Small vessel disease burden predicts functional outcomes in patients with acute ischemic stroke using machine learning.
Ontology highlight
ABSTRACT: Aims
Our purpose is to assess the role of cerebral small vessel disease (SVD) in prediction models in patients with different subtypes of acute ischemic stroke (AIS).Methods
We enrolled 398 small-vessel occlusion (SVO) and 175 large artery atherosclerosis (LAA) AIS patients. Functional outcomes were assessed using the modified Rankin Scale (mRS) at 90 days. MRI was performed to assess white matter hyperintensity (WMH), perivascular space (PVS), lacune, and cerebral microbleed (CMB). Logistic regression (LR) and machine learning (ML) were used to develop predictive models to assess the influences of SVD on the prognosis.Results
In the feature evaluation of SVO-AIS for different outcomes, the modified total SVD score (Gain: 0.38, 0.28) has the maximum weight, and periventricular WMH (Gain: 0.07, 0.09) was more important than deep WMH (Gain: 0.01, 0.01) in prognosis. In SVO-AIS, SVD performed better than regular clinical data, which is the opposite of LAA-AIS. Among all models, eXtreme gradient boosting (XGBoost) method with optimal index (OI) has the best performance to predict excellent outcome in SVO-AIS. [0.91 (0.84-0.97)].Conclusions
Our results revealed that different SVD markers had distinct prognostic weights in AIS patients, and SVD burden alone may accurately predict the SVO-AIS patients' prognosis.
SUBMITTER: Wang X
PROVIDER: S-EPMC10018092 | biostudies-literature | 2023 Apr
REPOSITORIES: biostudies-literature
Publications
Small vessel disease burden predicts functional outcomes in patients with acute ischemic stroke using machine learning.
Wang Xueyang X Lyu Jinhao J Meng Zhihua Z Wu Xiaoyan X Chen Wen W Wang Guohua G Niu Qingliang Q Li Xin X Bian Yitong Y Han Dan D Guo Weiting W Yang Shuai S Bian Xiangbing X Lan Yina Y Wang Liuxian L Duan Qi Q Zhang Tingyang T Duan Caohui C Tian Chenglin C Chen Ling L Lou Xin X
CNS neuroscience & therapeutics 20230117 4
<h4>Aims</h4>Our purpose is to assess the role of cerebral small vessel disease (SVD) in prediction models in patients with different subtypes of acute ischemic stroke (AIS).<h4>Methods</h4>We enrolled 398 small-vessel occlusion (SVO) and 175 large artery atherosclerosis (LAA) AIS patients. Functional outcomes were assessed using the modified Rankin Scale (mRS) at 90 days. MRI was performed to assess white matter hyperintensity (WMH), perivascular space (PVS), lacune, and cerebral microbleed (CM ...[more]
Similar Datasets
Project description:Background: Cerebral small vessel disease (SVD) is generally considered as a cause of stroke, disability, gait disturbances, vascular cognitive impairment, and dementia. The aim of this study was to investigate whether the total SVD burden can be used to predict functional outcome in patients with acute ischemic stroke. Methods: From April 2017 to January 2018, consecutive patients with acute ischemic stroke who underwent baseline MRI scan were evaluated. The functional outcome was assessed using the modified Rankin Scale (mRS) at 90 days and defined as i) excellent outcome (mRS ≤ 1) and ii) good outcome (mRS ≤ 2). Brain MRI was performed and assessed for lacunes, white matter hyperintensities (WMH), and enlarged perivascular spaces (EPVS). The total SVD burden was calculated based on lacunes, WMH, and EPVS and then summed up to generate an ordinal "total SVD burden" (range 0-3). Bivariate logistic regression models were used to identify the association between SVD and functional outcome. Results: A total of 416 patients were included in the final analysis; 44.0, 33.4, 19.2, and 3.4% of the patients had 0, 1, 2, and 3 features of SVD, respectively. In regard to individual SVD feature, lacunes (OR: 0.48, 95% CI: 0.32-0.71; OR: 0.49, 95% CI: 0.31-0.77) and WMH (OR: 0.53, 95% CI: 0.34-0.82; OR: 0.53, 95% CI: 0.33-0.85) were negatively associated with excellent outcome and good outcome. As to the total burden of SVD, three SVD features had strongest negative associations with functional outcomes (excellent outcome, OR: 0.13, 95% CI: 0.03-0.48; good outcome, OR: 0.18, 95% CI: 0.06-0.54). After adjustment for potential confounders, a high SVD burden (3 features, OR: 0.07, 95% CI: 0.01-0.41) and the score of total SVD burden (OR: 0.64, 95% CI: 0.44-0.93) remained negatively associated with excellent outcome. Conclusion: Total SVD burden negatively associated with functional outcome at 3 months in patients with acute ischemic stroke and is superior to individual SVD feature in prediction of functional outcome. MRI-based assessment of total SVD burden is highly valuable in clinical management of stroke victims and could help guide the allocation of resources to improve outcome.
