A Multimodal Ensemble Deep Learning Model for Functional Outcome Prognosis of Stroke Patients.

BACKGROUND AND PURPOSE: The accurate prediction of functional outcomes in patients with acute ischemic stroke (AIS) is crucial for informed clinical decision-making and optimal resource utilization. As such, this study aimed to construct an ensemble deep learning model that integrates multimodal imaging and clinical data to predict the 90-day functional outcomes after AIS. METHODS: We used data from the Korean Stroke Neuroimaging Initiative database, a prospective multicenter stroke registry to construct an ensemble model integrated individual 3D convolutional neural networks for diffusion-weighted imaging and fluid-attenuated inversion recovery (FLAIR), along with a deep neural network for clinical data, to predict 90-day functional independence after AIS using a modified Rankin Scale (mRS) of 3-6. To evaluate the performance of the ensemble model, we compared the area under the curve (AUC) of the proposed method with that of individual models trained on each modality to identify patients with AIS with an mRS score of 3-6. RESULTS: Of the 2,606 patients with AIS, 993 (38.1%) achieved an mRS score of 3-6 at 90 days post-stroke. Our model achieved AUC values of 0.830 (standard cross-validation [CV]) and 0.779 (time-based CV), which significantly outperformed the other models relying on single modalities: b-value of 1,000 s/mm2 (P<0.001), apparent diffusion coefficient map (P<0.001), FLAIR (P<0.001), and clinical data (P=0.004). CONCLUSION: The integration of multimodal imaging and clinical data resulted in superior prediction of the 90-day functional outcomes in AIS patients compared to the use of a single data modality.

Dilated perivascular spaces and steno-occlusive changes in children and adults with moyamoya disease.

BACKGROUND: Dilated perivascular spaces (DPVS), known as one of imaging markers in cerebral small vessel disease, may be found in patients with moyamoya disease (MMD). However, little is known about DPVS in MMD. The purpose of this study was to investigate the distribution pattern of dPVS in children and adults with MMD and determine whether it is related to steno-occlusive changes of MMD. METHODS: DPVS was scored in basal ganglia (BG) and white matter (WM) on T2-weighted imaging, using a validated 4-point semi-quantitative score. The degree of dPVS was classified as high (score > 2) or low (score ≤ 2) grade. The steno-occlusive changes on MR angiography (MRA) was scored using a validated MRA grading. Asymmetry of DPVS and MRA grading was defined as a difference of 1 grade or higher between hemispheres. RESULTS: Fifty-one patients with MMD (mean age 24.9 ± 21.1 years) were included. Forty-five (88.2%) patients had high WM-DPVS grade (degree 3 or 4). BG-DPVS was found in 72.5% of all patients and all were low grade (degree 1 or 2). The distribution patterns of DPVS degree in BG (P = 1.000) and WM (P = 0.767) were not different between child and adult groups. The asymmetry of WM-DPVS (26%) and MRA grade (42%) were significantly correlated to each other (Kendall's tau-b = 0.604, P < 0.001). CONCLUSIONS: DPVS of high grade in MMD is predominantly found in WM, which was not different between children and adults. The correlation between asymmetry of WM-DPVS degree and MRA grade suggests that weak cerebral artery pulsation due to steno-occlusive changes may affect WM-DPVS in MMD.

Corrected QTc interval combined with troponin value and mortality in acute ischemic stroke.

Background and Purpose: Cardiac biomarkers including, elevated troponin (ET) and prolonged heart rate-corrected QT (PQTc) interval on electrocardiography are known to frequent and have a prognostic significance in patients with acute ischemic stroke (AIS). However, it is still challenging to practically apply the results for appropriate risk stratification. This study evaluate whether combining ET and PQTc interval can better assess the long-term prognosis in AIS patients. Methods: In this prospectively registered observational study between May 2007 and December 2011, ET was defined as serum troponin-I ≥ 0.04 ng/ml and PQTc interval was defined as the highest tertile of sex-specific QTc interval (men ≥ 469 ms or women ≥ 487 ms). Results: Among the 1,668 patients [1018 (61.0%) men; mean age 66.0 ± 12.4 years], patients were stratified into four groups according to the combination of ET and PQTc intervals. During a median follow-up of 33 months, ET (hazard ratio [HR]: 4.38, 95% confidence interval [CI]: 2.94-6.53) or PQTc interval (HR: 1.53, 95% CI: 1.16-2.01) alone or both (HR: 1.77, 95% CI: 1.16-2.71) was associated with increased all-cause mortality. Furthermore, ET, PQTc interval alone or both was associated with vascular death, whereas only ET alone was associated with non-vascular death. Comorbidity burden, especially atrial fibrillation and congestive heart failure, and stroke severity gradually increased both with troponin value and QTc-interval. Conclusions: In patients with AIS, combining ET and PQTc interval on ECG enhances risk stratification for long-term mortality while facilitating the discerning ability for the burden of comorbidities and stroke severity.

