Strategic white matter hyperintensity locations associated with post-stroke cognitive impairment: a multicenter study in 1568 stroke patients

BACKGROUND

Post-stroke cognitive impairment (PSCI) occurs in up to 50% of stroke survivors. Presence of pre-existing vascular brain injury, in particular the extent of white matter hyperintensities (WMH), is associated with worse cognitive outcome after stroke, but the role of WMH location in this association is unclear.

AIM

We determined if WMH in strategic white matter tracts explain cognitive performance after stroke.

METHODS

Individual patient data from 9 ischemic stroke cohorts with MRI were harmonized through the Meta VCI Map consortium. The association between WMH volumes in strategic tracts and domain-specific cognitive functioning (attention and executive functioning, information processing speed, language and verbal memory) was assessed using linear mixed models and lasso regression. We used a hypothesis-driven design, primarily addressing four white matter tracts known to be strategic in memory clinic patients: the left and right anterior thalamic radiation, forceps major and left inferior fronto-occipital fasciculus.

RESULTS

The total study sample consisted of 1568 patients (39.9% female, mean age: 67.3 years). Total WMH volume was strongly related to cognitive performance on all four cognitive domains. WMH volume in the left anterior thalamic radiation was significantly associated with cognitive performance on attention and executive functioning and information processing speed, and WMH volume in the forceps major with information processing speed. The multivariable lasso regression showed that these associations were independent of age, sex, education, and total infarct volume and had larger coefficients than total WMH volume.

CONCLUSIONS

These results show tract-specific relations between WMH volume and cognitive performance after ischemic stroke, independent of total WMH volume. This implies that the concept of strategic lesions in PSCI extends beyond acute infarcts and also involves pre-existing WMH.

DATA AVAILABILITY

The Meta VCI Map consortium is dedicated to data sharing, following our guidelines.

Impact of the COVID-19 pandemic on mortality and loss to follow-up among patients with dementia receiving anti-dementia medications

The coronavirus disease 2019 (COVID-19) pandemic has profoundly impacted vulnerable groups, such as patients with dementia. We examined changes in mortality and loss to follow-up in patients with dementia using data from the Korean National Health Insurance Service research database. Patients with dementia who visited a medical institution with a recorded dementia-related diagnostic code, including Alzheimer's disease, and who received anti-dementia medication between February 2018 and January 2020 were included in this study. We divided patients with dementia receiving anti-dementia medications into two cohorts: those newly diagnosed with dementia between February 2018 and January 2019 (n = 62,631) and those diagnosed between February 2019 and January 2020 (n = 54,494). Then, we conducted a one-year follow-up of their records, tracking the cohort diagnosed between February 2018 and January 2019 from February 2019 to January 2020, as well as the cohort diagnosed between February 2019 and January 2020 from February 2020 to January 2021. There was a significant increase in follow-up loss among patients newly diagnosed with dementia during the COVID-19 outbreak, from 42.04% in 2019 to 45.89% in 2020. Female sex, younger age, fewer comorbidities, diagnosis of dementia at the Department of Neurology or Psychiatry, and higher income were associated with decreased follow-up loss and mortality. This study highlights the importance of paying extra attention to patients with dementia receiving anti-dementia medications, particularly during pandemics, given their increased risk of loss to follow-up.

Development of statistical auto-segmentation method for diffusion restriction gray matter lesions in patients with newly diagnosed sporadic Creutzfeldt-Jakob disease

Quantification of diffusion restriction lesions in sporadic Creutzfeldt-Jakob disease (sCJD) may provide information of the disease burden. We aim to develop an automatic segmentation model for sCJD and to evaluate the volume of disease extent as a prognostic marker for overall survival. Fifty-six patients (mean age ± SD, 61.2 ± 9.9 years) were included from February 2000 to July 2020. A threshold-based segmentation was used to obtain abnormal signal intensity masks. Segmented volumes were compared with the visual grade. The Dice similarity coefficient was calculated to measure the similarity between the automatic vs. manual segmentation. Cox proportional hazards regression analysis was performed to evaluate the volume of disease extent as a prognostic marker. The automatic segmentation showed good correlation with the visual grading. The cortical lesion volumes significantly increased as the visual grade aggravated (extensive: 112.9 ± 73.2; moderate: 45.4 ± 30.4; minimal involvement: 29.6 ± 18.1 mm3) (P < 0.001). The deep gray matter lesion volumes were significantly higher for positive than for negative involvement of the deep gray matter (5.6 ± 4.6 mm3 vs. 1.0 ± 1.3 mm3, P < 0.001). The mean Dice similarity coefficients were 0.90 and 0.94 for cortical and deep gray matter lesions, respectively. However, the volume of disease extent was not associated with worse overall survival (cortical extent: P = 0.07; deep gray matter extent: P = 0.12).

Clinical Associations and Prognostic Value of MRI-Visible Perivascular Spaces in Patients With Ischemic Stroke or TIA: A Pooled Analysis

BACKGROUND AND OBJECTIVES

Visible perivascular spaces are an MRI marker of cerebral small vessel disease and might predict future stroke. However, results from existing studies vary. We aimed to clarify this through a large collaborative multicenter analysis.

METHODS

We pooled individual patient data from a consortium of prospective cohort studies. Participants had recent ischemic stroke or transient ischemic attack (TIA), underwent baseline MRI, and were followed up for ischemic stroke and symptomatic intracranial hemorrhage (ICH). Perivascular spaces in the basal ganglia (BGPVS) and perivascular spaces in the centrum semiovale (CSOPVS) were rated locally using a validated visual scale. We investigated clinical and radiologic associations cross-sectionally using multinomial logistic regression and prospective associations with ischemic stroke and ICH using Cox regression.

RESULTS

We included 7,778 participants (mean age 70.6 years; 42.7% female) from 16 studies, followed up for a median of 1.44 years. Eighty ICH and 424 ischemic strokes occurred. BGPVS were associated with increasing age, hypertension, previous ischemic stroke, previous ICH, lacunes, cerebral microbleeds, and white matter hyperintensities. CSOPVS showed consistently weaker associations. Prospectively, after adjusting for potential confounders including cerebral microbleeds, increasing BGPVS burden was independently associated with future ischemic stroke (versus 0-10 BGPVS, 11-20 BGPVS: HR 1.19, 95% CI 0.93-1.53; 21+ BGPVS: HR 1.50, 95% CI 1.10-2.06; p = 0.040). Higher BGPVS burden was associated with increased ICH risk in univariable analysis, but not in adjusted analyses. CSOPVS were not significantly associated with either outcome.

DISCUSSION

In patients with ischemic stroke or TIA, increasing BGPVS burden is associated with more severe cerebral small vessel disease and higher ischemic stroke risk. Neither BGPVS nor CSOPVS were independently associated with future ICH.

The Usefulness of 18F-FDG PET to Differentiate Subtypes of Dementia: The Systematic Review and Meta-Analysis

Background and Purpose

Dementia subtypes, including Alzheimer's dementia (AD), dementia with Lewy bodies (DLB), and frontotemporal dementia (FTD), pose diagnostic challenges. This review examines the effectiveness of 18F-Fluorodeoxyglucose Positron Emission Tomography (18F-FDG PET) in differentiating these subtypes for precise treatment and management.

Methods

A systematic review following Preferred Reporting Items for Systematic reviews and Meta-Analyses guidelines was conducted using databases like PubMed and Embase to identify studies on the diagnostic utility of 18F-FDG PET in dementia. The search included studies up to November 16, 2022, focusing on peer-reviewed journals and applying the gold-standard clinical diagnosis for dementia subtypes.

Results

From 12,815 articles, 14 were selected for final analysis. For AD versus FTD, the sensitivity was 0.96 (95% confidence interval [CI], 0.88-0.98) and specificity was 0.84 (95% CI, 0.70-0.92). In the case of AD versus DLB, 18F-FDG PET showed a sensitivity of 0.93 (95% CI 0.88-0.98) and specificity of 0.92 (95% CI, 0.70-0.92). Lastly, when differentiating AD from non-AD dementias, the sensitivity was 0.86 (95% CI, 0.80-0.91) and the specificity was 0.88 (95% CI, 0.80-0.91). The studies mostly used case-control designs with visual and quantitative assessments.

Conclusions

18F-FDG PET exhibits high sensitivity and specificity in differentiating dementia subtypes, particularly AD, FTD, and DLB. This method, while not a standalone diagnostic tool, significantly enhances diagnostic accuracy in uncertain cases, complementing clinical assessments and structural imaging.

Relationship between disproportionately enlarged subarachnoid-space hydrocephalus and white matter tract integrity in normal pressure hydrocephalus

Normal pressure hydrocephalus (NPH) patients had altered white matter tract integrities on diffusion tensor imaging (DTI). Previous studies suggested disproportionately enlarged subarachnoid space hydrocephalus (DESH) as a prognostic sign of NPH. We examined DTI indices in NPH subgroups by DESH severity and clinical symptoms. This retrospective case-control study included 33 NPH patients and 33 age-, sex-, and education-matched controls. The NPH grading scales (0-12) were used to rate neurological symptoms. Patients with NPH were categorized into two subgroups, high-DESH and low-DESH groups, by the average value of the DESH scale. DTI indices, including fractional anisotropy, were compared across 14 regions of interest (ROIs). The high-DESH group had increased axial diffusivity in the lateral side of corona radiata (1.43 ± 0.25 vs. 1.72 ± 0.25, p = 0.04), and showed decreased fractional anisotropy and increased mean, and radial diffusivity in the anterior and lateral sides of corona radiata and the periventricular white matter surrounding the anterior horn of lateral ventricle. In patients with a high NPH grading scale, fractional anisotropy in the white matter surrounding the anterior horn of the lateral ventricle was significantly reduced (0.36 ± 0.08 vs. 0.26 ± 0.06, p = 0.03). These data show that DESH may be a biomarker for DTI-detected microstructural alterations and clinical symptom severity.

