Machine Learning-Based Prediction of COVID-19 Severity and Progression to Critical Illness Using CT Imaging and Clinical Data

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.

Machine Learning-Based Prediction of COVID-19 Severity and Progression to Critical Illness Using CT Imaging and Clinical Data

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.

A logistic regression model for prediction of glioma grading based on radiomics / 中南大学学报(医学版)

OBJECTIVES@#Glioma is the most common intracranial primary tumor in central nervous system. Glioma grading possesses important guiding significance for the selection of clinical treatment and follow-up plan, and the assessment of prognosis. This study aims to explore the feasibility of logistic regression model based on radiomics to predict glioma grading.@*METHODS@#Retrospective analysis was performed on 146 glioma patients with confirmed pathological diagnosis from January, 2012 to December, 2018. A total of 41 radiomics features were extracted from contrast-enhanced T@*RESULTS@#A total of 5 imaging features selected by LASSO were used to establish a logistic regression model for predicting glioma grading. The model showed good discrimination with AUC value of 0.919. Hosmer-Lemeshow test showed no significant difference between the calibration curve and the ideal curve (@*CONCLUSIONS@#The logistic regression model using radiomics exhibits a relatively high accuracy for predicting glioma grading, which may serve as a complementary tool for preoperative prediction of giloma grading.

An artificial neural network model for glioma grading using image information / 中南大学学报(医学版)

To explore the feasibility and efficacy of artificial neural network for differentiating high-grade glioma and low-grade glioma using image information.
 Methods: A total of 130 glioma patients with confirmed pathological diagnosis were selected retrospectively from 2012 to 2017. Forty one imaging features were extracted from each subjects based on 2-dimension magnetic resonance T1 weighted imaging with contrast-enhancement. An artificial neural network model was created and optimized according to the performance of feature selection. The training dataset was randomly selected half of the whole dataset, and the other half dataset was used to verify the performance of the neural network for glioma grading. The training-verification process was repeated for 100 times and the performance was averaged.
 Results: A total of 5 imaging features were selected as the ultimate input features for the neural network. The mean accuracy of the neural network for glioma grading was 90.32%, with a mean sensitivity at 87.86% and a mean specificity at 92.49%. The area under the curve of receiver operating characteristic curve was 0.9486.
 Conclusion: As a technique of artificial intelligence, neural network can reach a relatively high accuracy for the grading of glioma and provide a non-invasive and promising computer-aided diagnostic process for the pre-operative grading of glioma.