ABSTRACT
Purpose: To investigate the association between clinic-radiological features and glioma-associated epilepsy (GAE), we developed and validated a radiomics nomogram for predicting GAE in WHO grade II~IV gliomas. Methods: This retrospective study consecutively enrolled 380 adult patients with glioma (266 in the training cohort and 114 in the testing cohort). Regions of interest, including the entire tumor and peritumoral edema, were drawn manually. The semantic radiological characteristics were assessed by a radiologist with 15 years of experience in neuro-oncology. A clinic-radiological model, radiomic signature, and a combined model were built for predicting GAE. The combined model was visualized as a radiomics nomogram. The AUC was used to evaluate model classification performance, and the McNemar test and Delong test were used to compare the performance among the models. Statistical analysis was performed using SPSS software, and p < 0.05 was regarded as statistically significant. Results: The combined model reached the highest AUC with the testing cohort (training cohort, 0.911 [95% CI, 0.878-0.942]; testing cohort, 0.866 [95% CI, 0.790-0.929]). The McNemar test revealed that the differences among the accuracies of the clinic-radiological model, radiomic signature, and combined model in predicting GAE in the testing cohorts (p > 0.05) were not significantly different. The DeLong tests showed that the difference between the performance of the radiomic signature and the combined model was significant (p < 0.05). Conclusion: The radiomics nomogram predicted seizures in patients with glioma non-invasively, simply, and practically. Compared with the radiomics models, comprehensive clinic-radiological imaging signs observed by the naked eye have non-discriminatory performance in predicting GAE.
ABSTRACT
BackgroundThe evolving pandemic of COVID-19 is arousing alarm to public health. According to epidemiological and observational studies, coagulopathy was frequently seen in severe COVID-19 patients, yet the causality from specific coagulation factors to COVID-19 severity and the underlying mechanism remain elusive. MethodsFirst, we leveraged Mendelian randomization (MR) analyses to assess causal relationship between 12 coagulation factors and severe COVID-19 illness based on two genome-wide association study (GWAS) results of COVID-19 severity. Second, we curated clinical evidence supporting causal associations between COVID-19 severity and particular coagulation factors which showed significant results in MR analyses. Third, we validated our results in an independent cohort from UK Biobank (UKBB) using polygenic risk score (PRS) analysis and logistic regression model. For all MR analyses, GWAS summary-level data were used to ascertain genetic effects on exposures against disease risk. ResultsWe revealed that genetic predisposition to the antigen levels of von Willebrand factor (VWF) and the activity levels of its cleaving protease ADAMTS13 were causally associated with COVID-19 severity, wherein elevated VWF antigen level (P = 0.005, odds ratio (OR) = 1.35, 95% confidence interval (CI): 1.09-1.68 in the Severe COVID-19 GWAS Group cohort; P = 0.039, OR = 1.21, 95% CI: 1.01-1.46 in the COVID-19 Host Genetics Initiative cohort) and lowered ADAMTS13 activity (P = 0.025, OR = 0.69, 95% CI: 0.50-0.96 in the Severe COVID-19 GWAS Group cohort) lead to increased risk of severe COVID-19 illness. No significant causal association of tPA, PAI-1, D-dimer, FVII, PT, FVIII, FXI, aPTT, FX or ETP with COVID-19 severity was observed. In addition, as an independent factor, VWF PRS explains a 31% higher risk of severe COVID-19 illness in the UKBB cohort (P = 0.047, OR per SD increase = 1.31, 95% CI: 1.00-1.71). In combination with age, sex, BMI and several pre-existing disease statues, our model can predict severity risks with an AUC of 0.70. ConclusionTogether with the supporting evidence of recent retrospective cohort studies and independent validation based on UKBB data, our results suggest that the associations between coagulation factors VWF/ADAMTS13 and COVID-19 severity are essentially causal, which illuminates one of possible mechanisms underlying COVID-19 severity. This study also highlights the importance of dynamically monitoring the plasma levels of VWF/ADAMTS13 after SARS-CoV-2 infection, and facilitates the development of treatment strategy for controlling COVID-19 severity and associated thrombotic complication.