White Matter Hyperintensity Volume and Poststroke Cognition: An Individual Patient Data Pooled Analysis of 9 Ischemic Stroke Cohort Studies

BACKGROUND

White matter hyperintensities (WMH) are associated with cognitive dysfunction after ischemic stroke. Yet, uncertainty remains about affected domains, the role of other preexisting brain injury, and infarct types in the relation between WMH burden and poststroke cognition. We aimed to disentangle these factors in a large sample of patients with ischemic stroke from different cohorts.

METHODS

We pooled and harmonized individual patient data (n=1568) from 9 cohorts, through the Meta VCI Map consortium (www.metavcimap.org). Included cohorts comprised patients with available magnetic resonance imaging and multidomain cognitive assessment <15 months poststroke. In this individual patient data meta-analysis, linear mixed models were used to determine the association between WMH volume and domain-specific cognitive functioning (Z scores; attention and executive functioning, processing speed, language and verbal memory) for the total sample and stratified by infarct type. Preexisting brain injury was accounted for in the multivariable models and all analyses were corrected for the study site as a random effect.

RESULTS

In the total sample (67 years [SD, 11.5], 40% female), we found a dose-dependent inverse relationship between WMH volume and poststroke cognitive functioning across all 4 cognitive domains (coefficients ranging from -0.09 [SE, 0.04, P=0.01] for verbal memory to -0.19 [SE, 0.03, P<0.001] for attention and executive functioning). This relation was independent of acute infarct volume and the presence of lacunes and old infarcts. In stratified analyses, the relation between WMH volume and domain-specific functioning was also largely independent of infarct type.

CONCLUSIONS

In patients with ischemic stroke, increasing WMH volume is independently associated with worse cognitive functioning across all major domains, regardless of old ischemic lesions and infarct type.

High ApoB/ApoA-I Ratio Predicts Post-Stroke Cognitive Impairment in Acute Ischemic Stroke Patients with Large Artery Atherosclerosis

BACKGROUND

We aimed to investigate the association between the ApoB/ApoA-I ratio and post-stroke cognitive impairment (PSCI) in patients with acute stroke of large artery atherosclerosis etiology.

METHODS

Prospective stroke registry data were used to consecutively enroll patients with acute ischemic stroke due to large artery atherosclerosis. Cognitive function assessments were conducted 3 to 6 months after stroke. PSCI was defined as a z-score of less than -2 standard deviations from age, sex, and education-adjusted means in at least one cognitive domain. The ApoB/ApoA-I ratio was calculated, and patients were categorized into five groups according to quintiles of the ratio. Logistic regression analyses were performed to assess the association between quintiles of the ApoB/ApoA-I ratio and PSCI.

RESULTS

A total of 263 patients were included, with a mean age of 65.9 ± 11.6 years. The median NIHSS score and ApoB/ApoA-I ratio upon admission were 2 (IQR, 1-5) and 0.81 (IQR, 0.76-0.88), respectively. PSCI was observed in 91 (34.6%) patients. The highest quintile (Q5) of the ApoB/ApoA-I ratio was a significant predictor of PSCI compared to the lowest quintile (Q1) (adjusted OR, 3.16; 95% CI, 1.19-8.41; p-value = 0.021) after adjusting for relevant confounders. Patients in the Q5 group exhibited significantly worse performance in the frontal domain.

CONCLUSIONS

The ApoB/ApoA-I ratio in the acute stage of stroke independently predicted the development of PSCI at 3-6 months after stroke due to large artery atherosclerosis. Further, a high ApoB/ApoA-I ratio was specifically associated with frontal domain dysfunction.

Development and validation of an automatic classification algorithm for the diagnosis of Alzheimer's disease using a high-performance interpretable deep learning network

OBJECTIVES

To develop and validate an automatic classification algorithm for diagnosing Alzheimer's disease (AD) or mild cognitive impairment (MCI).

METHODS AND MATERIALS

This study evaluated a high-performance interpretable network algorithm (TabNet) and compared its performance with that of XGBoost, a widely used classifier. Brain segmentation was performed using a commercially approved software. TabNet and XGBoost were trained on the volumes or radiomics features of 102 segmented regions for classifying subjects into AD, MCI, or cognitively normal (CN) groups. The diagnostic performances of the two algorithms were compared using areas under the curves (AUCs). Additionally, 20 deep learning-based AD signature areas were investigated.

RESULTS

Between December 2014 and March 2017, 161 AD, 153 MCI, and 306 CN cases were enrolled. Another 120 AD, 90 MCI, and 141 CN cases were included for the internal validation. Public datasets were used for external validation. TabNet with volume features had an AUC of 0.951 (95% confidence interval [CI], 0.947-0.955) for AD vs CN, which was similar to that of XGBoost (0.953 [95% CI, 0.951-0.955], p = 0.41). External validation revealed the similar performances of two classifiers using volume features (0.871 vs. 0.871, p = 0.86). Likewise, two algorithms showed similar performances with one another in classifying MCI. The addition of radiomics data did not improve the performance of TabNet. TabNet and XGBoost focused on the same 13/20 regions of interest, including the hippocampus, inferior lateral ventricle, and entorhinal cortex.

CONCLUSIONS

TabNet shows high performance in AD classification and detailed interpretation of the selected regions.

CLINICAL RELEVANCE STATEMENT

Using a high-performance interpretable deep learning network, the automatic classification algorithm assisted in accurate Alzheimer's disease detection using 3D T1-weighted brain MRI and detailed interpretation of the selected regions.

KEY POINTS

• MR volumetry data revealed that TabNet had a high diagnostic performance in differentiating Alzheimer's disease (AD) from cognitive normal cases, which was comparable with that of XGBoost. • The addition of radiomics data to the volume data did not improve the diagnostic performance of TabNet. • Both TabNet and XGBoost selected the clinically meaningful regions of interest in AD, including the hippocampus, inferior lateral ventricle, and entorhinal cortex.

Machine learning-based prediction of post-stroke cognitive status using electroencephalography-derived brain network attributes

Objectives

More than half of patients with acute ischemic stroke develop post-stroke cognitive impairment (PSCI), a significant barrier to future neurological recovery. Thus, predicting cognitive trajectories post-AIS is crucial. Our primary objective is to determine whether brain network properties from electroencephalography (EEG) can predict post-stroke cognitive function using machine learning approach.

Methods

We enrolled consecutive stroke patients who underwent both EEG during the acute stroke phase and cognitive assessments 3 months post-stroke. We preprocessed acute stroke EEG data to eliminate low-quality epochs, then performed independent component analysis and quantified network characteristics using iSyncBrain®. Cognitive function was evaluated using the Montreal cognitive assessment (MoCA). We initially categorized participants based on the lateralization of their lesions and then developed machine learning models to predict cognitive status in the left and right hemisphere lesion groups.

Results

Eighty-seven patients were included, and the accuracy of lesion laterality prediction using EEG attributes was 97.0%. In the left hemispheric lesion group, the network attributes of the theta band were significantly correlated with MoCA scores, and higher global efficiency, clustering coefficient, and lower characteristic path length were associated with higher MoCA scores. Most features related to cognitive scores were selected from the frontal lobe. The predictive powers (R-squared) were 0.76 and 0.65 for the left and right stroke groups, respectively.

Conclusion

Estimating EEG-based network properties in the acute phase of ischemic stroke through a machine learning model has a potential to predict cognitive outcomes after ischemic stroke.

Bayesian modeling disentangles language versus executive control disruption in stroke

Stroke is the leading cause of long-term disability worldwide. Incurred brain damage disrupts cognition, often with persisting deficits in language and executive capacities. Despite their clinical relevance, the commonalities, and differences of language versus executive control impairments remain under-specified. We tailored a Bayesian hierarchical modeling solution in a largest-of-its-kind cohort (1080 stroke patients) to deconvolve language and executive control in the brain substrates of stroke insults. Four cognitive factors distinguished left- and right-hemispheric contributions to ischemic tissue lesion. One factor delineated language and general cognitive performance and was mainly associated with damage to left-hemispheric brain regions in the frontal and temporal cortex. A factor for executive control summarized control and visual-constructional abilities. This factor was strongly related to right-hemispheric brain damage of posterior regions in the occipital cortex. The interplay of language and executive control was reflected in two factors: executive speech functions and verbal memory. Impairments on both were mainly linked to left-hemispheric lesions. These findings shed light onto the causal implications of hemispheric specialization for cognition; and make steps towards subgroup-specific treatment protocols after stroke.

Development and validation of a deep learning-based automatic segmentation model for assessing intracranial volume: comparison with NeuroQuant, FreeSurfer, and SynthSeg

Background and purpose

To develop and validate a deep learning-based automatic segmentation model for assessing intracranial volume (ICV) and to compare the accuracy determined by NeuroQuant (NQ), FreeSurfer (FS), and SynthSeg.

Materials and methods

This retrospective study included 60 subjects [30 Alzheimer's disease (AD), 21 mild cognitive impairment (MCI), 9 cognitively normal (CN)] from a single tertiary hospital for the training and validation group (50:10). The test group included 40 subjects (20 AD, 10 MCI, 10 CN) from the ADNI dataset. We propose a robust ICV segmentation model based on the foundational 2D UNet architecture trained with four types of input images (both single and multimodality using scaled or unscaled T1-weighted and T2-FLAIR MR images). To compare with our model, NQ, FS, and SynthSeg were also utilized in the test group. We evaluated the model performance by measuring the Dice similarity coefficient (DSC) and average volume difference.