| S-EPMC6691043 | biostudies-literature
Project description:BackgroundCerebral small vessel disease (SVD) is common in the aging population. The study aimed to evaluate the effect of SVD on functional outcomes in patients with acute ischemic stroke (AIS) receiving endovascular treatment (EVT).MethodsFrom a prospective registry, we selected patients with AIS receiving EVT. SVD features, including white matter hyperintensities (WMH), lacunes and brain atrophy, were assessed on MRI and a validated SVD score was calculated to reflect the total SVD burden.ResultsAmong 137 patients included, 106 had none-mild SVD burden and 31 had moderate-severe SVD burden. The moderate-severe SVD burden group showed a significantly higher modified Rankin Scale score at 90 d (median, 4 versus 1 points, adjusted common odds ratio 0.32 [95% CI, 0.14-0.69], P < 0.01) and a significantly smaller improvement of NIHSS at 24 h (median, -3 versus -3 points, adjusted β coefficient 4.02 [95% CI, 0.57-7.48], P = 0.02) and 7 days (median, -4 versus -6 points, adjusted β coefficient 4.71 [95% CI, 1.06-8.36], P = 0.01) than the none-mild group. There was no significant difference in successful recanalization, death within 90 days, symptomatic intracranial hemorrhage within 24 h between two groups (all P > 0.05). Additionally, for each single SVD feature, brain atrophy and WMH, but not lacunes, were associated with the functional outcome.ConclusionModerate-severe SVD burden was associated with poor early and late functional outcomes in patients with AIS receiving EVT. Our results suggest that SVD score may act as a good predictor of outcomes in these patients.
| S-EPMC9234259 | biostudies-literature
Project description:The early detection of large-vessel occlusion (LVO) strokes is increasingly important as these patients are potential candidates for endovascular therapy, the availability of which is limited. Prehospital LVO detection scales mainly contain symptom variables only; however, recent studies revealed that other types of variables could be useful as well. Our aim was to comprehensively assess the predictive ability of several clinical variables for LVO prediction and to develop an optimal combination of them using machine learning tools. We have retrospectively analysed data from a prospectively collected multi-centre stroke registry. Data on 41 variables were collected and divided into four groups (baseline vital parameters/demographic data, medical history, laboratory values, and symptoms). Following the univariate analysis, the LASSO method was used for feature selection to select an optimal combination of variables, and various machine learning methods (random forest (RF), logistic regression (LR), elastic net method (ENM), and simple neural network (SNN)) were applied to optimize the performance of the model. A total of 526 patients were included. Several neurological symptoms were more common and more severe in the group of LVO patients. Atrial fibrillation (AF) was more common, and serum white blood cell (WBC) counts were higher in the LVO group, while systolic blood pressure (SBP) was lower among LVO patients. Using the LASSO method, nine variables were selected for modelling (six symptom variables, AF, chronic heart failure, and WBC count). When applying machine learning methods and 10-fold cross validation using the selected variables, all models proved to have an AUC between 0.736 (RF) and 0.775 (LR), similar to the performance of National Institutes of Health Stroke Scale (AUC: 0.790). Our study highlights that, although certain neurological symptoms have the best ability to predict an LVO, other variables (such as AF and CHF in medical history and white blood cell counts) should also be included in multivariate models to optimize their efficiency.
