tetano
Editor, Senior Moderator
Ann Transl Med
. 2021 Feb;9(3):216.
doi: 10.21037/atm-20-2464.
A deep learning-based quantitative computed tomography model for predicting the severity of COVID-19: a retrospective study of 196 patients
Weiya Shi[SUP] 1 [/SUP], Xueqing Peng[SUP] 2 [/SUP], Tiefu Liu[SUP] 3 [/SUP], Zenghui Cheng[SUP] 4 [/SUP], Hongzhou Lu[SUP] 5 [/SUP], Shuyi Yang[SUP] 1 [/SUP], Jiulong Zhang[SUP] 1 [/SUP], Mei Wang[SUP] 6 [/SUP], Yaozong Gao[SUP] 7 [/SUP], Yuxin Shi[SUP] 1 [/SUP], Zhiyong Zhang[SUP] 1 [/SUP], Fei Shan[SUP] 1 [/SUP]
Affiliations
Abstract
Background: The assessment of the severity of coronavirus disease 2019 (COVID-19) by clinical presentation has not met the urgent clinical need so far. We aimed to establish a deep learning (DL) model based on quantitative computed tomography (CT) and initial clinical features to predict the severity of COVID-19.
Methods: One hundred ninety-six hospitalized patients with confirmed COVID-19 were enrolled from January 20 to February 10, 2020 in our centre, and were divided into severe and non-severe groups. The clinico-radiological data on admission were retrospectively collected and compared between the two groups. The optimal clinico-radiological features were determined based on least absolute shrinkage and selection operator (LASSO) logistic regression analysis, and a predictive nomogram model was established by five-fold cross-validation. Receiver operating characteristic (ROC) analyses were conducted, and the areas under the receiver operating characteristic curve (AUCs) of the nomogram model, quantitative CT parameters that were significant in univariate analysis, and pneumonia severity index (PSI) were compared.
Results: In comparison with the non-severe group (151 patients), the severe group (45 patients) had a higher PSI (P<0.001). DL-based quantitative CT indicated that the mass of infection (MOI[SUB]CT[/SUB]) and the percentage of infection (POI[SUB]CT[/SUB]) in the whole lung were higher in the severe group (both P<0.001). The nomogram model was based on MOI[SUB]CT[/SUB] and clinical features, including age, cluster of differentiation 4 (CD4)[SUP]+[/SUP] T cell count, serum lactate dehydrogenase (LDH), and C-reactive protein (CRP). The AUC values of the model, MOI[SUB]CT[/SUB], POI[SUB]CT[/SUB], and PSI scores were 0.900, 0.813, 0.805, and 0.751, respectively. The nomogram model performed significantly better than the other three parameters in predicting severity (P=0.003, P=0.001, and P<0.001, respectively).
Conclusions: Although quantitative CT parameters and the PSI can well predict the severity of COVID-19, the DL-based quantitative CT model is more efficient.
Keywords: Coronavirus disease 2019 (COVID-19); computed tomography; deep learning; multivariate analysis; predicting.
. 2021 Feb;9(3):216.
doi: 10.21037/atm-20-2464.
A deep learning-based quantitative computed tomography model for predicting the severity of COVID-19: a retrospective study of 196 patients
Weiya Shi[SUP] 1 [/SUP], Xueqing Peng[SUP] 2 [/SUP], Tiefu Liu[SUP] 3 [/SUP], Zenghui Cheng[SUP] 4 [/SUP], Hongzhou Lu[SUP] 5 [/SUP], Shuyi Yang[SUP] 1 [/SUP], Jiulong Zhang[SUP] 1 [/SUP], Mei Wang[SUP] 6 [/SUP], Yaozong Gao[SUP] 7 [/SUP], Yuxin Shi[SUP] 1 [/SUP], Zhiyong Zhang[SUP] 1 [/SUP], Fei Shan[SUP] 1 [/SUP]
Affiliations
- PMID: 33708843
- PMCID: PMC7940921
- DOI: 10.21037/atm-20-2464
Abstract
Background: The assessment of the severity of coronavirus disease 2019 (COVID-19) by clinical presentation has not met the urgent clinical need so far. We aimed to establish a deep learning (DL) model based on quantitative computed tomography (CT) and initial clinical features to predict the severity of COVID-19.
Methods: One hundred ninety-six hospitalized patients with confirmed COVID-19 were enrolled from January 20 to February 10, 2020 in our centre, and were divided into severe and non-severe groups. The clinico-radiological data on admission were retrospectively collected and compared between the two groups. The optimal clinico-radiological features were determined based on least absolute shrinkage and selection operator (LASSO) logistic regression analysis, and a predictive nomogram model was established by five-fold cross-validation. Receiver operating characteristic (ROC) analyses were conducted, and the areas under the receiver operating characteristic curve (AUCs) of the nomogram model, quantitative CT parameters that were significant in univariate analysis, and pneumonia severity index (PSI) were compared.
Results: In comparison with the non-severe group (151 patients), the severe group (45 patients) had a higher PSI (P<0.001). DL-based quantitative CT indicated that the mass of infection (MOI[SUB]CT[/SUB]) and the percentage of infection (POI[SUB]CT[/SUB]) in the whole lung were higher in the severe group (both P<0.001). The nomogram model was based on MOI[SUB]CT[/SUB] and clinical features, including age, cluster of differentiation 4 (CD4)[SUP]+[/SUP] T cell count, serum lactate dehydrogenase (LDH), and C-reactive protein (CRP). The AUC values of the model, MOI[SUB]CT[/SUB], POI[SUB]CT[/SUB], and PSI scores were 0.900, 0.813, 0.805, and 0.751, respectively. The nomogram model performed significantly better than the other three parameters in predicting severity (P=0.003, P=0.001, and P<0.001, respectively).
Conclusions: Although quantitative CT parameters and the PSI can well predict the severity of COVID-19, the DL-based quantitative CT model is more efficient.
Keywords: Coronavirus disease 2019 (COVID-19); computed tomography; deep learning; multivariate analysis; predicting.