RESUMEN
BACKGROUND: Early identification of large vessel occlusion (LVO) in patients with ischemic stroke is crucial for timely interventions. We propose a machine learning-based algorithm (JLK-CTL) that uses handcrafted features from noncontrast computed tomography to predict LVO. METHODS: We included patients with ischemic stroke who underwent concurrent noncontrast computed tomography and computed tomography angiography in seven hospitals. Patients from 5 of these hospitals, admitted between May 2011 and March 2015, were randomly divided into training and internal validation (9:1 ratio). Those from the remaining 2 hospitals, admitted between March 2021 and September 2021, were designated for external validation. From each noncontrast computed tomography scan, we extracted differences in volume, tissue density, and Hounsfield unit distribution between bihemispheric regions (striatocapsular, insula, M1-M3, and M4-M6, modified from the Alberta Stroke Program Early Computed Tomography Score). A deep learning algorithm was used to incorporate clot signs as an additional feature. Machine learning models, including ExtraTrees, random forest, extreme gradient boosting, support vector machine, and multilayer perceptron, as well as a deep learning model, were trained and evaluated. Additionally, we assessed the models' performance after incorporating the National Institutes of Health Stroke Scale scores as an additional feature. RESULTS: Among 2919 patients, 83 were excluded. Across the training (n=2463), internal validation (n=275), and external validation (n=95) datasets, the mean ages were 68.5±12.4, 67.6±13.8, and 67.9±13.6 years, respectively. The proportions of men were 57%, 53%, and 59%, with LVO prevalences of 17.0%, 16.4%, and 26.3%, respectively. In the external validation, the ExtraTrees model achieved a robust area under the curve of 0.888 (95% CI, 0.850-0.925), with a sensitivity of 80.1% (95% CI, 72.0-88.1) and a specificity of 88.6% (95% CI, 84.7-92.5). Adding the National Institutes of Health Stroke Scale score to the ExtraTrees model increased sensitivity (from 80.1% to 92.1%) while maintaining specificity. CONCLUSIONS: Our algorithm provides reliable predictions of LVO using noncontrast computed tomography. By enabling early LVO identification, our algorithm has the potential to expedite the stroke workflow.
Asunto(s)
Angiografía por Tomografía Computarizada , Infarto de la Arteria Cerebral Media , Tomografía Computarizada por Rayos X , Humanos , Masculino , Anciano , Femenino , Tomografía Computarizada por Rayos X/métodos , Persona de Mediana Edad , Infarto de la Arteria Cerebral Media/diagnóstico por imagen , Angiografía por Tomografía Computarizada/métodos , Aprendizaje Automático , Anciano de 80 o más Años , Algoritmos , Accidente Cerebrovascular Isquémico/diagnóstico por imagen , Aprendizaje Profundo , Valor Predictivo de las PruebasRESUMEN
BACKGROUND: Glycated albumin (GA) is an indicator of glycemic variability over the past 2-4 weeks and has suitable characteristics for predicting the prognosis of ischemic stroke during the acute phase. This study evaluated the association between early neurological deterioration (END) and GA values in patients with acute ischemic stroke (AIS). METHODS: We assessed consecutive patients with AIS between 2022 and 2023 at two large medical centers in Korea. END was defined as an increase of ≥ 2 in the total National Institutes of Health Stroke Scale (NIHSS) score or ≥ 1 in the motor NIHSS score within the first 72 h of admission. We evaluated various glycemic parameters including fasting glucose (mg/dL), hemoglobin A1c (%), and GA (%). RESULTS: In total, 531 patients with AIS were evaluated (median age: 69 years, male sex: 66.3%). In the multivariable logistic regression analysis, GA value was positively associated with END (adjusted odds ratio [aOR] = 3.24, 95% confidence interval [CI]: 1.10-9.50). Initial NIHSS score (aOR = 1.04, 95% CI: 1.01-1.08) and thrombolytic therapy (aOR = 2.06, 95% CI: 1.14-3.73) were also associated with END. In a comparison of the predictive power of glycemic parameters for END, GA showed a higher area under the curve value on the receiver operating characteristic curve than fasting glucose and hemoglobin A1c. CONCLUSIONS: High GA values were associated with END in patients with AIS. Furthermore, GA was a better predictor of END than fasting glucose or hemoglobin A1c.