Results

The single-modality model trained with scaled T1-weighted images showed excellent performance with a DSC of 0.989 ± 0.002 and an average volume difference of 0.46% ± 0.38%. Our multimodality model trained with both unscaled T1-weighted and T2-FLAIR images showed similar performance with a DSC of 0.988 ± 0.002 and an average volume difference of 0.47% ± 0.35%. The overall average volume difference with our model showed relatively higher accuracy than NQ (2.15% ± 1.72%), FS (3.69% ± 2.93%), and SynthSeg (1.88% ± 1.18%). Furthermore, our model outperformed the three others in each subgroup of patients with AD, MCI, and CN subjects.

Conclusion

Our deep learning-based automatic ICV segmentation model showed excellent performance for the automatic evaluation of ICV.

Risk estimation for idiopathic normal-pressure hydrocephalus: development and validation of a brain morphometry-based nomogram

OBJECTIVES

To develop and validate a nomogram based on MRI features for predicting iNPH.

METHODS

Patients aged  ≥ 60 years (clinically diagnosed with iNPH, Parkinson's disease, or Alzheimer's disease or healthy controls) who underwent MRI including three-dimensional T1-weighted volumetric MRI were retrospectively identified from two tertiary referral hospitals (one hospital for derivation set and the other for validation set). Clinical and imaging features for iNPH were assessed. Deep learning-based brain segmentation software was used for 3D volumetry. A prediction model was developed using logistic regression and transformed into a nomogram. The performance of the nomogram was assessed with respect to discrimination and calibration abilities. The nomogram was internally and externally validated.

RESULTS

A total of 452 patients (mean age ± SD, 73.2 ± 6.5 years; 200 men) were evaluated as the derivation set. One hundred eleven and 341 patients were categorized into the iNPH and non-iNPH groups, respectively. In multivariable analysis, high-convexity tightness (odds ratio [OR], 35.1; 95% CI: 4.5, 275.5), callosal angle  < 90° (OR, 12.5; 95% CI: 3.1, 50.0), and normalized lateral ventricle volume (OR, 4.2; 95% CI: 2.7, 6.7) were associated with iNPH. The nomogram combining these three variables showed an area under the curve of 0.995 (95% CI: 0.991, 0.999) in the study sample, 0.994 (95% CI: 0.990, 0.998) in the internal validation sample, and 0.969 (95% CI: 0.940, 0.997) in the external validation sample.

CONCLUSION

A brain morphometry-based nomogram including high-convexity tightness, callosal angle  < 90°, and normalized lateral ventricle volume can help accurately estimate the probability of iNPH.

KEY POINTS

• The nomogram with MRI findings (high-convexity tightness, callosal angle, and normalized lateral ventricle volume) helped in predicting the probability of idiopathic normal-pressure hydrocephalus. • The nomogram may facilitate the prediction of idiopathic normal-pressure hydrocephalus and consequently avoid unnecessary invasive procedures such as the cerebrospinal fluid tap test, drainage test, and cerebrospinal fluid shunt surgery.

Sex Differences in Poststroke Cognitive Impairment: A Multicenter Study in 2343 Patients With Acute Ischemic Stroke

BACKGROUND

Poststroke cognitive impairment (PSCI) occurs in about half of stroke survivors. Cumulative evidence indicates that functional outcomes of stroke are worse in women than men. Yet it is unknown whether the occurrence and characteristics of PSCI differ between men and women.

METHODS

Individual patient data from 9 cohorts of patients with ischemic stroke were harmonized and pooled through the Meta-VCI-Map consortium (n=2343, 38% women). We included patients with visible symptomatic infarcts on computed tomography/magnetic resonance imaging and cognitive assessment within 15 months after stroke. PSCI was defined as impairment in ≥1 cognitive domains on neuropsychological assessment. Logistic regression analyses were performed to compare men to women, adjusted for study cohort, to obtain odds ratios for PSCI and individual cognitive domains. We also explored sensitivity and specificity of cognitive screening tools for detecting PSCI, according to sex (Mini-Mental State Examination, 4 cohorts, n=1814; Montreal Cognitive Assessment, 3 cohorts, n=278).

RESULTS

PSCI was found in 51% of both women and men. Men had a lower risk of impairment of attention and executive functioning (men: odds ratio, 0.76 [95% CI, 0.61-0.96]), and language (men: odds ratio, 0.67 [95% CI, 0.45-0.85]), but a higher risk of verbal memory impairment (men: odds ratio, 1.43 [95% CI, 1.17-1.75]). The sensitivity of Mini-Mental State Examination (<25) for PSCI was higher for women (0.53) than for men (0.27; P=0.02), with a lower specificity for women (0.80) than men (0.96; P=0.01). Sensitivity and specificity of Montreal Cognitive Assessment (<26.) for PSCI was comparable between women and men (0.91 versus 0.86; P=0.62 and 0.29 versus 0.28; P=0.86, respectively).

CONCLUSIONS

Sex was not associated with PSCI occurrence but affected domains differed between men and women. The latter may explain why sensitivity of the Mini-Mental State Examination for detecting PSCI was higher in women with a lower specificity compared with men. These sex differences need to be considered when screening for and diagnosing PSCI in clinical practice.

Prediction of post-stroke cognitive impairment after acute ischemic stroke using machine learning

BACKGROUND AND OBJECTIVES

Post-stroke cognitive impairment (PSCI) occurs in up to 50% of patients with acute ischemic stroke (AIS). Thus, the prediction of cognitive outcomes in AIS may be useful for treatment decisions. This PSCI cohort study aimed to determine the applicability of a machine learning approach for predicting PSCI after stroke.

METHODS

This retrospective study used a prospective PSCI cohort of patients with AIS. Demographic features, clinical characteristics, and brain imaging variables previously known to be associated with PSCI were included in the analysis. The primary outcome was PSCI at 3-6 months, defined as an adjusted z-score of less than - 2.0 standard deviation in at least one of the four cognitive domains (memory, executive/frontal, visuospatial, and language), using the Korean version of the Vascular Cognitive Impairment Harmonization Standards-Neuropsychological Protocol (VCIHS-NP). We developed four machine learning models (logistic regression, support vector machine, extreme gradient boost, and artificial neural network) and compared their accuracies for outcome variables.

RESULTS

A total of 951 patients (mean age 65.7 ± 11.9; male 61.5%) with AIS were included in this study. The area under the curve for the extreme gradient boost and the artificial neural network was the highest (0.7919 and 0.7365, respectively) among the four models for predicting PSCI according to the VCIHS-NP definition. The most important features for predicting PSCI include the presence of cortical infarcts, mesial temporal lobe atrophy, initial stroke severity, stroke history, and strategic lesion infarcts.

CONCLUSION

Our findings indicate that machine-learning algorithms, particularly the extreme gradient boost and the artificial neural network models, can best predict cognitive outcomes after ischemic stroke.

Detection rate of contrast-enhanced brain magnetic resonance imaging in patients with cognitive impairment

INTRODUCTION

The number of brain MRI with contrast media performed in patients with cognitive impairment has increased without universal agreement. We aimed to evaluate the detection rate of contrast-enhanced brain MRI in patients with cognitive impairment.

MATERIALS AND METHODS

This single-institution, retrospective study included 4,838 patients who attended outpatient clinics for cognitive impairment evaluation and underwent brain MRI with or without contrast enhancement from December 2015 to February 2020. Patients who tested positive for cognitive impairment were followed-up to confirm whether the result was true-positive and provide follow-up management. Detection rate was defined as the proportion of patients with true-positive results and was compared between groups with and without contrast enhancement. Individual matching in a 1:2 ratio according to age, sex, and year of test was performed.

RESULTS

The overall detection rates of brain MRI with and without contrast media were 4.7% (57/1,203; 95% CI: 3.6%-6.1%) and 1.8% (65/3,635; 95% CI: 1.4%-2.3%), respectively (P<0.001); individual matching demonstrated similar results (4.7% and 1.9%). Among 1,203 patients with contrast media, 3.6% was only detectable with the aid of contrast media. The proportion of patients who underwent follow-up imaging or treatment for the detected lesions were significantly higher in the group with contrast media (2.0% and 0.6%, P < .001).

CONCLUSIONS

Detection rate of brain MRI for lesions only detectable with contrast media in patients with cognitive impairment was not high enough and further study is needed to identify whom would truly benefit with contrast media.

Impact of Cerebral Microbleeds in Stroke Patients with Atrial Fibrillation

OBJECTIVES

Cerebral microbleeds are associated with the risks of ischemic stroke and intracranial hemorrhage, causing clinical dilemmas for antithrombotic treatment decisions. We aimed to evaluate the risks of intracranial hemorrhage and ischemic stroke associated with microbleeds in patients with atrial fibrillation treated with vitamin K antagonists, direct oral anticoagulants, antiplatelets, and combination therapy (i.e. concurrent oral anticoagulant and antiplatelet).

METHODS

We included patients with documented atrial fibrillation from the pooled individual patient data analysis by the Microbleeds International Collaborative Network. Risks of subsequent intracranial hemorrhage and ischemic stroke were compared between patients with and without microbleeds, stratified by antithrombotic use.

