An Interpretable Model-Based Prediction of Severity and Crucial Factors in Patients with COVID-19

Abstract

This study established an interpretable machine learning model to predict the severity of coronavirus disease 2019 (COVID-19) and output the most crucial deterioration factors. Clinical information, laboratory tests, and chest computed tomography (CT) scans at admission were collected. Two experienced radiologists reviewed the scans for the patterns, distribution, and CT scores of lung abnormalities. Six machine learning models were established to predict the severity of COVID-19. After parameter tuning and performance comparison, the optimal model was explained using Shapley Additive explanations to output the crucial factors. This study enrolled and classified 198 patients into mild (n = 162; 46.93 ± 14.49 years old) and severe (n = 36; 60.97 ± 15.91 years old) groups. The severe group had a higher temperature (37.42 ± 0.99°C vs. 36.75 ± 0.66°C), CT score at admission, neutrophil count, and neutrophil-to-lymphocyte ratio than the mild group. The XGBoost model ranked first among all models, with an AUC, sensitivity, and specificity of 0.924, 90.91%, and 97.96%, respectively. The early stage of chest CT, total CT score of the percentage of lung involvement, and age were the top three contributors to the prediction of the deterioration of XGBoost. A higher total score on chest CT had a more significant impact on the prediction. In conclusion, the XGBoost model to predict the severity of COVID-19 achieved excellent performance and output the essential factors in the deterioration process, which may help with early clinical intervention, improve prognosis, and reduce mortality.

Figure 1

Flow diagram of patient enrollment.

Figure 2

Illustration of the modeling framework.

Figure 3

The contribution of various features to the prediction model. The features are listed in descending order according to their contribution to the prediction of a patient becoming severe or critically ill. (a) The importance of features measured by the mean absolute Shapley values according to their contribution. (b) The combination of feature importance and feature effects. The color shows the value of the features from high to low. The horizontal location shows whether the effect of that value caused a higher or lower prediction. Each point is a Shapley value for a feature and an instance.

Figure 4

With the help of an interpretable module, we can know how the machine learning model concludes each individual. A 69-year-old patient was predicted to be deteriorating with a possibility of 0.978 (97.8%). The days from symptom onset to hospital admission was seven days, and the temperature at admission was 37.4°C. The neutrophil was 11 × 10⁹/L, with a neutrophil ratio of 92.5% and an NLR of 17.46.