Asunto(s)
Albúmina Sérica Glicada , Productos Finales de Glicación Avanzada , Accidente Cerebrovascular Isquémico , Anciano , Anciano de 80 o más Años , Femenino , Humanos , Masculino , Persona de Mediana Edad , Biomarcadores/sangre , Glucemia/metabolismo , Glucemia/análisis , Hemoglobina Glucada/análisis , Hemoglobina Glucada/metabolismo , Accidente Cerebrovascular Isquémico/sangre , Accidente Cerebrovascular Isquémico/diagnóstico , PronósticoRESUMEN
OBJECTIVE: Vagus nerve stimulation (VNS) has recently been reported to exert additional benefits for functional recovery in patients with brain injury. However, the mechanisms underlying these effects have not yet been elucidated. This study examined the effects of transcutaneous auricular VNS (taVNS) on cortical excitability in healthy adults. MATERIALS AND METHODS: We recorded subthreshold and suprathreshold single- and paired-pulse motor-evoked potentials (MEPs) in the right-hand muscles of 16 healthy adults by stimulating the left primary motor cortex. Interstimulus intervals were set at 2 milliseconds and 3 milliseconds for intracortical inhibition (ICI), and 10 milliseconds and 15 milliseconds for intracortical facilitation (ICF). taVNS was applied to the cymba conchae of both ears for 30 minutes. The intensity of taVNS was set to a maximum tolerable level of 1.95 mA. MEPs were measured before stimulation, 20 minutes after the beginning of the stimulation, and 10 minutes after the cessation of stimulation. RESULTS: The participants' age was 33.25 ± 7.08 years, and nine of 16 were male. No statistically significant changes were observed in the mean values of the single-pulse MEPs before, during, or after stimulation. Although the ICF showed an increasing trend after stimulation, the changes in ICI and ICF were not significant, primarily because of the substantial interindividual variability. CONCLUSIONS: The effect of taVNS on cortical excitability varied in healthy adults. An increase in ICF was observed after taVNS, although the difference was not statistically significant. Our findings contribute to the understanding of the mechanisms by which taVNS is effective in patients with brain disorders.
RESUMEN
A few cases of small fiber neuropathy (SFN) and tinnitus (TN) associated with coronavirus disease 2019 have been reported. However, the relationship between SFN and TN has not been studied. This study investigated a possible relationship between SFN and patients with TN (PwTNs) using autonomic function tests (AFTs) including quantitative sudomotor axon reflex tests (QSART). We performed QSARTs and other AFTs such as the Sympathetic skin response (SSR), Valsalva ratio (VR), and heart rate variability (HRV). The QSART results, obtained at seven hospitals using same protocols, were compared between PwTNs and healthy controls. We confirmed the abnormalities in SSR, VR, and HRV in PwTNs, although those parasympathetic AFTs were not performed in healthy controls. Additionally, we checked Tinnitus handicap inventory (THI) scores for PwTNs and ~50% of PwTNs had low-grade disability, whereas 9.3% had high-grade disability. Data from 57 PwTNs and 122 healthy controls were analyzed. The sweat volumes of QSART in the older age group tended to be higher in the PwTNs than in age-matched healthy controls, and significant differences between the PwTN and control groups were observed in the feet in both sexes (p < 0.001) and in the arms in women (p = 0.013). In the younger age group, the sweat volumes in the feet of men were higher in PwTNs than in healthy controls (p = 0.017). No association was observed between THI and QSART scores. In this study, the sweat volumes in QSARTs were higher in PwTNs than in healthy controls. However, abnormal SSR, HRV, and VR results were not commonly observed in PwTNs. Although the results should be interpreted with caution because of limitations in study, PwTNs might also have SFN apart from dysautonomia. This is the first study to perform QSART with other parasympathetic AFTs in PwTNs. However, larger and more rigorously controlled studies will be needed to reveal the relationship between SFN and TN in the future.
