Background and Purpose— Malignant brain edema after ischemic stroke has high mortality but limited treatment. Therefore, early prediction is important, and we systematically reviewed predictors and predictive models to identify reliable markers for the development of malignant edema. Methods— We searched Medline and Embase from inception to March 2018 and included studies assessing predictors or predictive models for malignant brain edema after ischemic stroke. Study quality was assessed by a 17-item tool. Odds ratios, mean differences, or standardized mean differences were pooled in random-effects modeling. Predictive models were descriptively analyzed. Results— We included 38 studies (3278 patients) with 24 clinical factors, 7 domains of imaging markers, 13 serum biomarkers, and 4 models. Generally, the included studies were small and showed potential publication bias. Malignant edema was associated with younger age (n=2075; mean difference, −4.42; 95% CI, −6.63 to −2.22), higher admission National Institutes of Health Stroke Scale scores (n=807, median 17–20 versus 5.5–15), and parenchymal hypoattenuation >50% of the middle cerebral artery territory on initial computed tomography (n=420; odds ratio, 5.33; 95% CI, 2.93–9.68). Revascularization (n=1600, odds ratio, 0.37; 95% CI, 0.24–0.57) were associated with a lower risk for malignant edema. Four predictive models all showed an overall C statistic >0.70, with a risk of overfitting. Conclusions— Younger age, higher National Institutes of Health Stroke Scale, and larger parenchymal hypoattenuation on computed tomography are reliable early predictors for malignant edema. Revascularization reduces the risk of malignant edema. Future studies with robust design are needed to explore optimal cutoff age and National Institutes of Health Stroke Scale scores and to validate and improve existing models.
Medical datasets are usually imbalanced, where negative cases severely outnumber p osit iv e cases. Therefore, it is essential to deal with this data skew problem when training machine learning algorithms. This study uses two representative lung cancer datasets, PLCO an d NLST, wit h imb alan ce ratios (the proportion of samples in the majority class to those in the minority class) of 24.7 and 25.0, respectively, to predict lung cancer incidence. This research uses the performance o f 23 clas s imb alan ce methods (resampling and hybrid systems) with three classical classifiers (logistic regression, random forest, and LinearSVC) to identify the best imbalance techniques suitable for medical datasets. Resampling includes ten under-sampling methods (RUS, Etc.), seven over-sampling methods (SMOTE, Etc.), an d t wo integrated sampling methods (SMOTEENN, SMOTE-Tomek). Hybrid systems include (Balanced Bagging, Etc.). The results show that class imbalance learning can improve the classification abilit y o f t h e mo d el. Compared with other imbalanced techniques, under-sampling techniques have the highest standard deviation (SD), and over-sampling techniques have the lowest SD. Over-sampling is a stable met h od, an d the AUC in the model is generally higher than in other ways. Using ROS, the random forest p erforms t h e best predictive ability and is more suitable for the lung cancer datasets used in this study.
Objectives: Cystatin C (Cys C) and high-density lipoprotein (HDL) play critical roles in neurodegenerative diseases, such as dementia, Alzheimer’s disease (AD) and vascular dementia (VaD). However, whether they can be used as reliable biomarkers to distinguish patients with dementia from healthy subjects and to determine disease severity remain largely unknown.Methods: We conducted a cross-sectional study to determine plasma Cys C and HDL levels of 88 patients with dementia (43 AD patients, 45 VaD patients) and 45 healthy age-matched controls. The severity of dementia was determined based on the Schwab and England Activities of Daily Living (ADL) Scale, the Mini-mental State Examination (MMSE), the Global Deterioration Scale (GDS), the Lawton Instrumental ADL (IADL) Scale, and the Hachinski Ischemia Scale (Hachinski). Receiver operating characteristic (ROC) curves were calculated to determine the diagnostic accuracy of Cys C and HDL levels in distinguishing patients with dementia from healthy subjects.Results: We found that plasma Cys C levels were higher, but HDL levels were lower in AD and VaD patients respectively, compared to healthy control subjects. Yet, Cys C levels were highest among patients with VaD. Interestingly, plasma Cys C levels were significantly correlated with IADL Scale scores. In addition, the ROC curves for Cys C (area under the curve, AUC 0.816 for AD, AUC 0.841 for VaD) and HDL (AUC 0.800 for AD, AUC 0.731 for VaD) exhibited potential diagnostic value in distinguishing AD/VaD patients from healthy subjects. While the ROC curve for the combination of Cys C and HDL (AUC 0.873 for AD, AUC 0.897 for VaD) showed higher diagnostic accuracy in distinguishing AD/VaD patients from healthy subjects than the separate curves for each parameter.Conclusions: Our findings suggest that the inflammatory mediators Cys C and HDL may play important roles in the pathogenesis of dementia, and plasma Cys C and HDL levels may be useful screening tools for differentiating AD/VaD patients from healthy subjects.HighlightsPlasma Cys C levels were higher in patients with AD/VaD than in healthy subjects.Plasma HDL levels were lower in patients with AD/VaD than in healthy subjects.Plasma Cys C levels were significantly correlated with dementia.The ROC curve for the combination of Cys C and HDL showed potential diagnostic value in distinguishing AD/VaD from healthy subjects.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.