Development and Validation of a Nomogram to Assist Monitoring Nosocomial SARS-CoV-2 Infection of Hospitalized Patients

Abstract

Chen Wang,1,* Chunyan Peng,2,* Leping Ning,3,* Xueping Qiu,1 Kaisong Wu,4 Na Yang,1 Bingyu Jin,1 Yue Zhao,1 Fang Zheng1 1Center for Gene Diagnosis, Department of Laboratory Medicine, Zhongnan Hospital of Wuhan University, Wuhan, Hubei, People’s Republic of China; 2Department of Laboratory Medicine, Taihe hospital, Hubei University of Medicine, Shiyan, Hubei, People’s Republic of China; 3Department of Laboratory Medicine, The People’s Hospital of Guangxi Zhuang Autonomous Region, Nanning, Guangxi, People’s Republic of China; 4Department of Respiratory Medicine, Zhongnan Hospital of Wuhan University, Wuhan, Hubei, People’s Republic of China*These authors contributed equally to this workCorrespondence: Fang Zheng, Center for Gene Diagnosis & Department of Laboratory Medicine, Zhongnan Hospital of Wuhan University, Wuhan University, No. 169 Donghu Road, Wuchang District, Wuhan, 430071, People’s Republic of China, Tel [phone], Fax [phone], Email [email protected]: SARS-CoV-2 is extremely infectious, and the incidence of nosocomial infection is conceivably high. We aimed to develop and validate a nomogram to assist monitoring nosocomial SARS-CoV-2 infection in hospitalized patients.Patients and Methods: There were 437 COVID-19 hospitalized cases and 420 negative inpatients enrolled from two hospitals in Hubei province, China. We compared the demographic and clinical characteristics of participants between the two groups. Then, LASSO regression and logistic regression were applied to build a nomogram for SARS-CoV-2 infection prediction in the development cohort. Our nomogram was assessed by area under the curve (AUC), calibration curve, decision curve (DCA) and clinical impact curve analysis (CICA).Results: After LASSO regression filtration, eleven laboratory indicators were correlated with SARS-CoV-2 infection. Then, we integrated these features and constructed a nomogram, which showed a high AUC 0.863 (95% CI: 0.834– 0.892) in the development cohort with a sensitivity of 80.41% and specificity of 77.38% and 0.813 (95% CI: 0.760– 0.866) in validation cohort with a sensitivity of 82.98% and specificity of 70.43%. The calibration plot displayed that the predicted outcomes were in good concordance with the actual observations. DCA and CICA further showed a larger clinical net benefit.Conclusion: We constructed and validated a nomogram that integrated eleven laboratory indexes to assist monitoring of nosocomial SARS-CoV-2 infection in hospitalized patients. Our nomogram is remarkably informative for clinical practice, which will be helpful for preventing SARS-CoV-2 further transmission in hospital and avoiding nosocomial infection.Graphical Abstract: Keywords: COVID-19, nomogram, nosocomial SARS-CoV-2 infection, machine learning

Keywords

• covid-19
• nomogram
• nosocomial sars-cov-2 infection
• machine learning