RESUMEN
BACKGROUND: Although stroke is commonly perceived as occurring in older adults, traumatic brain injury, one of the risk factors for stroke, is a leading cause of death in the younger adults. This study evaluated stroke risk in young-to-middle-aged adults based on traumatic brain injury severity and stroke subtypes. METHODS AND RESULTS: For this retrospective, population-based, cohort study, data of adults aged 18 to 49 years who were diagnosed with traumatic brain injury were obtained from the Korean National Health Insurance Service between 2010 and 2017. Traumatic brain injury history was measured based on the International Classification of Diseases, Tenth Revision (ICD-10), codes. Posttraumatic brain injury stroke risk was analyzed using a time-dependent Cox regression model. At baseline, 518423 patients with traumatic brain injury and 518 423 age- and sex-matched controls were included. The stroke incidence rate per 1000 person-years was 3.82 in patients with traumatic brain injury and 1.61 in controls. Stroke risk was approximately 1.89 times as high in patients with traumatic brain injury (hazard ratio, 1.89 [95% CI, 1.84-1.95]). After excluding stroke cases that occurred within 12 months following traumatic brain injury, these significant associations remained. In the subgroup analysis, patients with brain injury other than concussion had an approximately 9.34-fold risk of intracerebral hemorrhage than did the controls. CONCLUSIONS: Stroke prevention should be a priority even in young-to-middle-aged adult patients with traumatic brain injury. Managing stroke risk factors through regular health checkups and modifying health-related behaviors is necessary to prevent stroke.
Asunto(s)
Lesiones Traumáticas del Encéfalo , Humanos , Masculino , Femenino , Adulto , Lesiones Traumáticas del Encéfalo/epidemiología , Estudios Retrospectivos , Persona de Mediana Edad , Adulto Joven , República de Corea/epidemiología , Incidencia , Factores de Riesgo , Adolescente , Accidente Cerebrovascular/epidemiología , Medición de Riesgo , Factores de Tiempo , Factores de EdadRESUMEN
Aging manifests as many phenotypes, among which age-related changes in brain vessels are important, but underexplored. Thus, in the present study, we constructed a model to predict age using cerebrovascular morphological features, further assessing their clinical relevance using a novel pipeline. Age prediction models were first developed using data from a normal cohort (n = 1181), after which their relevance was tested in two stroke cohorts (n = 564 and n = 455). Our novel pipeline adapted an existing framework to compute generic vessel features for brain vessels, resulting in 126 morphological features. We further built various machine learning models to predict age using only clinical factors, only brain vessel features, and a combination of both. We further assessed deviation from healthy aging using the age gap and explored its clinical relevance by correlating the predicted age and age gap with various risk factors. The models constructed using only brain vessel features and those combining clinical factors with vessel features were better predictors of age than the clinical factor-only model (r = 0.37, 0.48, and 0.26, respectively). Predicted age was associated with many known clinical factors, and the associations were stronger for the age gap in the normal cohort. The age gap was also associated with important factors in the pooled cohort atherosclerotic cardiovascular disease risk score and white matter hyperintensity measurements. Cerebrovascular age, computed using the morphological features of brain vessels, could serve as a potential individualized marker for the early detection of various cerebrovascular diseases.
