RESUMO
Objective@#To develop a machine learning (ML) pipeline based on radiomics to predict Coronavirus Disease 2019 (COVID-19) severity and the future deterioration to critical illness using CT and clinical variables. @*Materials and Methods@#Clinical data were collected from 981 patients from a multi-institutional international cohort with real-time polymerase chain reaction-confirmed COVID-19. Radiomics features were extracted from chest CT of the patients. The data of the cohort were randomly divided into training, validation, and test sets using a 7:1:2 ratio. A ML pipeline consisting of a model to predict severity and time-to-event model to predict progression to critical illness were trained on radiomics features and clinical variables. The receiver operating characteristic area under the curve (ROC-AUC), concordance index (C-index), and time-dependent ROC-AUC were calculated to determine model performance, which was compared with consensus CT severity scores obtained by visual interpretation by radiologists. @*Results@#Among 981 patients with confirmed COVID-19, 274 patients developed critical illness. Radiomics features and clinical variables resulted in the best performance for the prediction of disease severity with a highest test ROC-AUC of 0.76 compared with 0.70 (0.76 vs. 0.70, p = 0.023) for visual CT severity score and clinical variables. The progression prediction model achieved a test C-index of 0.868 when it was based on the combination of CT radiomics and clinical variables compared with 0.767 when based on CT radiomics features alone (p < 0.001), 0.847 when based on clinical variables alone (p = 0.110), and 0.860 when based on the combination of visual CT severity scores and clinical variables (p = 0.549). Furthermore, the model based on the combination of CT radiomics and clinical variables achieved time-dependent ROC-AUCs of 0.897, 0.933, and 0.927 for the prediction of progression risks at 3, 5 and 7 days, respectively. @*Conclusion@#CT radiomics features combined with clinical variables were predictive of COVID-19 severity and progression to critical illness with fairly high accuracy.
RESUMO
Objective@#To develop a machine learning (ML) pipeline based on radiomics to predict Coronavirus Disease 2019 (COVID-19) severity and the future deterioration to critical illness using CT and clinical variables. @*Materials and Methods@#Clinical data were collected from 981 patients from a multi-institutional international cohort with real-time polymerase chain reaction-confirmed COVID-19. Radiomics features were extracted from chest CT of the patients. The data of the cohort were randomly divided into training, validation, and test sets using a 7:1:2 ratio. A ML pipeline consisting of a model to predict severity and time-to-event model to predict progression to critical illness were trained on radiomics features and clinical variables. The receiver operating characteristic area under the curve (ROC-AUC), concordance index (C-index), and time-dependent ROC-AUC were calculated to determine model performance, which was compared with consensus CT severity scores obtained by visual interpretation by radiologists. @*Results@#Among 981 patients with confirmed COVID-19, 274 patients developed critical illness. Radiomics features and clinical variables resulted in the best performance for the prediction of disease severity with a highest test ROC-AUC of 0.76 compared with 0.70 (0.76 vs. 0.70, p = 0.023) for visual CT severity score and clinical variables. The progression prediction model achieved a test C-index of 0.868 when it was based on the combination of CT radiomics and clinical variables compared with 0.767 when based on CT radiomics features alone (p < 0.001), 0.847 when based on clinical variables alone (p = 0.110), and 0.860 when based on the combination of visual CT severity scores and clinical variables (p = 0.549). Furthermore, the model based on the combination of CT radiomics and clinical variables achieved time-dependent ROC-AUCs of 0.897, 0.933, and 0.927 for the prediction of progression risks at 3, 5 and 7 days, respectively. @*Conclusion@#CT radiomics features combined with clinical variables were predictive of COVID-19 severity and progression to critical illness with fairly high accuracy.
RESUMO
<p><b>Background</b>Our previous studies have shown that Tongxinluo (TXL), a compound Chinese medicine, can decrease myocardial ischemia-reperfusion injury, protect capillary endothelium function, and lessen cardiac ventricle reconstitution in animal models. The aim of this study was to illuminate whether TXL can improve hypercholesterolemia-impaired heart function by protecting artery endothelial function and increasing microvascular density (MVD) in heart. Furthermore, we will explore the underlying molecular mechanism of TXL cardiovascular protection.</p><p><b>Methods</b>After intragastric administration of TXL (0.1 ml/10 g body weight) to C57BL/6J wild-type mice (n = 8) and ApoE-/- mice (n = 8), total cholesterol, high-density lipoprotein-cholesterol, very-low-density lipoprotein (VLDL)-cholesterol, triglyceride, and blood glucose levels in serum were measured. The parameters of heart rate (HR), left ventricular diastolic end diameter, and left ventricular systolic end diameter were harvested by ultrasonic cardiogram. The left ventricular ejection fraction, stroke volume, cardiac output, and left ventricular fractional shortening were calculated. Meanwhile, aorta peak systolic flow velocity (PSV), end diastolic flow velocity, and mean flow velocity (MFV) were measured. The pulsatility index (PI) and resistant index were calculated in order to evaluate the vascular elasticity and resistance. The endothelium-dependent vasodilatation was evaluated by relaxation of aortic rings in response to acetylcholine. Western blotting and real-time quantitative reverse transcription polymerase chain reaction were performed for protein and gene analyses of vascular endothelial growth factor (VEGF). Immunohistochemical detection was performed for myocardial CD34 expression. Data in this study were compared by one-way analysis of variance between groups. A value of P < 0.05 was considered statistically significant.</p><p><b>Results</b>Although there was no significant decrease of cholesterol level (F = 2.300, P = 0.240), TXL inhibited the level of triglyceride and VLDL (F = 9.209, P = 0.024 and F = 9.786, P = 0.020, respectively) in ApoE-/- mice. TXL improved heart function of ApoE-/- mice owing to the elevations of LVEF, SV, CO, and LVFS (all P < 0.05). TXL enhanced aortic PSV and MFV (F = 10.774, P = 0.024 and F = 11.354, P = 0.020, respectively) and reduced PI of ApoE-/- mice (1.41 ± 0.17 vs. 1.60 ± 0.17; P = 0.037). After incubation with 10 μmol/L acetylcholine, the ApoE-/- mice treated with TXL aortic segment relaxed by 44% ± 3%, significantly higher than control group mice (F = 9.280, P = 0.040). TXL also restrain the angiogenesis of ApoE-/- mice aorta (F = 21.223, P = 0.010). Compared with C57BL/6J mice, the MVD was decreased in heart tissue of untreated ApoE-/- mice (54.0 ± 3.0/mmvs. 75.0 ± 2.0/mm; F = 16.054, P = 0.010). However, TXL could significantly enhance MVD (65.0 ± 5.0/mmvs. 54.0 ± 3.0/mm; F = 11.929, P = 0.020) in treated ApoE-/- mice. In addition, TXL obviously increased the expression of VEGF protein determined by Western blot (F = 20.247, P = 0.004).</p><p><b>Conclusions</b>TXL obviously improves the ApoE-/- mouse heart function from different pathways, including reduces blood fat to lessen atherosclerosis; enhances aortic impulsivity, blood supply capacity, and vessel elasticity; improves endothelium-dependent vasodilatation; restraines angiogenesis of aorta-contained plaque; and enhances MVD of heart. The molecular mechanism of MVD enhancement maybe relate with increased VEGF expression.</p>