adversarial images in the training set can improve the model's robustness.

Genal: a Python toolkit for genetic risk scoring and Mendelian randomization.

Motivation: The expansion of genetic association data from genome-wide association studies has increased the importance of methodologies like Polygenic Risk Scores (PRS) and Mendelian Randomization (MR) in genetic epidemiology. However, their application is often impeded by complex, multi-step workflows requiring specialized expertise and the use of disparate tools with varying data formatting requirements. Existing solutions are frequently standalone packages or command-line based-largely due to dependencies on tools like PLINK-limiting accessibility for researchers without computational experience.

A Hybrid Transformer-Convolutional Neural Network for Segmentation of Intracerebral Hemorrhage and Perihematomal Edema on Non-Contrast Head Computed Tomography (CT) with Uncertainty Quantification to Improve Confidence.

Intracerebral hemorrhage (ICH) and perihematomal edema (PHE) are key imaging markers of primary and secondary brain injury in hemorrhagic stroke. Accurate segmentation and quantification of ICH and PHE can help with prognostication and guide treatment planning. In this study, we combined Swin-Unet Transformers with nnU-NETv2 convolutional network for segmentation of ICH and PHE on non-contrast head CTs.

Machine Learning Models for 3-Month Outcome Prediction Using Radiomics of Intracerebral Hemorrhage and Perihematomal Edema from Admission Head Computed Tomography (CT).

: Intracerebral hemorrhages (ICH) and perihematomal edema (PHE) are respective imaging markers of primary and secondary brain injury in hemorrhagic stroke. In this study, we explored the potential added value of PHE radiomic features for prognostication in ICH patients. : Using a multicentric trial cohort of acute supratentorial ICH ( = 852) patients, we extracted radiomic features from ICH and PHE lesions on admission non-contrast head CTs.

Lipid-Lowering Therapy Use When Indicated and Subsequent Ischemic Stroke Severity.

Background: Elevated low-density lipoprotein cholesterol is a risk factor for atherosclerotic cardiovascular disease, including acute ischemic stroke (AIS), due to large- and small-vessel disease. Cholesterol management guidelines recommend lipid-lowering therapy (LLT) to prevent atherosclerotic cardiovascular disease events. This study assessed use of LLT at the time of AIS according to guideline recommendations and determined the association of prestroke LLT use with stroke severity.

Pupil Abnormality Frequency in the First 72 Hours Improves IMPACT score in Traumatic Brain Injury.

Importance: In patients with traumatic brain injury (TBI), baseline pupillary assessment is common. However, the incidence and frequency of pupil abnormalities within the first several days remain poorly characterized.

Objectives: Our aim was to test the association between pupil abnormality frequency over the first 72 hours of admission and clinical outcomes.

Corrigendum: The predictive validity of a Brain Care Score for late-life depression and a composite outcome of dementia, stroke, and late-life depression: data from the UK Biobank cohort.

[This corrects the article DOI: 10.3389/fpsyt.2024.

Intravenous glibenclamide for cerebral oedema after large hemispheric stroke (CHARM): a phase 3, double-blind, placebo-controlled, randomised trial.

Background: No treatment is available to prevent brain oedema, which can occur after a large hemispheric infarction. Glibenclamide has previously been shown to improve functional outcome and reduce neurological or oedema-related death in patients younger than 70 years who were at risk of brain oedema after an acute ischaemic stroke. We aimed to assess whether intravenous glibenclamide could improve functional outcome at 90 days in patients with large hemispheric infarction.

Corrigendum: The predictive validity of a Brain Care Score for dementia and stroke: data from the UK Biobank cohort.

[This corrects the article DOI: 10.3389/fneur.2023.

Polygenic Risk of Epilepsy and Poststroke Epilepsy.

Background: Epilepsy is highly heritable, with numerous known genetic risk loci. However, the genetic predisposition's role in poststroke epilepsy (PSE) remains understudied. This study assesses whether a higher genetic predisposition to epilepsy raises poststroke survivor's risk of PSE.

Door-in-Door-Out Times at Referring Hospitals and Outcomes of Hemorrhagic Stroke.