| S-EPMC8877679 | biostudies-literature
Project description:IntroductionTo assess whether the asymmetrical cortical vessel sign (ACVS) on susceptibility-weighted imaging (SWI) could predict 90-day poor outcomes in anterior circulation acute ischemic stroke (AIS) patients treated with recombinant tissue plasminogen activator (r-tPA).MethodsClinical data of consecutive patients with anterior circulation AIS treated with r-tPA were retrospectively analyzed. Clinical variables included age, sex, vascular risk factors, NIHSS score, onset to treatment time, and initial hematologic and neuroimaging findings. Follow-up was performed 90 days after onset. Poor outcome was defined as a modified Rankin scale (mRS) ≥3 at 90 days.ResultsA total of 145 patients were included, 35 (24.1%) patients presented with ACVS (≥Grade 1) on SWI. Fifty-three (36.6%) patients had a poor outcome at 90 days. ACVS (≥Grade 1) occurred in 21 (39.6%) patients with poor outcome compared with 14 (15.2%) patients with favorable outcome (p = .001). Univariate analysis indicated that age, NIHSS score on admission, previous stroke, hemorrhagic transformation, severe intracranial large artery stenosis or occlusion (SILASO), and ACVS were associated with 90-day poor outcome (p < .05). Since SILASO and ACVS were highly correlated and ACVS had different grades, we used three logistic regression models. Results from the three models showed that ACVS was associated with 90-day poor outcome.ConclusionsIn r-tPA-treated patients with anterior circulation AIS, ACVS might be a helpful neuroimaging predictor for poor outcome at 90 days.
| S-EPMC7375089 | biostudies-literature
Project description:Background and aimsPredicting the prognosis of acute ischemic stroke (AIS) is crucial in a clinical setting for establishing suitable treatment plans. This study aimed to develop and validate a machine learning (ML) model that predicts the functional outcome of AIS patients and provides interpretable insights.MethodsWe included AIS patients from a multicenter stroke registry in this prognostic study. ML-based methods were utilized to predict 3-month functional outcomes, which were categorized as either favorable [modified Rankin Scale (mRS) ≤ 2] or unfavorable (mRS ≥ 3). The SHapley Additive exPlanations (SHAP) method was employed to identify significant features and interpret their contributions to the predictions of the model.ResultsThe dataset comprised a derivation set of 3,687 patients and two external validation sets totaling 250 and 110 patients each. Among them, the number of unfavorable outcomes was 1,123 (30.4%) in the derivation set, and 93 (37.2%) and 32 (29.1%) in external sets A and B, respectively. Among the ML models used, the eXtreme Gradient Boosting model demonstrated the best performance. It achieved an area under the receiver operating characteristic curve (AUC-ROC) of 0.790 (95% CI: 0.775-0.806) on the internal test set and 0.791 (95% CI: 0.733-0.848) and 0.873 (95% CI: 0.798-0.948) on the two external test sets, respectively. The key features for predicting functional outcomes were the initial NIHSS, early neurologic deterioration (END), age, and white blood cell count. The END displayed noticeable interactions with several other features.ConclusionML algorithms demonstrated proficient prediction for the 3-month functional outcome in AIS patients. With the aid of the SHAP method, we can attain an in-depth understanding of how critical features contribute to model predictions and how changes in these features influence such predictions.
| S-EPMC10513028 | biostudies-literature
Project description:Objective: Cerebral small vessel disease (SVD) is associated with increased mortality, disability and cognitive decline, depression in stroke survivors. This study examined the association between SVD burden, defined by a combination of SVD markers, and health-related quality of life (HRQoL) in acute ischemic stroke. Methods: Patients admitted with acute ischemic stroke of any etiology were prospectively screened between January 2010 to December 2014 and enrolled in the study if they met study entry criteria. HRQoL was evaluated with the 12-item Stroke Specific Quality of Life (SSQoL) at 3 months after the onset of acute ischemic stroke. SVD was ascertained by the presence of any of the SVD markers including lacune, white matter hyperintensities (WMH), cerebral microbleeds (CMB) and enlarged perivascular spaces (EPVS) in the basal ganglia or their combinations on brain magnetic resonance imaging (MRI). The presence of each individual marker scored 1 point and was summed up to generate an ordinal "SVD score" (0-4) capturing total SVD burden. Linear regression was used to determine the associations between SVD burden and HRQoL. Results: Of the743 acute ischemic stroke patients that formed he study sample (mean age: 66.3 ± 10.6 years; 41.7% women), 49.3%, 22.5%, 16.0%, 9.2% and 3.1% had SVD scores of 0, 1, 2, 3 and 4, respectively. After adjusting for demographic, clinical and imaging variables, the SVD score was independently associated with lower overall score of SSQoL (B = -1.39, SE = 0.56, p = 0.01), and its domains of mobility (B = -0.41, SE = 0.10, p < 0.001) and vision (B = -0.12, SE = 0.06, p = 0.03). Acute infract volume (B = -1.44, SE = 0.54, p = 0.01), functional independence (B = 5.69, SE = 0.34, p < 0.001) and anxious (B = -1.13, SE = 0.23, p < 0.001) and depressive symptoms (B = -3.41, SE = 0.22, p < 0.001) were also the significant predictors of the overall score of SSQoL. Conclusion: The brain's SVD burden predicts lower HRQoL, predominantly in domains of mobility and vision at 3 months after acute ischemic stroke. The evaluation of SVD burden could facilitate developing individual treatment strategies.