Papilledema and venous stasis in patients with cerebral venous and sinus thrombosis.

BACKGROUND: Cerebral venous and sinus thrombosis (CVST) can cause increased intracranial pressure, often leading to papilledema. In this study, we investigated the association between papilledema and venous stasis on susceptibility weighted imaging (SWI) in CVST. METHODS: Patients with CVST between 2008 and 2020 were reviewed. Patients without fundoscopic examination or SWI were excluded in this study. Venous stasis was evaluated and scored for each cerebral hemisphere: each hemisphere was divided into 5 regions according to the venous drainage territories (superior sagittal sinus, Sylvian veins, transverse sinus and vein of Labbé, deep cerebral veins, and medullary veins) and 1 point was added if venous prominence was confirmed in one territory on SWI. The venous stasis score on SWI between cerebral hemispheres with and without papilledema was compared. RESULTS: Eight of 19 patients with CVST were excluded because of the absence of fundoscopic examination or SWI. Eleven patients (26.5 ± 2.1 years) were included in this study. Papilledema was identified in 6 patients: bilateral papilledema in 4 patients and unilateral papilledema in 2 patients. The venous stasis score on SWI was significantly higher (P = 0.013) in the hemispheres with papilledema (median, 4.0; 95% CI, 3.038-4.562) than in the hemispheres without papilledema (median, 2.5; 95% CI, 0.695-2.805). CONCLUSIONS: This study shows that higher score of venous stasis on SWI is associated with papilledema. Therefore, the venous stasis on SWI may be an imaging surrogate marker of increased intracranial pressure in patients with CVST.

Explanatory Power and Prognostic Implications of Factors Associated with Troponin Elevation in Acute Ischemic Stroke.

BACKGROUND AND PURPOSE: We investigated the impact of comorbidity burden on troponin elevation, with separate consideration of neurological conditions, in patients with acute ischemic stroke (AIS). METHODS: This prospective, observational cohort study consecutively enrolled patients with AIS for 2 years. Serum cardiac troponin I was repeatedly measured, and disease-related biomarkers were collected for diagnosis of preassigned comorbidities, including atrial fibrillation (AF), ischemic heart disease (IHD), myocardial hypertrophy (MH), heart failure (HF), renal insufficiency (RI), and active cancer. The severity of neurological deficits and insular cortical ischemic lesions were assessed as neurological conditions. Adjusted associations between these factors and troponin elevation were determined using a multivariate ordinal logistic regression model and area under the receiver operating characteristic curve (AUC). Cox proportional hazards model was used to determine the prognostic significance of comorbidity beyond neurological conditions. RESULTS: Among 1,092 patients (66.5±12.4 years, 63.3% male), 145 (13.3%) and 335 (30.7%) had elevated (≥0.040 ng/mL) and minimally-elevated (0.040-0.010 ng/mL) troponin, respectively. In the adjusted analysis, AF, MH, HF, RI, active cancer, and neurological deficits were associated with troponin elevation. The multivariate model with six comorbidities and two neurological conditions exhibited an AUC of 0.729 (95% confidence interval [CI], 0.698-0.759). In Cox regression, AF, IHD, and HF were associated with adverse cardio-cerebrovascular events, whereas HF and active cancer were associated with mortality. CONCLUSION: Troponin elevation in patients with AIS can be explained by the burden of comorbidities in combination with neurological status, which explains the prognostic significance of troponin assay.

Usefulness of cone-beam computed tomography to predict residual stenosis after carotid artery stenting.

