Severity Assessment of COVID-19 based on Clinical and Imaging Data

Abstract

Objectives This study aims to develop a machine learning approach for automated severity assessment of COVID-19 patients based on clinical and imaging data. Materials and Methods Clinical data, including demographics, signs, symptoms, comorbidities and blood test results and chest CT scans of 346 patients from two hospitals in the Hubei province, China, were used to develop machine learning models for automated severity assessment of diagnosed COVID-19 cases. We compared the predictive power of clinical and imaging data by testing multiple machine learning models, and further explored the use of four oversampling methods to address the imbalance distribution issue. Features with the highest predictive power were identified using the SHAP framework. Results Targeting differentiation between mild and severe cases, logistic regression models achieved the best performance on clinical features (AUC:0.848, sensitivity:0.455, specificity:0.906), imaging features (AUC:0.926, sensitivity:0.818, specificity:0.901) and the combined features (AUC:0.950, sensitivity:0.764, specificity:0.919). The SMOTE oversampling method further improved the performance of the combined features to AUC of 0.960 (sensitivity:0.845, specificity:0.929). Discussion Imaging features had the strongest impact on the model output, while a combination of clinical and imaging features yielded the best performance overall. The identified predictive features were consistent with findings from previous studies. Oversampling yielded mixed results, although it achieved the best performance in our study. Conclusions This study indicates that clinical and imaging features can be used for automated severity assessment of COVID-19 patients and have the potential to assist with triaging COVID-19 patients and prioritizing care for patients at higher risk of severe cases. [Manuscript last updated on 31 July, 2020]

Development and Validation of an Explainable Machine Learning Model for Major Complications After Cytoreductive Surgery

“…To our knowledge, a few studies have adopted SHAP values to explain their models, but none have included SHAP plots to explain the model both on a local and a global level. 20 , 21 , 22 , 23 A 2020 study 20 on predicting acute kidney injury after cardiac surgery used a SHAP summary plot to explain the associations of the top 20 predictors with the outcome on the global level and the nonlinear association of several predictors. Fong et al 21 used a SHAP dependence plot to explain a 2-way interaction from a model to predict hospital mortality.…”

“…Fong et al 21 used a SHAP dependence plot to explain a 2-way interaction from a model to predict hospital mortality. A third study 22 also used a SHAP summary plot to explore the top contributing factors that predicted illness severity among COVID-19 patients.…”

“…As such, this study is one of the most comprehensive clinical applications using the SHAP values. To our knowledge, a few studies have adopted SHAP values to explain their models, but none have included SHAP plots to explain the model both on a local and a global level . A 2020 study on predicting acute kidney injury after cardiac surgery used a SHAP summary plot to explain the associations of the top 20 predictors with the outcome on the global level and the nonlinear association of several predictors.…”

Impact of Spherical Coordinates Transformation Pre-processing in Deep Convolution Neural Networks for Brain Tumor Segmentation and Survival Prediction

“…There is a wealth of information in the brain tumors including shape, texture, location, extent and distribution of involvement of the abnormality, that can be extracted by the lesion encoder. While it has been demonstrated in COVID-19 progression prediction [9] and severity assessment [15], here we demonstrated a new application of LE in patient OS prediction. It may have strong potential in a wide range of other clinical and research applications, e.g., brain tumor pseudo-progression detection [16] and ophthalmic disease screening [17].…”

The application of artificial intelligence and data integration in COVID-19 studies: a scoping review

“…In fact, many of the medical imaging studies that integrated heterogenous data have shown that data integration led to AI models with better performance compared to models built with imaging data alone. 53–55 , 62 , 65 , 69 , 76–78 Furthermore, although some data are difficult to get due to privacy issues or simply being unavailable, there are still a range of public data on risk factors that could be easily obtained for modeling. Many studies we reviewed leveraged the “free” data sources, such as the huge amounts of environmental data from the National Oceanic and Atmospheric Administration or the socioeconomic data from the Census Bureau.…”