The severity assessment and nucleic acid turning-negative-time prediction in COVID-19 patients with COPD using a fused deep learning model

Abstract

Background Previous studies have shown that patients with pre-existing chronic pulmonary inflammations of chronic obstructive pulmonary diseases (COPD) were more likely to be infected with COVID-19 and lead to more severe lung lesions. However, few studies have explored the severity and prognosis of COVID-19 patients with different phenotypes of COPD. Purpose The aim of this study to investigate the value of the deep learning and radiomics features to evaluated the severity and predict the nucleic acid turning-negative time in COVID-19 patients with COPD including two phenotype of chronic bronchitis predominant patients and emphysema predominant patients. Methods A total of 281 patients were retrospectively collected from Hohhot First Hospital between October 2022 and January 2023. They were divided to three groups: COVID-19 group of 95 patients, COVID-19 with emphysema groups of 94 patients, COVID-19 with chronic bronchitis groups of 92 patients. All patients underwent chest scans and recorded clinical data. The U-net network was trained to segment the infection regions on CT images and the severity of pneumonia were evaluated by the percentage of pulmonary involvement volume to lung volume. The 107 radiomics features were extracted by pyradiomics package. The Spearman method was employed to analyze the correlation between the data and visualize it through a heatmap. Then we respectively establish a deep learning model using original CT image and a fusion model combined deep learning with radiomics features to predict the time for nucleic acid turning-negative. Results COVID-19 patients with emphysema was lowest in the lymphocyte count compared to COVID-19 patients and COVID-19 companied with chronic bronchitis, and they have the most extensive range of pulmonary inflammation. The lymphocyte count was significantly correlated with pulmonary involvement and the time to nucleic acid turning negative (r=-0.145, P < 0.05). Importantly, our results demonstrated that the fusion model achieved an accuracy of 80.9% in predicting nucleic acid turning-negative time. Conclusion The pre-existing emphysema phenotype of COPD severely aggravated the pulmonary involvement. Deep learning and radiomics features may provide more information to accurately predict the nucleic acid turning-negative time, which is expected to play an important role in clinical practice.