Search

Andrea Esposito,1 Elena Casiraghi,2 Francesca Chiaraviglio,1 Alice Scarabelli,3 Elvira Stellato,3 Guido Plensich,3 Giulia Lastella,1 Letizia Di Meglio,3 Stefano Fusco,3 Emanuele Avola,3 Alessandro Jachetti,4 Caterina Giannitto,5 Dario Malchiodi,2 Marco Frasca,2 Afshin Beheshti,6,7 Peter N Robinson,8,9 Giorgio Valentini,2 Laura Forzenigo,1 Gianpaolo Carrafiello1 1Radiology Department, Foundation IRCCS Ospedale Maggiore Policlinico Hospital, Milan, 20122, Italy; 2Anacleto Lab, Computer Science Department, University of Milan, Milan, 20133, Italy; 3Postgraduate School of Diagnostic and Interventional Radiology, University of Milan, Milan, 20122, Italy; 4Accident and Emergency Department, Foundation IRCCS Ospedale Maggiore Policlinico Hospital, Milan, 20122, Italy; 5Radiology Department, Humanitas Research Hospital, Milan, 20013, Italy; 6KBR, Space Biosciences Division, NASA Ames Research Center, Moffett Field, CA, 94035, USA; 7Stanley Center for Psychiatric Research, Broad Institute of MIT and Harvard, Cambridge, MA, 02142, USA; 8The Jackson Laboratory for Genomic Medicine, Farmington, CT, 06032, USA; 9Institute for Systems Genomics, University of Connecticut, Farmington, CT, 06030, USACorrespondence: Elvira Stellato; Alice Scarabelli Email elvira.stellato@gmail.com; alice.scarabelli1105@gmail.comPurpose: To determine the performance of a chest radiograph (CXR) severity scoring system combined with clinical and laboratory data in predicting the outcome of COVID-19 patients.Materials and Methods: We retrospectively enrolled 301 patients who had reverse transcriptase-polymerase chain reaction (RT-PCR) positive results for COVID-19. CXRs, clinical and laboratory data were collected. A CXR severity scoring system based on a qualitative evaluation by two expert thoracic radiologists was defined. Based on the clinical outcome, the patients were divided into two classes: moderate/mild (patients who did not die or were not intubated) and severe (patients who were intubated and/or died). ROC curve analysis was applied to identify the cut-off point maximizing the Youden index in the prediction of the outcome. Clinical and laboratory data were analyzed through Boruta and Random Forest classifiers.Results: The agreement between the two radiologist scores was substantial (kappa = 0.76). A radiological score ≥ 9 predicted a severe class: sensitivity = 0.67, specificity = 0.58, accuracy = 0.61, PPV = 0.40, NPV = 0.81, F1 score = 0.50, AUC = 0.65. Such performance was improved to sensitivity = 0.80, specificity = 0.86, accuracy = 0.84, PPV = 0.73, NPV = 0.90, F1 score = 0.76, AUC= 0.82, combining two clinical variables (oxygen saturation [SpO2]), the ratio of arterial oxygen partial pressure to fractional inspired oxygen [P/F ratio] and three laboratory test results (C-reactive protein, lymphocytes [%], hemoglobin).Conclusion: Our CXR severity score assigned by the two radiologists, who read the CXRs combined with some specific clinical data and laboratory results, has the potential role in predicting the outcome of COVID-19 patients.Keywords: radiography, thoracic, COVID-19, artificial intelligence, prognosis

Additional file 3. Forest plots about the subgroup analysis performed if considering variability in age and in the means of delayed bleeding detection (Figure A to C), and about the two sensitivity analyses performed (Figure D and E).

Additional file 2. Additional data about the general characteristcs of the included studies (Table A) and about the subgroup analysis performed if considering variability in the administered antiplatelet agents (Table B).

Additional file 1. Massive Haemorrhage protocol.