Development and Validation of a Nomogram for Assessing Survival in Patients With COVID-19 Pneumonia
Development and Validation of a Nomogram for Assessing Survival in Patients With COVID-19 Pneumonia
复制标题
DOI：
10.1093/cid/ciaa963
复制
发表时间：
2021-02-15
影响因子：
11.8
通讯作者：
Ye, Da-Wei
中科院分区：
文献类型：
--
作者：
Dong, Yi-Min;Sun, Jia;Ye, Da-Wei
背景2019冠状病毒病（COVID-19）爆发已在全球蔓延，并继续威胁人民的健康，并对医疗系统的可及性造成压力。住院患者生存的早期预测将有助于COVID-19的临床管理，但仍然缺乏可靠有效的预测模型。我们回顾性纳入了中国武汉同济医院628例使用SARS-CoV-2阳性RT-PCR检测的COVID-19确诊病例。这些患者被随机分组为训练（60%）和验证（40%）队列。在训练队列中，使用LASSO回归分析和多变量考克斯回归分析来确定COVID-19患者住院生存的预后因素。建立了基于3个变量的诺模图以供临床使用。使用AUC、一致性指数（C指数）和校准曲线来评估诺模图在训练和验证队列中的效率。研究发现，高血压、嗜中性粒细胞与淋巴细胞比率较高以及NT-proBNP值升高与COVID-19住院患者的预后不良显著相关。3个预测因子进一步用于构建预测诺模图。训练和验证队列中列线图的C指数分别为0.901和0.892。训练队列中14天和21天住院生存概率的AUC分别为0.922和0.919，而在验证队列中分别为0.922和0.881。此外，14天和21天生存率的校准曲线也显示了预测和实际生存概率之间的高度一致性。我们建立了一个预测模型，并构建了一个诺模图，用于预测COVID-19患者的住院生存率。该模型具有良好的性能，可用于COVID-19的临床管理。
Background. The outbreak of coronavirus disease 2019 (COVID-19) has spread worldwide and continues to threaten peoples' health as well as put pressure on the accessibility of medical systems. Early prediction of survival of hospitalized patients will help in the clinical management of COVID-19, but a prediction model that is reliable and valid is still lacking.Methods. We retrospectively enrolled 628 confirmed cases of COVID-19 using positive RT-PCR tests for SARS-CoV-2 in Tongji Hospital, Wuhan, China. These patients were randomly grouped into a training (60%) and a validation (40%) cohort. In the training cohort, LASSO regression analysis and multivariate Cox regression analysis were utilized to identify prognostic factors for in-hospital survival of patients with COVID-19. A nomogram based on the 3 variables was built for clinical use. AUCs, concordance indexes (C-index), and calibration curves were used to evaluate the efficiency of the nomogram in both training and validation cohorts.Results. Hypertension, higher neutrophil-to-lymphocyte ratio, and increased NT-proBNP values were found to be significantly associated with poorer prognosis in hospitalized patients with COVID-19. The 3 predictors were further used to build a prediction nomogram. The C-indexes of the nomogram in the training and validation cohorts were 0.901 and 0.892, respectively. The AUC in the training cohort was 0.922 for 14-day and 0.919 for 21-day probability of in-hospital survival, while in the validation cohort this was 0.922 and 0.881, respectively. Moreover, the calibration curve for 14- and 21-day survival also showed high coherence between the predicted and actual probability of survival.Conclusions. We built a predictive model and constructed a nomogram for predicting in-hospital survival of patients with COVID-19. This model has good performance and might be utilized clinically in management of COVID-19.