OBJECTIVES: The long-term durability of carotid artery stenting (CAS) may be determined by various factors; however, residual stenosis is a known risk factor for in-stent restenosis. The authors of this article utilized cone-beam computed tomography (CBCT) in angiosuite to investigate plaque features affecting the character and quality of stent expansion after CAS. METHODS: Forty-two CAS cases with both pre- and post-CAS CBCT evaluations were included in this retrospective analysis. Five features derived from pre-CAS images were tested: (1) eccentricity, (2) overballoon, (3) maximum plaque thickness, (4) calcification barrier, and (5) stenotic degree. For post-CAS CBCT, stent configuration was assessed if the stent was expanded and oval or round in shape as well as outward or inward in orientation. Variables were tested if they were associated with oval expansion, outward expansion, and 20% residual stenosis after CAS. RESULTS: Oval or outward expansion is directly related to residual stenosis. The oval expansion was associated with maximum plaque thickness, and outward expansion was associated with the presence of a calcification barrier. Variables related to > 20% residual stenosis were the maximum plaque thickness, calcification barrier, and pre-CAS stenotic degree. CONCLUSIONS: CBCT for carotid stenosis may provide valuable information about plaque features, especially calcification features that may interfere with the angioplasty effect, as well as the characteristics and quality of stent expansion. Residual stenosis > 20% was associated with calcification barrier, maximum plaque thickness, and pre-CAS stenotic degree.

Prognostic Significance of Prolonged Corrected QT Interval in Acute Ischemic Stroke.

Background and Purpose: The aim of this study was to determine the relationship between the heart rate-corrected QT (QTc) interval and the risk of incident long-term mortality in patients with acute ischemic stroke (AIS), considering the impact of sex differences on clinical characteristics, outcomes, and QTc intervals. Methods: We analyzed prospectively registered data included patients with AIS who visited the emergency room within 24 h of stroke onset and underwent routine cardiac testing, such as measurements of cardiac enzymes and 12-lead ECG. QTc interval was corrected for heart rate using Fridericia's formula and was stratified by sex-specific quartiles. Cox proportional hazards models were used to examine the association between baseline QTc interval and incident all-cause death. Results: A total of 1,668 patients with 1,018 (61.0%) men and mean age 66.0 ± 12.4 years were deemed eligible. Based on the categorized quartiles of the QTc interval, cardiovascular risk profile, and stroke severity increased with prolonged QTc interval, and the risk of long-term mortality increased over a median follow-up of 33 months. Cox proportional hazard model analysis showed that the highest quartile of QTc interval (≥479 msec in men and ≥498 msec in women; hazard ratio [HR]: 1.49, 95% confidence interval [CI]: 1.07-2.08) was associated with all-cause death. Furthermore, dichotomized QTc interval prolongation, defined by the highest septile of the QTc interval (≥501 ms in men and ≥517 m in women: HR: 1.33, 95% CI: 1.00-1.80) was significantly associated with all-cause mortality after adjusting for all clinically relevant variables, such as stroke severity. Conclusions: Prolonged QTc interval was associated with increased risk of long-term mortality, in parallel with the increasing trend of prevalence of cardiovascular risk profiles and stroke severity, across sex differences in AIS patients.

Hospital Volume Threshold Associated with Higher Survival after Endovascular Recanalization Therapy for Acute Ischemic Stroke.

BACKGROUND AND PURPOSE: Endovascular recanalization therapy (ERT) is becoming increasingly important in the management of acute ischemic stroke (AIS). However, the hospital volume threshold for optimal ERT remains unknown. We investigated the relationship between hospital volume of ERT and risk-adjusted patient outcomes. METHODS: From the National Health Insurance claims data in Korea, 11,745 patients with AIS who underwent ERT from July 2011 to June 2016 in 111 hospitals were selected. We measured the hospital's ERT volume and patient outcomes, including the 30-day mortality, readmission, and postprocedural intracranial hemorrhage (ICH) rates. For each outcome measure, we constructed risk-adjusted prediction models incorporating demographic variables, the modified Charlson comorbidity index, and the stroke severity index (SSI), and validated them. Risk-adjusted outcomes of AIS cases were compared across hospital quartiles to confirm the volume-outcome relationship (VOR) in ERT. Spline regression was performed to determine the volume threshold. RESULTS: The mean AIS volume was 14.8 cases per hospital/year and the unadjusted means of mortality, readmission, and ICH rates were 11.6%, 4.6%, and 8.6%, respectively. The VOR was observed in the risk-adjusted 30-day mortality rate across all quartile groups, and in the ICH rate between the first and fourth quartiles (P<0.05). The volume threshold was 24 cases per year. CONCLUSIONS: There was an association between hospital volume and outcomes, and the volume threshold in ERT was identified. Policies should be developed to ensure the implementation of the AIS volume threshold for hospitals performing ERT.