| S-EPMC5693845 | biostudies-literature
Project description:Background and purposeEarly identification of large vessel occlusions (LVO) and timely recanalization are paramount to improved clinical outcomes in acute ischemic stroke. A stroke assessment that maximizes sensitivity and specificity for LVOs is needed to identify these cases and not overburden the health system with unnecessary transfers. Machine learning techniques are being used for predictive modeling in many aspects of stroke care and may have potential in predicting LVO presence and mechanical thrombectomy (MT) candidacy.MethodsIschemic stroke patients treated at Loyola University Medical Center from July 2018 to June 2019 (N = 286) were included. Thirty-five clinical and demographic variables were analyzed using machine learning algorithms, including logistic regression, extreme gradient boosting, random forest (RF), and decision trees to build models predictive of LVO presence and MT candidacy by area of the curve (AUC) analysis. The best performing model was compared with prior stroke scales.ResultsWhen using all 35 variables, RF best predicted LVO presence (AUC = 0.907 ± 0.856-0.957) while logistic regression best predicted MT candidacy (AUC = 0.930 ± 0.886-0.974). When compact models were evaluated, a 10-feature RF model best predicted LVO (AUC = 0.841 ± 0.778-0.904) and an 8-feature RF model best predicted MT candidacy (AUC = 0.862 ± 0.782-0.942). The compact RF models had sensitivity, specificity, negative predictive value and positive predictive value of 0.81, 0.87, 0.92, 0.72 for LVO and 0.87, 0.97, 0.97, 0.86 for MT, respectively. The 10-feature RF model was superior at predicting LVO to all previous stroke scales (AUC 0.944 vs 0.759-0.878) and the 8-feature RF model was superior at predicting MT (AUC 0.970 vs 0.746-0.834).ConclusionRandom forest machine learning models utilizing clinical and demographic variables predicts LVO presence and MT candidacy with a high degree of accuracy in an ischemic stroke cohort. Further validation of this strategy for triage of stroke patients requires prospective and external validation.
| S-EPMC8404508 | biostudies-literature
Project description:Background and objectiveAutomated machine learning or autoML has been widely deployed in various industries. However, their adoption in healthcare, especially in clinical settings is constrained due to a lack of clear understanding and explainability. The aim of this study is to utilize autoML for the prediction of functional outcomes in patients who underwent mechanical thrombectomy and compare it with traditional ML models with a focus on the explainability of the trained models.MethodsA total of 156 patients of acute ischemic stroke with Large Vessel Occlusion (LVO) who underwent mechanical thrombectomy within 24 h of stroke onset were included in the study. A total of 34 treatment variables including clinical, demographic, imaging, and procedure-related data were extracted. Various conventional machine learning models such as decision tree classifier, logistic regression, random forest, kNN, and SVM as well as various autoML models such as AutoGluon, MLJAR, Auto-Sklearn, TPOT, and H2O were used to predict the modified Rankin score (mRS) at the time of patient discharge and 3 months follow-up. The sensitivity, specificity, accuracy, and AUC for traditional ML and autoML models were compared.ResultsThe autoML models outperformed the traditional ML models. For the prediction of mRS at discharge, the highest testing accuracy obtained by traditional ML models for the decision tree classifier was 74.11%, whereas for autoML which was obtained through AutoGluon, it showed an accuracy of 88.23%. Similarly, for mRS at 3 months, the highest testing accuracy of traditional ML was that of the SVM classifier at 76.5%, whereas that of autoML was 85.18% obtained through MLJAR. The 24-h ASPECTS score was the most important predictor for mRS at discharge whereas for prediction of mRS at 3 months, the most important factor was mRS at discharge.ConclusionAutomated machine learning models based on multiple treatment variables can predict the functional outcome in patients more accurately than traditional ML models. The ease of clinical coding and deployment can assist clinicians in the critical decision-making process. We have developed a demo application which can be accessed at https://mrs-score-calculator.onrender.com/.