RESULTS

A total of 7,839 patients were included. The presence of microbleeds was associated with an increased relative risk of intracranial hemorrhage (adjusted hazard ratio [aHR] = 2.74, 95% confidence interval = 1.76-4.26) and ischemic stroke (aHR = 1.29, 95% confidence interval = 1.04-1.59). For the entire cohort, the absolute incidence of ischemic stroke was higher than intracranial hemorrhage regardless of microbleed burden. However, for the subgroup of patients taking combination of anticoagulant and antiplatelet therapy, the absolute risk of intracranial hemorrhage exceeded that of ischemic stroke in those with 2 to 4 microbleeds (25 vs 12 per 1,000 patient-years) and ≥ 11 microbleeds (94 vs 48 per 1,000 patient-years).

INTERPRETATION

Patients with atrial fibrillation and high burden of microbleeds receiving combination therapy have a tendency of higher rate of intracranial hemorrhage than ischemic stroke, with potential for net harm. Further studies are needed to help optimize stroke preventive strategies in this high-risk group. ANN NEUROL 2023;94:61-74.

Short-term Trajectories of Poststroke Cognitive Function: A STROKOG Collaboration Study

BACKGROUND AND OBJECTIVES

Past studies on post-stroke cognitive function have focused on the average performance or change over time, but few have investigated patterns of cognitive trajectories after stroke. This project used latent class growth analysis (LCGA) to identify clusters of patients with similar patterns of cognition scores over the first-year post-stroke and the extent to which long-term cognitive outcome is predicted by the clusters ("trajectory groups").

METHODS

Data were sought from the Stroke and Cognition consortium (STROKOG). LCGA was used to identify clusters of trajectories based on standardized global cognition scores at baseline (T₁) and at the 1-year follow-up (T₂). One-step IPD meta-analysis was used to examine risk factors for trajectory groups and association of trajectory groups with cognition at the long-term follow-up (T₃).

RESULTS

Nine hospital-based stroke cohorts with 1149 patients (63% male; mean age 66.4 years (SD=11.0)) were included. The median time assessed at T₁ was 3.6 months post-stroke, 1.0 year at T₂ and 3.2 years at T₃. LCGA identified 3 trajectory groups, which were characterized by different mean levels of cognition scores at T₁ (low-, -3.27SD (0.94), 17%; medium-, -1.23SD (0.68), 48%; and high-performance, 0.71SD (0.77), 35%). There was significant improvement in cognition for the high-performance group (0.22 SD/year, 95% CI 0.07, 0.36), but changes for the low and medium performance groups were not significant (-0.10 SD/year, 95% CI -0.33, 0.13; 0.11 SD/year, 95% CI -0.08, 0.24 respectively). Factors associated with the low- (versus high-) performance group include age (relative risk ratio [RRR] 1.18, 95% CI 1.14, 1.23), years of education (RRR 0.61, 95% CI 0.56, 0.67), diabetes (RRR 3.78, 95% CI 2.08, 6.88), large artery versus small vessel strokes (RRR 2.77, 95% CI 1.32, 5.83), and moderate/severe strokes (RRR 3.17, 95% 1.42, 7.08). Trajectory groups were predictive of global cognition at T₃, but its predictive power was comparable to scores at T₁.

CONCLUSION

The trajectory of cognitive function over the first-year post-stroke is heterogenous. Baseline cognitive function ∼3.6 months post-stroke is a good predictor of long-term cognitive outcome. Older age, lower levels of education, diabetes, large artery strokes, and greater stroke severity are risk factors for lower cognitive performance over the first year.

Disentangling poststroke cognitive deficits and their neuroanatomical correlates through combined multivariable and multioutcome lesion-symptom mapping

Studies in patients with brain lesions play a fundamental role in unraveling the brain's functional anatomy. Lesion-symptom mapping (LSM) techniques can relate lesion location to cognitive performance. However, a limitation of current LSM approaches is that they can only evaluate one cognitive outcome at a time, without considering interdependencies between different cognitive tests. To overcome this challenge, we implemented canonical correlation analysis (CCA) as combined multivariable and multioutcome LSM approach. We performed a proof-of-concept study on 1075 patients with acute ischemic stroke to explore whether addition of CCA to a multivariable single-outcome LSM approach (support vector regression) could identify infarct locations associated with deficits in three well-defined verbal memory functions (encoding, consolidation, retrieval) based on four verbal memory subscores derived from the Seoul Verbal Learning Test (immediate recall, delayed recall, recognition, learning ability). We evaluated whether CCA could extract cognitive score patterns that matched prior knowledge of these verbal memory functions, and if these patterns could be linked to more specific infarct locations than through single-outcome LSM alone. Two of the canonical modes identified with CCA showed distinct cognitive patterns that matched prior knowledge on encoding and consolidation. In addition, CCA revealed that each canonical mode was linked to a distinct infarct pattern, while with multivariable single-outcome LSM individual verbal memory subscores were associated with largely overlapping patterns. In conclusion, our findings demonstrate that CCA can complement single-outcome LSM techniques to help disentangle cognitive functions and their neuroanatomical correlates.

Bayesian stroke modeling details sex biases in the white matter substrates of aphasia

Ischemic cerebrovascular events often lead to aphasia. Previous work provided hints that such strokes may affect women and men in distinct ways. Women tend to suffer strokes with more disabling language impairment, even if the lesion size is comparable to men. In 1401 patients, we isolate data-led representations of anatomical lesion patterns and hand-tailor a Bayesian analytical solution to carefully model the degree of sex divergence in predicting language outcomes ~3 months after stroke. We locate lesion-outcome effects in the left-dominant language network that highlight the ventral pathway as a core lesion focus across different tests of language performance. We provide detailed evidence for sex-specific brain-behavior associations in the domain-general networks associated with cortico-subcortical pathways, with unique contributions of the fornix in women and cingular fiber bundles in men. Our collective findings suggest diverging white matter substrates in how stroke causes language deficits in women and men. Clinically acknowledging such sex disparities has the potential to improve personalized treatment for stroke patients worldwide.

Stroke Risk and Antithrombotic Treatment During Follow-up of Patients With Ischemic Stroke and Cortical Superficial Siderosis

BACKGROUND AND OBJECTIVES

In patients with ischemic stroke (IS) or transient ischemic attack (TIA) and cortical superficial siderosis (cSS), there are few data regarding the risk of future cerebrovascular events and also about the benefits and safety of antithrombotic drugs for secondary prevention. We investigated the associations of cSS and stroke risk in patients with recent IS or TIA.

METHODS

We retrospectively analyzed the Microbleeds International Collaborative Network (MICON) database. We selected patients with IS or TIA from cohorts who had MRI-assessed cSS, available data on antithrombotic treatments, recurrent cerebrovascular events (intracranial hemorrhage [ICrH], IS, or any stroke [ICrH or IS]), and mortality. We calculated incidence rates (IRs) and performed univariable and multivariable Cox regression analyses.

RESULTS

Of 12,669 patients (mean age 70.4 ± 12.3 years, 57.3% men), cSS was detected in 273 (2.2%) patients. During a mean follow-up of 24 ± 17 months, IS was more frequent than ICrH in both cSS (IR 57.1 vs 14.6 per 1,000 patient-years) and non-cSS (33.7 vs 6.3 per 1,000 patient-years) groups. Compared with the non-cSS group, cSS was associated with any stroke on multivariable analysis {IR 83 vs 42 per 1,000 patient-years, adjusted hazard ratio [HR] for cSS 1.62 (95% CI: 1.14-2.28; p = 0.006)}. This association was not significant in subgroups of patients treated with antiplatelet drugs (n = 6,554) or with anticoagulants (n = 4,044). Patients with cSS who were treated with both antiplatelet drugs and anticoagulants (n = 1,569) had a higher incidence of ICrH (IR 107.5 vs 4.9 per 1,000 patient-years, adjusted HR 13.26; 95% CI: 2.90-60.63; p = 0.001) and of any stroke (IR 198.8 vs 34.7 per 1,000 patient-years, adjusted HR 5.03; 95% CI: 2.03-12.44; p < 0.001) compared with the non-cSS group.

DISCUSSION

Patients with IS or TIA with cSS are at increased risk of stroke (ICrH or IS) during follow-up; the risk of IS exceeds that of ICrH for patients receiving antiplatelet or anticoagulant treatment alone, but the risk of ICrH exceeds that of IS in patients receiving both treatments. The findings suggest that either antiplatelet or anticoagulant treatment alone should not be avoided in patients with cSS, but combined antithrombotic therapy might be hazardous. Our findings need to be confirmed by randomized clinical trials.

Association between exercise habit changes and incident dementia after ischemic stroke

We aimed to investigate the effects of exercise habit changes on the risk of incident dementia after ischemic stroke using the Korean National Health Insurance Services Database. This study included 223,426 patients with a new diagnosis of ischemic stroke between 2010 and 2016 who underwent two serial ambulatory health checkups. The participants were divided into four categories according to their habit change or regular exercise: persistent non-exercisers, new exercisers, exercise dropouts, and exercise maintainers. The primary outcome was new diagnosis of dementia. Multivariate Cox proportional models were used to assess the effects of changes in exercise habits on the risk of incident dementia. After a median of 4.02 years of follow-up, 22,554 (10.09%) dementia cases were observed. After adjusting for covariates, exercise dropouts, new exercisers, and exercise maintainers were significantly associated with a lower risk of incident dementia than persistent non-exercisers (adjusted hazard ratio [aHR] 0.937; 95% confidence interval [CI] 0.905-0.970, aHR 0.876; 95% CI 0.843-0.909, aHR 0.705; 95% CI 0.677-0.734, respectively). The impact of changes in exercise habit was more prominent in the 40-65 years age group. An energy expenditure ≥ 1000 metabolic equivalents of task-min/wk post-stroke, regardless of pre-stroke physical activity status, was mostly associated with a lower risk of each outcome. In this retrospective cohort study, initiating or continuing moderate-to-vigorous exercise after ischemic stroke was associated with a lower risk of dementia development. Further, pre-stroke regular physical activity also reduced the risk of incident dementia. The promotion of exercise in ambulatory stroke patients may reduce their future risk of incident dementia.