Study Objective: Interhospital transfer is often required in the care of patients with hemorrhagic stroke. Guidelines recommend a door-in-door-out (DIDO) time of ≤120 minutes at the transferring emergency department (ED); however, it is unknown whether DIDO times are related to clinical outcomes of hemorrhagic stroke.

Methods: Retrospective, observational cohort study using US registry data from Get With The Guidelines-Stroke participating hospitals.

Life's Essential 8 and Poor Brain Health Outcomes in Middle-Aged Adults.

Background And Objectives: Mounting evidence points to a strong connection between cardiovascular risk during middle age and brain health later in life. The American Heart Association's Life's Essential 8 (LE8) constitutes a research and public health construct capturing key determinants of cardiovascular health. However, the overall effect of the LE8 on global, clinically relevant metrics of brain health is still unknown.

Twenty Years of Sustained Improvement in Quality of Care and Outcomes for Patients Hospitalized With Stroke or Transient Ischemic Attack: Data From The Get With The Guidelines-Stroke Program.

Background: The Get With The Guidelines-Stroke program is a quality improvement initiative designed to enhance adherence to evidence-based stroke care. Since its inception in 2003, over 2800 hospitals in the United States have participated in the program.

Methods: We examined patient characteristics, adherence to performance measures, and in-hospital outcomes in patients hospitalized for acute ischemic stroke, subarachnoid hemorrhage, intracerebral hemorrhage, and transient ischemic attack in The Get With The Guidelines-Stroke hospitals from 2003 through 2022.

The human claustrum tracks slow waves during sleep.

Slow waves are a distinguishing feature of non-rapid-eye-movement (NREM) sleep, an evolutionarily conserved process critical for brain function. Non-human studies suggest that the claustrum, a small subcortical nucleus, coordinates slow waves. We show that, in contrast to neurons from other brain regions, claustrum neurons in the human brain increase their spiking activity and track slow waves during NREM sleep, suggesting that the claustrum plays a role in coordinating human sleep architecture.

Socioeconomic and medical determinants of state-level subjective cognitive decline in the United States.

Introduction: It is important to understand the socioeconomic and medical determinants of subjective cognitive decline (SCD) at a population level in the United States.

Methods: The primary outcomes are state-level rates of SCD and SCD-related functional impairment in adults aged ≥ 45, both measured in the Behavioral Risk Factor Surveillance System from 2016 to 2022. The exposures are state-level rates of poverty, unemployment, homelessness, college education, racial and ethnic minorities, uninsurance, smoking, hypertension, diabetes, and obesity as well as household income and physician density.

Blood Pressure and Cognitive Function in Older Adults.

This review explores the extensive evidence linking hypertension with vascular cognitive impairment and dementia, emphasizing its role as a treatable risk factor. Drawing on observational data, it will elucidate how the chronicity of hypertension at different life stages amplifies cognitive decline risk. It explores the mechanisms underlying hypertension's association with dementia, assesses the neuroprotective properties of antihypertensive therapy, and evaluates novel blood pressure metrics and monitoring methods for their diagnostic and therapeutic potential in dementia management.

Brain Health Outcomes in Sexual and Gender Minority Groups: Results From the All of Us Research Program.

Background And Objectives: Sexual and gender minority (SGM) groups have been historically underrepresented in neurologic research, and their brain health disparities are unknown. We aim to evaluate whether SGM persons are at higher risk of adverse brain health outcomes compared with cisgender straight (non-SGM) individuals.

Methods: We conducted a cross-sectional study in the All of Us Research Program, a US population-based study, including all participants with information on gender identity and sexual orientation.

Fever Prevention in Patients With Acute Vascular Brain Injury: The INTREPID Randomized Clinical Trial.

Importance: Fever is associated with worse outcomes in patients with stroke, but whether preventing fever improves outcomes is unclear.

Objective: To determine whether fever prevention after acute vascular brain injury is achievable and impacts functional outcome.

Design, Setting, And Participants: Open-label randomized clinical trial with blinded outcome assessment that enrolled 686 of 1176 planned critically ill patients with stroke at 43 intensive care units in 7 countries from March 2017 to April 2021 (last date of follow-up was May 12, 2022).