IRCCS Policlinico San Donato
Published February 25, 2022 | Version v1
Dataset Restricted

Machine Learning to Predict In-Hospital Mortality in COVID-19 Patients Using Computed Tomography-Derived Pulmonary and Vascular Features

Authors/Creators

  • 1. Unit of Radiology, IRCCS Policlinico San Donato, Via Rodolfo Morandi 30, 20097 Milan, Italy.
  • 2. Department of Radiology, School of Medicine, Stanford University, 300 Pasteur Drive, Stanford, CA 94305, USA.
  • 3. Department of Biomedical Sciences for Health, Università degli Studi di Milano, Via Luigi Mangiagalli 31, 20133 Milan, Italy.
  • 4. IRCCS Istituto Ortopedico Galeazzi, Via Riccardo Galeazzi 4, 20161 Milan, Italy.
  • 5. Department of Diagnostic Imaging and Stereotactic Radiosurgery, C.D.I. Centro Diagnostico Italiano S.p.A., Via Simone Saint Bon 20, 20147 Milan, Italy.
  • 6. Radiodiagnostics, Department of Diagnosis and Treatment Services, Azienda Ospedaliero Universitaria Maggiore della Carità, Corso Giuseppe Mazzini 18, 28100 Novara, Italy.
  • 7. Postgraduate School in Radiodiagnostics, Università degli Studi di Milano, Via Festa del Perdono 7, 20122 Milan, Italy.
  • 8. Unit of Interventional Radiology, Unit of Radiology, Fondazione Poliambulanza Istituto Ospedaliero, Via Leonida Bissolati 57, 25124 Brescia, Italy.
  • 9. Diagnostic and Interventional Radiology Service, ASST Santi Paolo e Carlo, Via Antonio di Rudinì 8, 20142 Milan, Italy.
  • 10. Unit of Radiology, Ospedale Universitario Luigi Sacco-ASST Fatebenefratelli Sacco, Via Giovanni Battista Grassi 74, 20157 Milan, Italy.
  • 11. Unit of Interventional Radiology, Unit of Radiology, ASST Crema-Ospedale Maggiore, Largo Ugo Dossena 2, 26013 Crema, Italy.
  • 12. High Speciality Center for Dietetics, Nutritional Education and Cardiometabolic Prevention, IRCCS Policlinico San Donato, Via Rodolfo Morandi 30, 20097 Milan, Italy.
  • 13. Department of Oncology and Hematology-Oncology, Università degli Studi di Milano, Via Festa del Perdono 7, 20122 Milan, Italy.
  • 14. Division of Breast Radiology, IEO-Istituto Europeo di Oncologia IRCCS, Via Giuseppe Ripamonti 435, 20141 Milan, Italy.
  • 15. Department of General and Emergency Surgery, ASST Crema-Ospedale Maggiore, Largo Ugo Dossena 2, 26013 Crema, Italy.
  • 16. ASST Grande Ospedale Metropolitano Niguarda, Piazza dell'Ospedale Maggiore 3, 20162 Milan, Italy.
  • 17. ASST Grande Ospedale Metropolitano Niguarda, Piazza dell'Ospedale Maggiore 3, 20162 Milan, Italy

Description

Dataset from Schiaffino S, Codari M, Cozzi A, Albano D, Alì M, Arioli R, Avola E, Bnà C, Cariati M, Carriero S, Cressoni M, Danna PSC, Della Pepa G, Di Leo G, Dolci F, Falaschi Z, Flor N, Foà RA, Gitto S, Leati G, Magni V, Malavazos AE, Mauri G, Messina C, Monfardini L, Paschè A, Pesapane F, Sconfienza LM, Secchi F, Segalini E, Spinazzola A, Tombini V, Tresoldi S, Vanzulli A, Vicentin I, Zagaria D, Fleischmann D, Sardanelli F. Machine Learning to Predict In-Hospital Mortality in COVID-19 Patients Using Computed Tomography-Derived Pulmonary and Vascular Features. J Pers Med. 2021 Jun 3;11(6):501. doi: 10.3390/jpm11060501. PMID: 34204911; PMCID: PMC8230339.

Abstract

Pulmonary parenchymal and vascular damage are frequently reported in COVID-19 patients and can be assessed with unenhanced chest computed tomography (CT), widely used as a triaging exam. Integrating clinical data, chest CT features, and CT-derived vascular metrics, we aimed to build a predictive model of in-hospital mortality using univariate analysis (Mann-Whitney U test) and machine learning models (support vectors machines (SVM) and multilayer perceptrons (MLP)). Patients with RT-PCR-confirmed SARS-CoV-2 infection and unenhanced chest CT performed on emergency department admission were included after retrieving their outcome (discharge or death), with an 85/15% training/test dataset split. Out of 897 patients, the 229 (26%) patients who died during hospitalization had higher median pulmonary artery diameter (29.0 mm) than patients who survived (27.0 mm, p < 0.001) and higher median ascending aortic diameter (36.6 mm versus 34.0 mm, p < 0.001). SVM and MLP best models considered the same ten input features, yielding a 0.747 (precision 0.522, recall 0.800) and 0.844 (precision 0.680, recall 0.567) area under the curve, respectively. In this model integrating clinical and radiological data, pulmonary artery diameter was the third most important predictor after age and parenchymal involvement extent, contributing to reliable in-hospital mortality prediction, highlighting the value of vascular metrics in improving patient stratification.

Files

Restricted

The record is publicly accessible, but files are restricted. <a href="https://zenodo.org/account/settings/login?next=https://zenodo.org/records/6277756">Log in</a> to check if you have access.

Request access

If you would like to request access to these files, please fill out the form below.

You need to satisfy these conditions in order for this request to be accepted:

These data are available upon duly motivated request to: simone.schiaffino@grupposandonato.it

You are currently not logged in. Do you have an account? Log in here