感染症と治療ジャーナル

抽象的な

Interpretable Machine-Learning Model for Prediction of Convalescent COVID-19 Patients with Pulmonary Diffusing Capacity Impairment

Fu-qiang MA, Cong HE, Cong HE, Cong HE, Hao-ran Yang, Zuo-wei HU, Ji-xian Zhang, Cun-yu FAN, Bo XU

Introduction: The COVID-19 patients in the convalescent stage noticeably have pulmonary diffusing capacity impairment (PDCI). The pulmonary diffusing capacity is an important indicator of the COVID-19 survivors’ prognosis of pulmonary function, but the current studies focusing on prediction of the pulmonary diffusing capacity of these people are limited. The aim of this study was to develop and validate a machine learning (ML) model for predicting PDCI in the COVID-19 patients using routinely available clinical data, thus assisting the clinical diagnosis.

Methods: The data used in this study were collected from a follow-up study from August to September 2021 of 221 hospitalized COVID-19 survivors 18 months after discharge from Wuhan, including the demographic characteristics and clinical examination. The data were randomly split into a training (80%) data set and a validation (20%) data set. Six popular machine learning models were developed to predict the pulmonary diffusing capacity of COVID-19 patients in the recovery stage. The performance indicators of the model included area under the curve (AUC), Accuracy, Recall, Precision and F1. The model with the optimum performance was defined as the optimal model, which was further used in the interpretability analysis. The MAHAKIL method was utilized to balance the data and optimize the balance of sample distribution, while the RFECV method for feature selection was utilized to select combined features more favorable to machine learning.

Results: A total of 221 COVID-19 survivors discharged from hospitals in Wuhan were enrolled in this study. Of these participants, 117 (52.94%) were female, with a median age of 58.2 years (Standard Deviation (SD)=12). After feature selection, 31 of the 37 clinical factors were ultimately chosen for use in the model construction. Among the six ML models tested, the best performance was accomplished in the XGBoost model, with an AUC of 0.755 and an accuracy of 78.01% after experimental verification. The SHAPELY Additive explanations (SHAP) summary analysis exhibited that Hemoglobin (Hb), Maximal Voluntary Ventilation (MVV), severity of illness, Platelet (PLT), Uric Acid (UA) and Blood Urea Nitrogen (BUN) were the top six most important factors affecting the XGBoost model decision-making.

Conclusion: The XGBoost model reported here showed good prognostic prediction ability for Carbon Monoxide Diffusing Capacity of the lungs (DLCO) of COVID-19 survivors during the recovery period. Of the features selected, Hb and MVV contributed most to the outcome prediction of DLCO of the convalescent COVID-19 survivors.