RESUMEN
Introduction: We developed and externally validated a fully automated algorithm using deep learning to detect large vessel occlusion (LVO) in computed tomography angiography (CTA). Method: A total of 2,045 patients with acute ischemic stroke who underwent CTA were included in the development of our model. We validated the algorithm using two separate external datasets: one with 64 patients (external 1) and another with 313 patients (external 2), with ischemic stroke. In the context of current clinical practice, thrombectomy amenable vessel occlusion (TAVO) was defined as an occlusion in the intracranial internal carotid artery (ICA), or in the M1 or M2 segment of the middle cerebral artery (MCA). We employed the U-Net for vessel segmentation on the maximum intensity projection images, followed by the application of the EfficientNetV2 to predict TAVO. The algorithm's diagnostic performance was evaluated by calculating the area under the receiver operating characteristics curve (AUC), sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). Results: The mean age in the training and validation dataset was 68.7 ± 12.6; 56.3% of participants were men, and 18.0% had TAVO. The algorithm achieved AUC of 0.950 (95% CI, 0.915-0.971) in the internal test. For the external datasets 1 and 2, the AUCs were 0.970 (0.897-0.997) and 0.971 (0.924-0.990), respectively. With a fixed sensitivity of 0.900, the specificities and PPVs for the internal test, external test 1, and external test 2 were 0.891, 0.796, and 0.930, and 0.665, 0.583, and 0.667, respectively. The algorithm demonstrated a sensitivity and specificity of approximately 0.95 in both internal and external datasets, specifically for cases involving intracranial ICA or M1-MCA occlusion. However, the diagnostic performance was somewhat reduced for isolated M2-MCA occlusion; the AUC for the internal and combined external datasets were 0.903 (0.812-0.944) and 0.916 (0.816-0.963), respectively. Conclusion: We developed and externally validated a fully automated algorithm that identifies TAVO. Further research is needed to evaluate its effectiveness in real-world clinical settings. This validated algorithm has the potential to assist early-career physicians, thereby streamlining the treatment process for patients who can benefit from endovascular treatment.
RESUMEN
BACKGROUND AND PURPOSE: Accurate classification of ischemic stroke subtype is important for effective secondary prevention of stroke. We used diffusion-weighted image (DWI) and atrial fibrillation (AF) data to train a deep learning algorithm to classify stroke subtype. METHODS: Model development was done in 2,988 patients with ischemic stroke from three centers by using U-net for infarct segmentation and EfficientNetV2 for subtype classification. Experienced neurologists (n=5) determined subtypes for external test datasets, while establishing a consensus for clinical trial datasets. Automatically segmented infarcts were fed into the model (DWI-only algorithm). Subsequently, another model was trained, with AF included as a categorical variable (DWI+AF algorithm). These models were tested: (1) internally against the opinion of the labeling experts, (2) against fresh external DWI data, and (3) against clinical trial dataset. RESULTS: In the training-and-validation datasets, the mean (±standard deviation) age was 68.0±12.5 (61.1% male). In internal testing, compared with the experts, the DWI-only and the DWI+AF algorithms respectively achieved moderate (65.3%) and near-strong (79.1%) agreement. In external testing, both algorithms again showed good agreements (59.3%-60.7% and 73.7%-74.0%, respectively). In the clinical trial dataset, compared with the expert consensus, percentage agreements and Cohen's kappa were respectively 58.1% and 0.34 for the DWI-only vs. 72.9% and 0.57 for the DWI+AF algorithms. The corresponding values between experts were comparable (76.0% and 0.61) to the DWI+AF algorithm. CONCLUSION: Our model trained on a large dataset of DWI (both with or without AF information) was able to classify ischemic stroke subtypes comparable to a consensus of stroke experts.
