AUTHOR=Vaidya Pranjal , Alilou Mehdi , Hiremath Amogh , Gupta Amit , Bera Kaustav , Furin Jennifer , Armitage Keith , Gilkeson Robert , Yuan Lei , Fu Pingfu , Lu Cheng , Ji Mengyao , Madabhushi Anant 

TITLE=An End-to-End Integrated Clinical and CT-Based Radiomics Nomogram for Predicting Disease Severity and Need for Ventilator Support in COVID-19 Patients: A Large Multisite Retrospective Study

JOURNAL=Frontiers in Radiology

VOLUME=Volume 2 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/radiology/articles/10.3389/fradi.2022.781536

DOI=10.3389/fradi.2022.781536

ISSN=2673-8740

ABSTRACT=The disease COVID-19 has caused a widespread global pandemic with ~3.93 million deaths worldwide. In this work, we present three models- Radiomics (MRM), Clinical (MCM), and combined Clinical-Radiomics (MRCM) nomogram to predict COVID-19 positive patients who will end up needing invasive mechanical ventilation from the baseline CT scans.

We performed a retrospective multicohort study of individuals with COVID-19 positive findings for a total of 980 patients from 2 different institutions (Renmin hospital of Wuhan University, D1 =787 and University Hospitals, US D2 = 110). The patients from institution-1 were divided into 60% training, D1T (N=473), and 40% test set D1V (N=314). The patients from institution-2 were used for an independent validation test set D2V(N=110). A U-Net-based neural network (CNN) was trained to automatically segment out the COVID consolidations on the CT scans. The segmented regions from the CT scans were used for extracting first-order and higher-order Radiomic textural features. The top Radiomic and clinical features were selected using the Least Absolute Shrinkage and Selection Operator (LASSO) with an optimal binomial regression model within D1T. 

The 3 out of the top 5 features identified using D1T were higher-order textural features (GLCM, GLRLM, GLSZM), whereas the last two features included the absolute infection size on the CT scan and the total intensity of the COVID consolidations. The Radiomics Model (MRM) yielded an area under the receiver operating characteristic curve (AUC) of 0.754 [0.709-0.799] on D1T, 0.836 on D1V, and 0.748 D2V. The top prognostic clinical factors identified in the analysis were dehydrogenase(LDH), age, and albumin(ALB). The clinical model had an AUC of 0.784 [0.743-0.825] on D1T, 0.813 on D1V, and 0.723 on D2V. Finally, the combined model, MRCM integrating Radiomic Score, age, LDH, and ALB, yielded an AUC of 0.814 [0.774-0.853] on D1T, 0.847 on D1V, and 0.772 on D2V. The MRCM had an overall improvement in the performance of ~3.77% (D1T: p = 0.0003; D1V: p= 0.0165; D2V: p = 0.024) over MCM.

Our results across multiple sites suggest that the integrated Radiomics and clinical nomogram could help identify COVID-19 patients with more severe disease phenotype and potentially requiring mechanical ventilation.