Prediction and Feature Importance Analysis for Severity of COVID-19 in South Korea Using Artificial Intelligence: Model Development and Validation

Abstract

Background The number of deaths from COVID-19 continues to surge worldwide. In particular, if a patient’s condition is sufficiently severe to require invasive ventilation, it is more likely to lead to death than to recovery. Objective The goal of our study was to analyze the factors related to COVID-19 severity in patients and to develop an artificial intelligence (AI) model to predict the severity of COVID-19 at an early stage. Methods We developed an AI model that predicts severity based on data from 5601 COVID-19 patients from all national and regional hospitals across South Korea as of April 2020. The clinical severity of COVID-19 was divided into two categories: low and high severity. The condition of patients in the low-severity group corresponded to no limit of activity, oxygen support with nasal prong or facial mask, and noninvasive ventilation. The condition of patients in the high-severity group corresponded to invasive ventilation, multi-organ failure with extracorporeal membrane oxygenation required, and death. For the AI model input, we used 37 variables from the medical records, including basic patient information, a physical index, initial examination findings, clinical findings, comorbid diseases, and general blood test results at an early stage. Feature importance analysis was performed with AdaBoost, random forest, and eXtreme Gradient Boosting (XGBoost); the AI model for predicting COVID-19 severity among patients was developed with a 5-layer deep neural network (DNN) with the 20 most important features, which were selected based on ranked feature importance analysis of 37 features from the comprehensive data set. The selection procedure was performed using sensitivity, specificity, accuracy, balanced accuracy, and area under the curve (AUC). Results We found that age was the most important factor for predicting disease severity, followed by lymphocyte level, platelet count, and shortness of breath or dyspnea. Our proposed 5-layer DNN with the 20 most important features provided high sensitivity (90.2%), specificity (90.4%), accuracy (90.4%), balanced accuracy (90.3%), and AUC (0.96). Conclusions Our proposed AI model with the selected features was able to predict the severity of COVID-19 accurately. We also made a web application so that anyone can access the model. We believe that sharing the AI model with the public will be helpful in validating and improving its performance.

Machine Learning–Based Prediction of COVID-19 Mortality With Limited Attributes to Expedite Patient Prognosis and Triage: Retrospective Observational Study

“…These results strongly suggest that dimensionality reduction can be beneficial to model performance or can provide reduced dependence on large feature sets at minimal cost to performance. We also note that all models tested on either the 25-feature or 7-feature data sets performed roughly in line with or not much worse than existing studies drawing on a plethora of additional blood markers and vitals [ 12 - 15 ].…”

“…RenderX tested on either the 25-feature or 7-feature data sets performed roughly in line with or not much worse than existing studies drawing on a plethora of additional blood markers and vitals [12][13][14][15].…”

“…Several such models have now entered the academic literature, but with varying degrees of usability. Many suffer from mild to severe flaws, such as training on alternative diseases such as pneumonia as a proxy for COVID-19 [11], depending on less immediately available data from blood tests and other monitoring equipment [12][13][14][15], and unrepresentative population samples-often older skewing [16] or monolocalized [17]; these flaws result either in low performance or, more worryingly, in excessively optimistic expectations of performance that overfit to a certain facet of the population.…”

Uncovering Clinical Risk Factors and Predicting Severe COVID-19 Cases Using UK Biobank Data: Machine Learning Approach

“…A variety of methods including XGboost, generalized additive model, and LASSO were employed. Chung et al [ 7 ] employed deep neural networks to predict the severity of COVID-19 infection based on basic patient information, comorbidities, vital signs, clinical symptoms, and complete blood count. Wynants et al [ 8 ] performed a systematic review of COVID-19–related prediction models up to July 1, 2020, covering 169 studies describing 232 prediction models.…”

Gender Bias in Artificial Intelligence: Severity Prediction at an Early Stage of COVID-19

“…For the investigation, we extended our previous AI study, which is to predict patient severity in the early stage of coronavirus disease (COVID-19) (Chung et al, 2021).…”