| S-EPMC10569475 | biostudies-literature
Project description:ObjectivesWe aim to investigate whether cerebral small vessel disease (cSVD) imaging markers correlate with deep medullary vein (DMV) damage in small vessel occlusion acute ischemic stroke (SVO-AIS) patients.MethodsThe DMV was divided into six segments according to the regional anatomy. The total DMV score (0-18) was calculated based on segmental continuity and visibility. The damage of DMV was grouped according to the quartiles of the total DMV score. Neuroimaging biomarkers of cSVD including white matter hyperintensity (WMH), cerebral microbleed (CMB), perivascular space (PVS), and lacune were identified. The cSVD score were further analyzed.ResultsWe included 229 SVO-AIS patients, the mean age was 63.7 ± 23.1 years, the median NIHSS score was 3 (IQR, 2-6). In the severe DMV burden group (the 4th quartile), the NIHSS score grade (6 (3-9)) was significantly higher than other groups (p < 0.01). The grade scores for basal ganglia PVS (BG-PVS) were positively correlated with the degree of DMV (R = 0.67, p < 0.01), rather than centrum semivole PVS (CS-PVS) (R = 0.17, p = 0.1). In multivariate analysis, high CMB burden (adjusted odds ratio [aOR], 25.38; 95% confidence interval [CI], 1.87-345.23) was associated with severe DMV scores. In addition, BG-PVS was related to severe DMV burden in a dose-dependent manner: when BG-PVS score was 3 and 4, the aORs of severe DMV burden were 18.5 and 12.19, respectively.ConclusionThe DMV impairment was associated with the severity of cSVD, which suggests that DMV burden may be used for risk stratification in SVO-AIS patients.Clinical relevance statementThe DMV damage score, based on the association between small vessel disease and the deep medullary veins impairment, is a potential new imaging biomarker for the prognosis of small vessel occlusion acute ischemic stroke, with clinical management implications.Key points• The damage to the deep medullary vein may be one mechanism of cerebral small vessel disease. • Severe burden of the basal ganglia perivascular space and cerebral microbleed is closely associated with significant impairment to the deep medullary vein. • The deep medullary vein damage score may reflect a risk of added vascular damage in small vessel occlusion acute ischemic stroke patients.
| S-EPMC11364723 | biostudies-literature
Project description:Background: Cerebral small vessel disease (SVD) is prevalent in the population, especially among elderly individuals. Substantial uncertainties remain about the clinical relevance of SVD with outcomes of mechanical thrombectomy (MT) in acute ischemic stroke (AIS). Objectives: This systematic review and meta-analysis was performed to evaluate the association between SVD and clinical outcomes in patients with AIS undergoing MT. Methods: We systematically searched the Medline, Embase, and Cochrane databases for relevant clinical studies. The exposure of SVD mainly included leukoaraiosis, cerebral microbleeds (CMBs), and lacunes. The pooled OR was used to calculate the association between each subtype of SVD and outcomes of MT. The primary outcome was poor functional outcome, which was defined as a modified Rankin Scale score (mRS) ≥3 at 90 days after MT. The secondary outcomes included mortality at 90 days, in-hospital mortality, intracranial hemorrhage (ICH) and symptomatic intracranial hemorrhage (sICH), successful recanalization and futile recanalization (FR), early neurological improvement, and early neurological deterioration (END) after MT. Results: Overall, 20 studies with 5,189 patients with AIS undergoing MT were included. High leukoaraiosis burden (HLB) at baseline was associated with increased risks of poor functional outcome at 90 days (OR 2.70, 95% CI 2.01-3.63; p < 0.001; 10 studies; n = 2,004), in-hospital mortality (OR 4.06, 95% CI 1.48-11.13; p = 0.006; 2 studies; n = 314), FR (OR 5.00, 95% CI 2.86-8.73; p < 0.001; 3 studies; n = 493), and END (OR 2.65, 95% CI 1.09-6.45; 1 study; n = 273) after MT. HLB (VSS 3-4 or FS ≥ 2) at baseline was not associated with mortality at 90 days, ICH, or sICH after MT. CMBs at baseline were found to be associated with increased risks of poor functional outcome at 90 days (OR 1.84, 95% CI 1.17-2.90; p = 0.008; 2 studies; n = 1,924) after MT. We found no association between the presence of lacunes and poor functional outcome at 90 days after MT. Conclusions: In patients with AIS undergoing MT, HLB and CMBs were associated with increased risks of unfavorable outcomes after MT.
| S-EPMC8058474 | biostudies-literature