RESUMO
INTRODUCTION: The COVID-19 patients in the convalescent stage noticeably have pulmonary diffusing capacity impairment (PDCI). The pulmonary diffusing capacity is a frequently-used 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: Collected from a follow-up study from August to September 2021 of 221 hospitalized survivors of COVID-19 18 months after discharge from Wuhan, including the demographic characteristics and clinical examination, the data in this study were randomly separated 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 patients infected with COVID-19 in the recovery stage. The performance indicators of the model included area under the curve (AUC), Accuracy, Recall, Precision, Positive Predictive Value(PPV), Negative Predictive Value (NPV) and F1. The model with the optimum performance was defined as the optimal model, which was further employed 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 were recruited in this study after discharge from hospitals in Wuhan. 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 finally selected for use in constructing the model. Among the six tested ML models, 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 a good prognostic prediction ability for PDCI of COVID-19 survivors during the recovery period. Among the interpretation methods based on the importance of SHAP values, Hb and MVV contributed the most to the prediction of PDCI outcomes of COVID-19 survivors in the recovery period.
Assuntos
COVID-19 , Capacidade de Difusão Pulmonar , Humanos , Feminino , Pessoa de Meia-Idade , Masculino , Seguimentos , Área Sob a Curva , Aprendizado de MáquinaRESUMO
IMPORTANCE: An ongoing outbreak of COVID-19 has exhibited significant threats around the world. We found a significant decrease of T lymphocyte subsets and an increase of inflammatory cytokines of hospitalized patients with COVID-19 in clinical practice. METHODS: We conducted a retrospective, single-center observational study of in-hospital adult patients with confirmed COVID-19 in Hubei Provincial Hospital of traditional Chinese and Western medicine (Wuhan, China) by Mar 1, 2020. Demographic, clinical, laboratory information, especially T lymphocyte subsets and inflammatory cytokines were reported. For patients who died or discharge from hospital, the associations of T lymphocyte subsets on admission were evaluated by univariate logistic regression with odds ratios (ORs) and 95% confidence intervals (CIs), warning values to predict in-hospital death were assessed by Receiver Operator Characteristic (ROC) curves. RESULTS: A total of 187 patients were enrolled in our study from Dec 26, 2019 to Mar 1, 2020, of whom 145 were survivors (discharge = 117) or non-survivors (in-hospital death ==28). All patients exhibited a significant drop of T lymphocyte subsets counts with remarkably increasing concentrations of SAA, CRP, IL-6, and IL-10 compared to normal values. The median concentrations of SAA and CRP in critically-ill patients were nearly 4- and 10-fold than those of mild-ill patients, respectively. As the severity of COVID-19 getting worse, the counts of T lymphocyte drop lower.28 patients died in hospital, the median lymphocyte, CD3+ T-cell, CD4+ T-cell, CD8+ T-cell and B-cell were significantly lower than other patients. Lower counts (/uL) of T lymphocyte subsets lymphocyte (<500), CD3+T-cell (<200), CD4+ T-cell (<100), CD8+ T-cell (<100) and B-cell (<50) were associated with higher risks of in-hospital death of CIVID-19. The warning values to predict in-hospital death of lymphocyte, CD3+ T-cell, CD4+ T-cell, CD8+ T-cell, and B-cell were 559, 235, 104, 85 and 82, respectively. CONCLUSION: We find a significant decrease of T lymphocyte subset is positively correlated with in-hospital death and severity of illness. The decreased levels of T lymphocyte subsets reported in our study were similar with SARS but not common among other virus infection, which may be possible biomarkers for early diagnosis of COVID-19. Our findings may shed light on early warning of high risks of mortality and help early intervention and treatment of COVID-19.