Efficacy and safety of oxiracetam in patients with vascular cognitive impairment: A multicenter, randomized, double-blinded, placebo-controlled, phase IV clinical trial

BACKGROUND

Oxiracetam may have a modest effect on preventing cognitive decline. Exercise can also enhance cognitive function. This trial aims to investigate the effect of oxiracetam on post-stroke cognitive impairment and explore whether this effect is modified by exercise. Furthermore, the mechanisms that mediate this effect will be investigated through a neural network analysis.

METHODS

This is a multicenter, randomized, double-blind, placebo-controlled phase IV trial. Patients who complained of cognitive decline 3 months after stroke and had a high risk of cognitive decline were eligible. Patients were randomly assigned to receive either 800 mg of oxiracetam or placebo twice daily for 36 weeks. After randomization, a predetermined exercise protocol was provided to each participant, and the degree of physical activity was assessed using wrist actigraphy at 4, 12, 24, and 36 weeks. Resting-state functional MRI was obtained in baseline and 36-week follow-up. Co-primary endpoints are changes in the Mini-Mental State Examination and Clinical Dementia Rating-Sum of Boxes. Secondary endpoints include changes in the NINDS-CSN VCIHS-Neuropsychology Protocol, Euro QoL, patient's global assessment, and functional network connectivity. If there is a significant difference in physical activity between the two groups, the interaction effect between physical activity and the treatment group will be examined. A total of 500 patients were enrolled from February 2018, and the last patient's final follow-up was completed in September 2022.

CONCLUSION

This trial is meaningful not only to prove the efficacy of oxiracetam, but also evaluate whether exercise can modify the effects of medication and how cognitive function can be restored. Trial registrationhttp://cris.nih.go.kr (KCT0005137).

Diagnostic performance of deep learning-based automatic white matter hyperintensity segmentation for classification of the Fazekas scale and differentiation of subcortical vascular dementia

Purpose

To validate the diagnostic performance of commercially available, deep learning-based automatic white matter hyperintensity (WMH) segmentation algorithm for classifying the grades of the Fazekas scale and differentiating subcortical vascular dementia.

Methods

This retrospective, observational, single-institution study investigated the diagnostic performance of a deep learning-based automatic WMH volume segmentation to classify the grades of the Fazekas scale and differentiate subcortical vascular dementia. The VUNO Med-DeepBrain was used for the WMH segmentation system. The system for segmentation of WMH was designed with convolutional neural networks, in which the input image was comprised of a pre-processed axial FLAIR image, and the output was a segmented WMH mask and its volume. Patients presented with memory complaint between March 2017 and June 2018 were included and were split into training (March 2017–March 2018, n = 596) and internal validation test set (April 2018–June 2018, n = 204).

Results

Optimal cut-off values to categorize WMH volume as normal vs. mild/moderate/severe, normal/mild vs. moderate/severe, and normal/mild/moderate vs. severe were 3.4 mL, 9.6 mL, and 17.1 mL, respectively, and the AUC were 0.921, 0.956 and 0.960, respectively. When differentiating normal/mild vs. moderate/severe using WMH volume in the test set, sensitivity, specificity, and accuracy were 96.4%, 89.9%, and 91.7%, respectively. For distinguishing subcortical vascular dementia from others using WMH volume, sensitivity, specificity, and accuracy were 83.3%, 84.3%, and 84.3%, respectively.

Conclusion

Deep learning-based automatic WMH segmentation may be an accurate and promising method for classifying the grades of the Fazekas scale and differentiating subcortical vascular dementia.

Incidence of Amyloid-Related Imaging Abnormalities in Patients With Alzheimer Disease Treated With Anti-β-amyloid Immunotherapy: A Meta-analysis

OBJECTIVES

To assess the incidence of ARIA in clinical trials of anti-Aβ immunotherapy and compare the incidence among different agents and clinical characteristics to identify possible predisposing factors for ARIA.

METHODS

The PubMed and Embase databases were searched for clinical trials of anti-Aβ immunotherapy published on or before January 12, 2022. Phase 2 or 3 randomized controlled trials reporting detailed data sufficient to assess the incidence of ARIA were selected. The pooled incidences of ARIA and subgroup analyses according to agent and ApoE-4 carrier status were calculated using the DerSimonian-Liard random-effects model. The proportion of symptomatic ARIA cases was also calculated.

RESULTS

In total, 19 eligible studies, including 24 cohorts, were identified and 9,429 patients were analyzed. The overall pooled incidence of ARIA-effusion (E) and ARIA-hemorrhage (H) was 6.5% and 7.8%, respectively. In the subgroup analysis, the incidence of ARIA was different according to anti-Aβ immunotherapy agent. The cohorts treated with aducanumab had a significantly higher incidence of ARIA-E and ARIA-H (30.7% and 30.0%, respectively; both P < 0.001) compared to cohorts from other drugs. In subgroup analysis according to ApoE-4 carrier status, the incidences of ARIA-E and ARIA-H were higher in the ApoE-4 carrier group than those in ApoE-4 non-carrier group, but there was no statistical significance ( ApoE-4 carrier vs. non-carrier, ARIA-E; 8.6% vs. 6.9%, P = 0.663, and ARIA-H; 10.5% vs. 6.6%, P = 0.398). The pooled proportion of asymptomatic ARIA, detected by routine scheduled MRI surveillances, was 80.4%.

CONCLUSIONS

The overall incidences of ARIA-E and ARIA-H were 6.5% and 7.8%, respectively, and the pooled proportion of asymptomatic ARIA was 80.4%. The cohorts treated with aducanumab showed a significantly higher incidence of ARIA-E and ARIA-H (30.7% and 30.0%) compared with other drugs.

Diagnostic yield of TOF-MRA for detecting incidental vascular lesions in patients with cognitive impairment: An observational cohort study

Objectives

The role of three-dimensional (3D) TOF-MRA in patients with cognitive impairment is not well established. We evaluated the diagnostic yield of 3D TOF-MRA for detecting incidental extra- or intracranial artery stenosis and intracranial aneurysm in this patient group.

Methods

This retrospective study included patients with cognitive impairment undergoing our brain MRI protocol from January 2013 to February 2020. The diagnostic yield of TOF-MRA for detecting incidental vascular lesions was calculated. Patients with positive TOF-MRA results were reviewed to find whether additional treatment was performed. Logistic regression analysis was conducted to identify the clinical risk factors for positive TOF-MRA findings.

Results

In total, 1,753 patients (mean age, 70.2 ± 10.6 years; 1,044 women) were included; 199 intracranial aneurysms were detected among 162 patients (9.2%, 162/1,753). A 3D TOF-MRA revealed significant artery stenoses (>50% stenosis) in 162 patients (9.2%, 162/1,753). The overall diagnostic yield of TOF-MRA was 16.8% (294/1,753). Among them, 92 patients (31.3%, 92/294) underwent either medical therapy, endovascular intervention, or surgery. In total, eighty-one patients with stenosis were prescribed with either antiplatelet medications or lipid-lowering agent. In total, fifteen patients (aneurysm: 11 patients, stenosis: 4 patients) were further treated with endovascular intervention or surgery. Thus, the “number needed to scan” was 19 for identifying one patient requiring treatment. Multivariate logistic regression analysis showed that being female (odds ratio [OR] 2.05) and old age (OR 1.04) were the independent risk factors for intracranial aneurysm; being male (OR 1.52), old age (OR 1.06), hypertension (OR 1.78), and ischemic heart disease history (OR 2.65) were the independent risk factors for significant artery stenosis.

Conclusions

Our study demonstrated the potential benefit of 3D TOF-MRA, given that it showed high diagnostic yield for detecting vascular lesions in patients with cognitive impairment and the considerable number of these lesions required further treatment. A 3D TOF-MRA may be included in the routine MR protocol for the work-up of this patient population, especially in older patients and patients with vascular risk factors.

Predicting progression to dementia with “comprehensive visual rating scale” and machine learning algorithms

Background and Objective

Identifying biomarkers for predicting progression to dementia in patients with mild cognitive impairment (MCI) is crucial. To this end, the comprehensive visual rating scale (CVRS), which is based on magnetic resonance imaging (MRI), was developed for the assessment of structural changes in the brains of patients with MCI. This study aimed to investigate the use of the CVRS score for predicting dementia in patients with MCI over a 2-year follow-up period using various machine learning (ML) algorithms.

Methods

We included 197 patients with MCI who were followed up more than once. The data used for this study were obtained from the Japanese-Alzheimer's Disease Neuroimaging Initiative study. We assessed all the patients using their CVRS scores, cortical thickness data, and clinical data to determine their progression to dementia during a follow-up period of over 2 years. ML algorithms, such as logistic regression, random forest (RF), XGBoost, and LightGBM, were applied to the combination of the dataset. Further, feature importance that contributed to the progression from MCI to dementia was analyzed to confirm the risk predictors among the various variables evaluated.

Results

Of the 197 patients, 108 (54.8%) showed progression from MCI to dementia. Tree-based classifiers, such as XGBoost, LightGBM, and RF, achieved relatively high performance. In addition, the prediction models showed better performance when clinical data and CVRS score (accuracy 0.701–0.711) were used than when clinical data and cortical thickness (accuracy 0.650–0.685) were used. The features related to CVRS helped predict progression to dementia using the tree-based models compared to logistic regression.