RESUMEN
BACKGROUND AND PURPOSE: The influence of imaging features of brain frailty on outcomes were investigated in acute ischemic stroke patients with minor symptoms and large-vessel occlusion (LVO). METHODS: This was a retrospective analysis of a prospective, multicenter, nationwide registry of consecutive patients with acute (within 24 h) minor (National Institutes of Health Stroke Scale score=0-5) ischemic stroke with anterior circulation LVO (acute minor LVO). Brain frailty was stratified according to the presence of an advanced white-matter hyperintensity (WMH) (Fazekas grade 2 or 3), silent/old brain infarct, or cerebral microbleeds. The primary outcome was a composite of stroke, myocardial infarction, and all-cause mortality within 1 year. RESULTS: In total, 1,067 patients (age=67.2±13.1 years [mean±SD], 61.3% males) were analyzed. The proportions of patients according to the numbers of brain frailty burdens were as follows: no burden in 49.2%, one burden in 30.0%, two burdens in 17.3%, and three burdens in 3.5%. In the Cox proportional-hazards analysis, the presence of more brain frailty burdens was associated with a higher risk of 1-year primary outcomes, but after adjusting for clinically relevant variables there were no significant associations between burdens of brain frailty and 1-year vascular outcomes. For individual components of brain frailty, an advanced WMH was independently associated with an increased risk of 1-year primary outcomes (adjusted hazard ratio [aHR]=1.33, 95% confidence interval [CI]=1.03-1.71) and stroke (aHR=1.32, 95% CI=1.00-1.75). CONCLUSIONS: The baseline imaging markers of brain frailty were common in acute minor ischemic stroke patients with LVO. An advanced WMH was the only frailty marker associated with an increased risk of vascular events. Further research is needed into the association between brain frailty and prognosis in patients with acute minor LVO.
RESUMEN
Importance: The associations between blood pressure (BP) decreases induced by medication and functional outcomes in patients with successful endovascular thrombectomy remain uncertain. Objective: To evaluate whether BP reductions induced by intravenous BP medications are associated with poor functional outcomes at 3 months. Design, Setting, and Participants: This cohort study was a post hoc analysis of the Outcome in Patients Treated With Intra-Arterial Thrombectomy-Optimal Blood Pressure Control trial, a comparison of intensive and conventional BP management during the 24 hours after successful recanalization from June 18, 2020, to November 28, 2022. This study included 302 patients who underwent endovascular thrombectomy, achieved successful recanalization, and exhibited elevated BP within 2 hours of successful recanalization at 19 stroke centers in South Korea. Exposure: A BP decrease was defined as at least 1 event of systolic BP less than 100 mm Hg. Patients were divided into medication-induced BP decrease (MIBD), spontaneous BP decrease (SpBD), and no BP decrease (NoBD) groups. Main Outcomes and Measures: The primary outcome was a modified Rankin scale score of 0 to 2 at 3 months, indicating functional independence. Primary safety outcomes were symptomatic intracerebral hemorrhage within 36 hours and mortality due to index stroke within 3 months. Results: Of the 302 patients (median [IQR] age, 75 [66-82] years; 180 [59.6%] men), 47 (15.6%)were in the MIBD group, 39 (12.9%) were in the SpBD group, and 216 (71.5%) were in the NoBD group. After adjustment for confounders, the MIBD group exhibited a significantly smaller proportion of patients with functional independence at 3 months compared with the NoBD group (adjusted odds ratio [AOR], 0.45; 95% CI, 0.20-0.98). There was no significant difference in functional independence between the SpBD and NoBD groups (AOR, 1.41; 95% CI, 0.58-3.49). Compared with the NoBD group, the MIBD group demonstrated higher odds of mortality within 3 months (AOR, 5.15; 95% CI, 1.42-19.4). The incidence of symptomatic intracerebral hemorrhage was not significantly different among the groups (MIBD vs NoBD: AOR, 1.89; 95% CI, 0.54-5.88; SpBD vs NoBD: AOR, 2.75; 95% CI, 0.76-9.46). Conclusions and Relevance: In this cohort study of patients with successful endovascular thrombectomy after stroke, MIBD within 24 hours after successful recanalization was associated with poor outcomes at 3 months. These findings suggested lowering systolic BP to below 100 mm Hg using BP medication might be harmful.