Conclusions

Tree-based ML algorithms can predict progression from MCI to dementia using baseline CVRS scores combined with clinical data.

Network impact score is an independent predictor of post-stroke cognitive impairment: A multicenter cohort study in 2341 patients with acute ischemic stroke

BACKGROUND

Post-stroke cognitive impairment (PSCI) is a common consequence of stroke. Accurate prediction of PSCI risk is challenging. The recently developed network impact score, which integrates information on infarct location and size with brain network topology, may improve PSCI risk prediction.

AIMS

To determine if the network impact score is an independent predictor of PSCI, and of cognitive recovery or decline.

METHODS

We pooled data from patients with acute ischemic stroke from 12 cohorts through the Meta VCI Map consortium. PSCI was defined as impairment in ≥ 1 cognitive domain on neuropsychological examination, or abnormal Montreal Cognitive Assessment. Cognitive recovery was defined as conversion from PSCI < 3 months post-stroke to no PSCI at follow-up, and cognitive decline as conversion from no PSCI to PSCI. The network impact score was related to serial measures of PSCI using Generalized Estimating Equations (GEE) models, and to PSCI stratified according to post-stroke interval (<3, 3-12, 12-24, >24 months) and cognitive recovery or decline using logistic regression. Models were adjusted for age, sex, education, prior stroke, infarct volume, and study site.

RESULTS

We included 2341 patients with 4657 cognitive assessments. PSCI was present in 398/844 patients (47%) <3 months, 709/1640 (43%) at 3-12 months, 243/853 (28%) at 12-24 months, and 208/522 (40%) >24 months. Cognitive recovery occurred in 64/181 (35%) patients and cognitive decline in 26/287 (9%). The network impact score predicted PSCI in the univariable (OR 1.50, 95%CI 1.34-1.68) and multivariable (OR 1.27, 95%CI 1.10-1.46) GEE model, with similar ORs in the logistic regression models for specified post-stroke intervals. The network impact score was not associated with cognitive recovery or decline.

CONCLUSIONS

The network impact score is an independent predictor of PSCI. As such, the network impact score may contribute to a more precise and individualized cognitive prognostication in patients with ischemic stroke. Future studies should address if multimodal prediction models, combining the network impact score with demographics, clinical characteristics and other advanced brain imaging biomarkers, will provide accurate individualized prediction of PSCI. A tool for calculating the network impact score is freely available at https://metavcimap.org/features/software-tools/lsm-viewer/.

Long-Term Cognitive Decline After Stroke: An Individual Participant Data Meta-Analysis

BACKGROUND AND PURPOSE

Poststroke cognitive impairment is common, but the trajectory and magnitude of cognitive decline after stroke is unclear. We examined the course and determinants of cognitive change after stroke using individual participant data from the Stroke and Cognition Consortium.

METHODS

Nine longitudinal hospital-based cohorts from 7 countries were included. Neuropsychological test scores and normative data were used to calculate standardized scores for global cognition and 5 cognitive domains. One-step individual participant data meta-analysis was used to examine the rate of change in cognitive function and risk factors for cognitive decline after stroke. Stroke-free controls were included to examine rate differences. Based on the literature and our own data that showed short-term improvement in cognitive function after stroke, key analyses were restricted to the period beginning 1-year poststroke to focus on its long-term effects.

RESULTS

A total of 1488 patients (mean age, 66.3 years; SD, 11.1; 98% ischemic stroke) were followed for a median of 2.68 years (25th-75th percentile: 1.21-4.14 years). After an initial period of improvement through up to 1-year poststroke, decline was seen in global cognition and all domains except executive function after adjusting for age, sex, education, vascular risk factors, and stroke characteristics (-0.053 SD/year [95% CI, -0.073 to -0.033]; P<0.001 for global cognition). Recurrent stroke and older age were associated with faster decline. Decline was significantly faster in patients with stroke compared with controls (difference=-0.078 SD/year [95% CI, -0.11 to -0.045]; P<0.001 for global cognition in a subgroup analysis).

CONCLUSIONS

Patients with stroke experience cognitive decline that is faster than that of stroke-free controls from 1 to 3 years after onset. An increased rate of decline is associated with older age and recurrent stroke.

Post-Stroke Cognitive Impairment: Pathophysiological Insights into Brain Disconnectome from Advanced Neuroimaging Analysis Techniques

The neurological symptoms of stroke have traditionally provided the foundation for functional mapping of the brain. However, there are many unresolved aspects in our understanding of cerebral activity, especially regarding high-level cognitive functions. This review provides a comprehensive look at the pathophysiology of post-stroke cognitive impairment in light of recent findings from advanced imaging techniques. Combining network neuroscience and clinical neurology, our research focuses on how changes in brain networks correlate with post-stroke cognitive prognosis. More specifically, we first discuss the general consequences of stroke lesions due to damage of canonical resting-state large-scale networks or changes in the composition of the entire brain. We also review emerging methods, such as lesion-network mapping and gradient analysis, used to study the aforementioned events caused by stroke lesions. Lastly, we examine other patient vulnerabilities, such as superimposed amyloid pathology and blood-brain barrier leakage, which potentially lead to different outcomes for the brain network compositions even in the presence of similar stroke lesions. This knowledge will allow a better understanding of the pathophysiology of post-stroke cognitive impairment and provide a theoretical basis for the development of new treatments, such as neuromodulation.

Strategic Infarct Locations for Poststroke Depressive Symptoms: A Lesion- and Disconnection-Symptom Mapping Study

BACKGROUND

Depression is the most common neuropsychiatric complication after stroke. Infarct location is associated with poststroke depressive symptoms (PSDS), but it remains debated which brain structures are critically involved. We performed a large-scale lesion-symptom mapping study to identify infarct locations and white matter disconnections associated with PSDS.

METHODS

We included 553 patients (mean [SD] age = 69 [11] years, 42% female) with acute ischemic stroke. PSDS were measured using the 30-item Geriatric Depression Scale. Multivariable support vector regression (SVR)-based analyses were performed both at the level of individual voxels (voxel-based lesion-symptom mapping) and at predefined regions of interest to relate infarct location to PSDS. We externally validated our findings in an independent stroke cohort (N = 459). Finally, disconnectome-based analyses were performed using SVR voxel-based lesion-symptom mapping, in which white matter fibers disconnected by the infarct were analyzed instead of the infarct itself.

RESULTS

Infarcts in the right amygdala, right hippocampus, and right pallidum were consistently associated with PSDS (permutation-based p < .05) in SVR voxel-based lesion-symptom mapping and SVR region-of-interest analyses. External validation confirmed the association between infarcts in the right amygdala and pallidum, but not the right hippocampus, and PSDS. Disconnectome-based analyses revealed that disconnections in the right parahippocampal white matter, right thalamus and pallidum, and right anterior thalamic radiation were significantly associated (permutation-based p < .05) with PSDS.

CONCLUSIONS

Infarcts in the right amygdala and pallidum and disconnections of right limbic and frontal cortico-basal ganglia-thalamic circuits are associated with PSDS. Our findings provide a comprehensive and integrative picture of strategic infarct locations for PSDS and shed new light on pathophysiological mechanisms of depression after stroke.

Anatomy of phonemic and semantic fluency: A lesion and disconnectome study in 1231 stroke patients

Disturbances of semantic and phonemic fluency are common after brain damage, as a manifestation of language, executive, or memory dysfunction. Lesion-symptom mapping (LSM) studies can provide fundamental insights in shared and distinct anatomical correlates of these cognitive functions and help to understand which patients suffer from these deficits. We performed a multivariate support vector regression-based lesion-symptom mapping and structural disconnection study on semantic and phonemic fluency in 1231 patients with acute ischemic stroke. With the largest-ever LSM study on verbal fluency we achieved almost complete brain lesion coverage. Lower performance on both fluency types was related to left hemispheric frontotemporal and parietal cortical regions, and subcortical regions centering on the left thalamus. Distinct correlates for phonemic fluency were the anterior divisions of middle and inferior frontal gyri. Distinct correlates for semantic fluency were the posterior regions of the middle and inferior temporal gyri, parahippocampal and fusiform gyri and triangular part of the inferior frontal gyrus. The disconnectome-based analyses additionally revealed phonemic fluency was associated with a more extensive frontoparietal white matter network, whereas semantic fluency was associated with disconnection of the fornix, mesiotemporal white matter, splenium of the corpus callosum. These results provide the most detailed outline of the anatomical correlates of phonemic and semantic fluency to date, stress the crucial role of subcortical regions and reveal a novel dissociation in the left temporal lobe.

Insurance coverage gap for treatment of melasma compared to rosacea: it pays to be light

Treatments for many common dermatologic diagnoses are denied insurance coverage due to their arbitrary cosmetic classification. Melasma is one such diagnosis often considered cosmetic by payers, and since it is commonly identified in darker-skinned individuals, its cosmetic classification creates an economic barrier for patients of color. Although dermatologists have previously described insurance coverage gaps for conditions typically seen in patients of color, this coverage gap has never been quantified.¹ Thus, we investigated the rate of insurance coverage for first-line topical treatments for rosacea versus melasma. Rosacea and melasma share a number of key features - both are common, chronic, dermatological conditions that are exacerbated by sun exposure, are primarily treated topically, and cause measurably decreased quality of life in affected patients.^2,3 Rosacea, however, is often diagnosed in patients with Fitzpatrick skin types I-II, with 91.8% of rosacea diagnoses seen in white patients, while melasma is predominantly diagnosed in patients with Fitzpatrick skin types III-V.^4-6.

Differential effects of body mass index on domain-specific cognitive outcomes after stroke

Although the obesity paradox is an important modifiable factor in cardiovascular diseases, little research has been conducted to determine how it affects post-stroke cognitive function. We aimed to investigate the association between body mass index (BMI) and domain-specific cognitive outcomes, focusing on the subdivision of each frontal domain function in post-ischemic stroke survivors. A total of 335 ischemic stroke patients were included in the study after completion of the Korean-Mini Mental Status Examination (K-MMSE) and the vascular cognitive impairment harmonization standards neuropsychological protocol at 3 months after stroke. Frontal lobe functions were analyzed using semantic/phonemic fluency, processing speed, and mental set shifting. Our study participants were categorized into four groups according to BMI quartiles. The z-scores of K-MMSE at 3 months differed significantly between the groups after adjustment for initial stroke severity (p = 0.014). Global cognitive function in stroke survivors in the Q1 (the lowest quartile) BMI group was significantly lower than those in Q2 and Q4 (the highest quartile) BMI groups (K-MMSE z-scores, Q1: − 2.10 ± 3.40 vs. Q2: 0.71 ± 1.95 and Q4: − 1.21 ± 1.65). Controlled oral word association test findings indicated that phonemic and semantic word fluency was lower in Q4 BMI group participants than in Q2 BMI group participants (p = 0.016 and p = 0.023 respectively). BMI might differentially affect cognitive domains after ischemic stroke. Although being underweight may negatively affect global cognition post-stroke, obesity could induce frontal lobe dysfunctions, specifically phonemic and semantic word fluency.

High Triglyceride Glucose Index Is Associated with Poor Outcomes in Ischemic Stroke Patients after Reperfusion Therapy

INTRODUCTION

The triglyceride glucose index (TyG index) is a simple and reliable surrogate marker of insulin resistance (IR) that can predict functional outcomes and mortality after acute ischemic stroke (AIS). However, it is unclear whether the TyG index is associated with functional outcomes in patients with stroke who receive reperfusion therapy. Thus, we aimed to explore the prognostic value of the TyG index for the clinical outcomes of patients with AIS who underwent reperfusion therapy.

METHODS

We retrospectively assessed patients with AIS, with occlusion of either the middle cerebral artery or internal carotid artery, who were evaluated using multiphase computed tomography angiography (mCTA) and received reperfusion therapy. The TyG index was calculated as "ln [fasting glucose level (mg/dL) × triglyceride level (mg/dL)]/2." Collateral status was evaluated using mCTA based on the University of Calgary Scale. Clinical outcomes included 3-month functional outcomes, early neurological deterioration, recanalization status, and hemorrhagic transformation.

RESULTS

In all, 183 subjects (age 69.5 ± 12.4 years; men, 59.0%) were enrolled. The median initial National Institutes of Health Stroke Scale score was 15.0 (interquartile range [IQR] 11-18). The median TyG index was 4.8 (IQR, 4.6-5.1), and 158 patients had TyG levels >4.49, which represents the presence of IR. On univariate analysis, a higher TyG index was associated with both early neurological deterioration (18.4 vs. 0.0%, p = 0.041) and a 3-month poor functional outcome (mRS3-6) (61.4 vs. 32.0%, p = 0.011). After adjusting for multiple variables, including age, sex, type of reperfusion therapy, recanalization status, initial stroke severity, type of stroke, and history of hypertension and diabetes, high TyG index remained an independent predictor of a poor 3-month functional outcome (adjusted OR, 5.22; p = 0.014). However, TyG levels were not significantly associated with collateral status (p = 0.756).

CONCLUSIONS

IR, represented by a high TyG index, may predict poor 3-month functional outcomes in patients with AIS who undergo reperfusion therapy.

High Neutrophil-Lymphocyte Ratio Predicts Post-stroke Cognitive Impairment in Acute Ischemic Stroke Patients

Background and Aims: Systemic inflammation is associated with an increased risk of cognitive impairment and dementia, but the associations between them in stroke patients are less clear. We examined the impact of systemic inflammation represented as the neutrophil-lymphocyte ratio (NLR) on the development of post-stroke cognitive impairment (PSCI) and domain-specific cognitive outcomes 3-month after ischemic stroke. Methods: Using prospective stroke registry data, we consecutively enrolled 345 participants with ischemic stroke whose cognitive functions were evaluated 3-month after stroke. Their cognition was assessed with the Korean version of the Vascular Cognitive Impairment Harmonization Standards and the Korean-Mini Mental Status Examination. PSCI was defined as a z-score of < -2 standard deviations for age, sex, and education adjusted means in at least one cognitive domain. The participants were categorized into five groups according to the quintiles of NLR (lowest NLR, Q1). The cross-sectional association between NLR and PSCI was assessed using multiple logistic regression, adjusting for age, sex, education, vascular risk factors, and stroke type. Results: A total of 345 patients were enrolled. The mean age was 63.0 years and the median NIHSS score and NLR were 2 [1-4] and 2.26 [1.65-2.91], respectively. PSCI was identified in 71 (20.6%) patients. NLR was a significant predictor for PSCI both as a continuous variable (adjusted OR, 1.14; 95% CI, 1.00-1.31) and as a categorical variable (Q5, adjusted OR, 3.26; 95% CI, 1.17-9.08). Patients in the Q5 group (NLR ≥ 3.80) showed significantly worse performance in global cognition and in visuospatial and memory domains. Conclusions: NLR in the acute stage of ischemic stroke was independently associated with PSCI at 3 months after stroke, and high NLR was specifically associated with cognitive dysfunction in the memory and visuospatial domains. Thus, systemic inflammation may be a modifiable risk factor that may influence cognitive outcomes after stroke.

Strategic infarct locations for post-stroke cognitive impairment: a pooled analysis of individual patient data from 12 acute ischaemic stroke cohorts

BACKGROUND

Post-stroke cognitive impairment (PSCI) occurs in approximately half of people in the first year after stroke. Infarct location is a potential determinant of PSCI, but a comprehensive map of strategic infarct locations predictive of PSCI is unavailable. We aimed to identify infarct locations most strongly predictive of PSCI after acute ischaemic stroke and use this information to develop a prediction model.

METHODS

In this large-scale multicohort lesion-symptom mapping study, we pooled and harmonised individual patient data from 12 cohorts through the Meta-analyses on Strategic Lesion Locations for Vascular Cognitive Impairment using Lesion-Symptom Mapping (Meta VCI Map) consortium. The identified cohorts (as of Jan 1, 2019) comprised patients with acute symptomatic infarcts on CT or MRI (with available infarct segmentations) and a cognitive assessment up to 15 months after acute ischaemic stroke onset. PSCI was defined as performance lower than the fifth percentile of local normative data, on at least one cognitive domain on a multidomain neuropsychological assessment or on the Montreal Cognitive Assessment. Voxel-based lesion-symptom mapping (VLSM) was used to calculate voxel-wise odds ratios (ORs) for PSCI that were mapped onto a three-dimensional brain template to visualise PSCI risk per location. For the prediction model of PSCI risk, a location impact score on a 5-point scale was derived from the VLSM results on the basis of the mean voxel-wise coefficient (ln[OR]) within each patient's infarct. We did combined internal-external validation by leave-one-cohort-out cross-validation for all 12 cohorts using logistic regression. Predictive performance of a univariable model with only the location impact score was compared with a multivariable model with addition of other clinical PSCI predictors (age, sex, education, time interval between stroke onset and cognitive assessment, history of stroke, and total infarct volume). Testing of visual ratings was done by three clinicians, and accuracy, inter-rater reliability, and intra-rater reliability were assessed with Cohen's weighted kappa.

FINDINGS

In our sample of 2950 patients (mean age 66·8 years [SD 11·6]; 1157 [39·2%] women), 1286 (43·6%) had PSCI. We achieved high lesion coverage of the brain in our analyses (86·9%). Infarcts in the left frontotemporal lobes, left thalamus, and right parietal lobe were strongly associated with PSCI (after false discovery rate correction, q<0·01; voxel-wise ORs >20). On cross-validation, the location impact score showed good correspondence, based on visual assessment of goodness of fit, between predicted and observed risk of PSCI across cohorts after adjusting for cohort-specific PSCI occurrence. Cross-validations showed that the location impact score by itself had similar performance to the combined model with other PSCI predictors, while allowing for easy visual assessment. Therefore the univariable model with only the location impact score was selected as the final model. Correspondence between visual ratings and actual location impact score (Cohen's weighted kappa: range 0·88-0·92), inter-rater agreement (0·85-0·87), and intra-rater agreement (for a single rater, 0·95) were all high.

INTERPRETATION

To the best of our knowledge, this study provides the first comprehensive map of strategic infarct locations associated with risk of PSCI. A location impact score was derived from this map that robustly predicted PSCI across cohorts. Furthermore, we developed a quick and reliable visual rating scale that might in the future be applied by clinicians to identify individual patients at risk of PSCI.

FUNDING

The Netherlands Organisation for Health Research and Development.