Asunto(s)
Hipertensión , Accidente Cerebrovascular , Anciano , Femenino , Humanos , Masculino , Presión Sanguínea , Hemorragia Cerebral , Estudios de Cohortes , Hipertensión/epidemiología , Presión , Accidente Cerebrovascular/cirugía , Anciano de 80 o más AñosRESUMEN
BACKGROUND: Multiple attempts of thrombectomy have been linked to a higher risk of intracerebral hemorrhage and worsened functional outcomes, potentially influenced by blood pressure (BP) management strategies. Nonetheless, the impact of intensive BP management following successful recanalization through multiple attempts remains uncertain. AIMS: This study aimed to investigate whether conventional and intensive BP managements differentially affect outcomes according to multiple-attempt recanalization (MAR) and first-attempt recanalization (FAR) groups. METHODS: In this secondary analysis of the OPTIMAL-BP trial, which was a comparison of intensive (systolic BP target: <140 mm Hg) and conventional (systolic BP target = 140-180 mm Hg) BP managements during the 24 h after successful recanalization, we included intention-to-treat population of the trial. Patients were divided into the MAR and the FAR groups. We examined a potential interaction between the number of thrombectomy attempts (MAR and FAR groups) and the effect of BP managements on clinical and safety outcomes. The primary outcome was functional independence at 3 months. Safety outcomes were symptomatic intracerebral hemorrhage within 36 h and mortality within 3 months. RESULTS: Of the 305 patients (median = 75 years), 102 (33.4%) were in the MAR group and 203 (66.6%) were in the FAR group. The intensive BP management was significantly associated with a lower rate of functional independence in the MAR group (intensive, 32.7% vs conventional, 54.9%, adjusted odds ratio (OR) = 0.33, 95% confidence interval (CI) = 0.12-0.90, p = 0.03). In the FAR group, the proportion of patients with functional independence was not significantly different between the BP managements (intensive, 42.5% vs conventional, 54.2%, adjusted OR = 0.73, 95% CI = 0.38-1.40). Incidences of symptomatic intracerebral hemorrhage and mortality rates were not significantly different according to the BP managements in both MAR and FAR groups. CONCLUSIONS: Among stroke patients who received multiple attempts of thrombectomy, intensive BP management for 24 h resulted in a reduced chance of functional independence at 3 months and did not reduce symptomatic intracerebral hemorrhage following successful reperfusion.
RESUMEN
Background: Diabetes is associated with an increased risk of Parkinson's disease dementia (PDD); however, it is unknown whether this association is dependent on continuous hyperglycemia, hypoglycemic events, or glycemic variability. We aimed to investigate the relationship between visit-to-visit fasting glucose variability and PDD development in patients with Parkinson's disease (PD). Methods: Using data from the Korean National Health Insurance Service, we examined 9,264 patients aged ≥40 years with de novo Parkinson's disease (PD) who underwent ≥3 health examinations and were followed up until December 2019. Glucose variability was measured using the coefficient of variation, variability independent of the mean, and average real variability. Fine and Gray competing regression analysis was performed to determine the effect of glucose variability on incident PDD. Results: During the 9.5-year follow-up period, 1,757 of 9,264 (19.0%) patients developed PDD. Patients with a higher visit-to-visit glucose variability had a higher risk of future PDD. In the multivariable adjusted model, patients with PD in the highest quartile (subdistribution hazard ratio [SHR] = 1.50, 95% CI 1.19 to 1.88), quartile 3 (SHR = 1.29, 95% CI 1.02 to 1.62), and quartile 2 (SHR = 1.30, 95% CI 1.04 to 1.63) were independently associated with a higher risk of PDD than those in the lowest quartile. Conclusion: We highlighted the effect of long-term glucose variability on the development of PDD in patients with PD. Furthermore, our findings suggest that preventive measures for constant glucose control may be necessary to prevent PDD.