Generative lesion pattern decomposition of cognitive impairment after stroke

Cognitive impairment is a frequent and disabling sequela of stroke. There is however incomplete understanding of how lesion topographies in the left and right cerebral hemisphere brain interact to cause distinct cognitive deficits. We integrated machine learning and Bayesian hierarchical modelling to enable a hemisphere-aware analysis of 1080 acute ischaemic stroke patients with deep profiling ∼3 months after stroke. We show the relevance of the left hemisphere in the prediction of language and memory assessments and relevance of the right hemisphere in the prediction of visuospatial functioning. Global cognitive impairments were equally well predicted by lesion topographies from both sides. Damage to the hippocampal and occipital regions on the left was particularly informative about lost naming and memory functions, while damage to these regions on the right was linked to lost visuospatial functioning. Global cognitive impairment was predominantly linked to lesioned tissue in the supramarginal and angular gyrus, the post-central gyrus as well as the lateral occipital and opercular cortices of the left hemisphere. Hence, our analysis strategy uncovered that lesion patterns with unique hemispheric distributions are characteristic of how cognitive capacity is lost due to ischaemic brain tissue damage.

Development of imaging-based risk scores for prediction of intracranial haemorrhage and ischaemic stroke in patients taking antithrombotic therapy after ischaemic stroke or transient ischaemic attack: a pooled analysis of individual patient data from cohort studies

BACKGROUND

Balancing the risks of recurrent ischaemic stroke and intracranial haemorrhage is important for patients treated with antithrombotic therapy after ischaemic stroke or transient ischaemic attack. However, existing predictive models offer insufficient performance, particularly for assessing the risk of intracranial haemorrhage. We aimed to develop new risk scores incorporating clinical variables and cerebral microbleeds, an MRI biomarker of intracranial haemorrhage and ischaemic stroke risk.

METHODS

We did a pooled analysis of individual-patient data from the Microbleeds International Collaborative Network (MICON), which includes 38 hospital-based prospective cohort studies from 18 countries. All studies recruited participants with previous ischaemic stroke or transient ischaemic attack, acquired baseline MRI allowing quantification of cerebral microbleeds, and followed-up participants for ischaemic stroke and intracranial haemorrhage. Participants not taking antithrombotic drugs were excluded. We developed Cox regression models to predict the 5-year risks of intracranial haemorrhage and ischaemic stroke, selecting candidate predictors on biological relevance and simplifying models using backward elimination. We derived integer risk scores for clinical use. We assessed model performance in internal validation, adjusted for optimism using bootstrapping. The study is registered on PROSPERO, CRD42016036602.

FINDINGS

The included studies recruited participants between Aug 28, 2001, and Feb 4, 2018. 15 766 participants had follow-up for intracranial haemorrhage, and 15 784 for ischaemic stroke. Over a median follow-up of 2 years, 184 intracranial haemorrhages and 1048 ischaemic strokes were reported. The risk models we developed included cerebral microbleed burden and simple clinical variables. Optimism-adjusted c indices were 0·73 (95% CI 0·69-0·77) with a calibration slope of 0·94 (0·81-1·06) for the intracranial haemorrhage model and 0·63 (0·62-0·65) with a calibration slope of 0·97 (0·87-1·07) for the ischaemic stroke model. There was good agreement between predicted and observed risk for both models.

INTERPRETATION

The MICON risk scores, incorporating clinical variables and cerebral microbleeds, offer predictive value for the long-term risks of intracranial haemorrhage and ischaemic stroke in patients prescribed antithrombotic therapy for secondary stroke prevention; external validation is warranted.

FUNDING

British Heart Foundation and Stroke Association.

Blood pressure variability is related to faster cognitive decline in ischemic stroke patients: PICASSO subanalysis

Blood pressure variability (BPV) is associated with higher cardiovascular morbidity risks; however, its association with cognitive decline remains unclear. We investigated whether higher BPV is associated with faster declines in cognitive function in ischemic stroke (IS) patients. Cognitive function was evaluated between April 2010 and August 2015 using the Mini-mental State Examination (MMSE) and Montreal Cognitive Assessment in 1,240 Korean PICASSO participants. Patients for whom baseline and follow-up cognitive test results and at least five valid BP readings were available were included. A restricted maximum likelihood–based Mixed Model for Repeated Measures was used to compare changes in cognitive function over time. Among a total of 746 participants (64.6 ± 10.8 years; 35.9% female). Baseline mean-MMSE score was 24.9 ± 4.7. The median number of BP readings was 11. During a mean follow-up of 2.6 years, mean baseline and last follow-up MMSE scores were 25.4 ± 4.8 vs. 27.8 ± 4.4 (the lowest BPV group) and 23.9 ± 5.2 vs. 23.2 ± 5.9 (the highest BPV group). After adjusting for multiple variables, higher BPV was independently associated with faster cognitive decline over time. However, no significant intergroup difference in cognitive changes associated with mean systolic BP was observed. Further research is needed to elucidate how BPV might affect cognitive function.

Post-stroke cognitive impairment on the Mini-Mental State Examination primarily relates to left middle cerebral artery infarcts

Background

Post-stroke cognitive impairment can occur after damage to various brain regions, and cognitive deficits depend on infarct location. The Mini-Mental State Examination (MMSE) is still widely used to assess post-stroke cognition, but it has been criticized for capturing only certain cognitive deficits. Along these lines, it might be hypothesized that cognitive deficits as measured with the MMSE primarily involve certain infarct locations.

Aims

This comprehensive lesion-symptom mapping study aimed to determine which acute infarct locations are associated with post-stroke cognitive impairment on the MMSE.

Methods

We examined associations between impairment on the MMSE (<5th percentile; normative data) and infarct location in 1198 patients (age 67 ± 12 years, 43% female) with acute ischemic stroke using voxel-based lesion-symptom mapping. As a frame of reference, infarct patterns associated with impairments in individual cognitive domains were determined, based on a more detailed neuropsychological assessment.

Results

Impairment on the MMSE was present in 420 patients (35%). Large voxel clusters in the left middle cerebral artery territory and thalamus were significantly (p < 0.01) associated with cognitive impairment on the MMSE, with highest odds ratios (>15) in the thalamus and superior temporal gyrus. In comparison, domain-specific impairments were related to various infarct patterns across both hemispheres including the left medial temporal lobe (verbal memory) and right parietal lobe (visuospatial functioning).

Conclusions

Our findings indicate that post-stroke cognitive impairment on the MMSE primarily relates to infarct locations in the left middle cerebral artery territory. The MMSE is apparently less sensitive to cognitive deficits that specifically relate to other locations.

Serum Homocysteine Is Associated With HDL Only in Stroke Patients With Small Vessel Occlusion

Background: Although controversial, homocysteine (Hcy) and lipid parameters have been associated with particular stroke subtypes. However, there are limited studies concerning the relationship between Hcy and lipid levels in acute ischemic stroke (AIS). We evaluated the impact of Hcy levels on lipid profiles in terms of specific stroke subtypes. Methods: A total of 2,324 patients with first-ever AIS were recruited from two hospitals in South Korea. The exclusion criteria were as follows: (a) pre-stroke modified Rankin scale (mRS) ≥ 1, (b) undetermined or other stroke etiology, and (c) absence of Hcy data. Among the 1,580 eligible patients, the Hcy level was divided into tertile groups. Logistic regression was used to assess association of Hcy levels with lipid levels by stroke subtypes. Results: Significant downward trends in total cholesterol, low-density lipoprotein (LDL), and high-density lipoprotein (HDL) were only observed in patients with small vessel occlusion (SVO) as Hcy increased. In logistic regression analysis, while in patients with SVO subtype, the highest level of Hcy tertiles (OR = 1.648, 95% CI = 1.047-2.594) was associated with the lower HDL level (≤40 mg/dL), the significance disappeared in patients with LAA and CE subtypes. Conclusion: Although our study does not demonstrate causal relationship, we suggest that Hcy might play a mediating role between HDL and SVO stroke development. To clarify the role of Hcy on AIS, this study will provide academic support for designing future research.

Prediction of Coronary Artery Calcium Score Using Machine Learning in a Healthy Population

Background: Coronary artery calcium score (CACS) is a reliable predictor for future cardiovascular disease risk. Although deep learning studies using computed tomography (CT) images to predict CACS have been reported, no study has assessed the feasibility of machine learning (ML) algorithms to predict the CACS using clinical variables in a healthy general population. Therefore, we aimed to assess whether ML algorithms other than binary logistic regression (BLR) could predict high CACS in a healthy population with general health examination data. Methods: This retrospective observational study included participants who had regular health screening including coronary CT angiography. High CACS was defined by the Agatston score ≥ 100. Univariable and multivariable BLR was performed to assess predictors for high CACS in the entire dataset. When performing ML prediction for high CACS, the dataset was randomly divided into a training and test dataset with a 7:3 ratio. BLR, catboost, and xgboost algorithms with 5-fold cross-validation and grid search technique were used to find the best performing classifier. Performance comparison of each ML algorithm was evaluated with the area under the receiver operating characteristic (AUROC) curve. Results: A total of 2133 participants were included in the final analysis. Mean age and proportion of male sex were 55.4 ± 11.3 years and 1483 (69.5%), respectively. In multivariable BLR analysis, age (odds ratio [OR], 1.12; 95% confidence interval [CI], 1.10–1.15, p < 0.001), male sex (OR, 2.91; 95% CI, 1.57–5.38, p < 0.001), systolic blood pressure (OR, 1.02; 95% CI, 1.00–1.03, p = 0.019), and low-density lipoprotein cholesterol (OR, 1.00; 95% CI, 0.99–1.00, p = 0.047) were significant predictors for high CACS. Performance in predicting high CACS of xgboost was AUROC of 0.823, followed by catboost (0.750) and BLR (0.585). The comparison of AUROC between xgboost and BLR was significant (p for AUROC comparison < 0.001). Conclusions: Xgboost ML algorithm was found to be a more reliable predictor of CACS in healthy participants compared to the BLR algorithm. ML algorithms may be useful for predicting CACS with only laboratory data in healthy participants.