The incremental value of computed tomography of COVID-19 pneumonia in predicting ICU admission

  1. Maurizio Bartolucci
  2. Matteo Benelli
  3. Margherita Betti
  4. Sara Bicchi
  5. Luca Fedeli
  6. Federico Giannelli
  7. Donatella Aquilini
  8. Alessio Baldini
  9. Guglielmo Consales
  10. Massimo Edoardo Di Natale
  11. Pamela Lotti
  12. Letizia Vannucchi
  13. Michele Trezzi
  14. Lorenzo Nicola Mazzoni
  15. Sandro Santini
  16. Roberto Carpi
  17. Daniela Matarrese
  18. Luca Bernardi
  19. Mario Mascalchi
  20. COVID Working Group USL Toscana Centro and Azienda Ospedaliero-Universitaria Careggi
  21. members of the Working Group USL Toscana Centro and Azienda Ospedaliero-Universitaria Careggi
  22. Germana Allescia
  23. Simone Busoni
  24. Alessandra Bindi
  25. Edoardo Cavigli
  26. Diletta Cozzi
  27. Giovanni Luca Dedola
  28. Silvia Mazzocchi
  29. Vittorio Miele
  30. Chiara Pozzessere
  31. Adriana Taddeucci
  32. Adriano Viviani
  33. Chiara Zini
1 evaluations Published on
Read the full article Related papers
This article on Sciety

Abstract

Rationale

Triage is crucial for patient’s management and estimation of the required Intensive Care Unit (ICU) beds is fundamental for Health Systems during the COVID-19 pandemic.

Objective

To assess whether chest Computed Tomography (CT) of COVID-19 pneumonia has an incremental role in predicting patient’s admission to ICU.

Methods

We performed volumetric and texture analysis of the areas of the affected lung in CT of 115 outpatients with COVID-19 infection presenting to the Emergency Room with dyspnea and unresponsive hypoxyemia. Admission blood laboratory including lymphocyte count, serum lactate dehydrogenase, D-dimer and C-Reactive Protein and the ratio between the arterial partial pressure of oxygen and inspired oxygen were collected. By calculating the areas under the receiver-operating characteristic curves (AUC), we compared the performance of blood laboratory-arterial gas analyses features alone and combined with the CT features in two hybrid models (Hybrid radiological and Hybrid radiomics)for predicting ICU admission. Following a machine learning approach, 63 patients were allocated to the training and 52 to the validation set.

Measurements and Main Results

Twenty-nine (25%) of patients were admitted to ICU. The Hybrid radiological model comprising the lung %consolidation performed significantly (p=0.04) better in predicting ICU admission in the validation (AUC=0.82; 95%Confidence Interval 0.68-0.95) set than the blood laboratory-arterial gas analyses features alone (AUC=0.71; 95%Confidence Interval 0.56-0.86). A risk calculator for ICU admission was derived and is available at:<ext-link xmlns:xlink="http://www.w3.org/1999/xlink" ext-link-type="uri" xlink:href="https://github.com/cgplab/covidapp">https://github.com/cgplab/covidapp</ext-link>

Conclusions

The volume of the consolidated lung in CT of patients with COVID-19 pneumonia has a mild but significant incremental value in predicting ICU admission.

Related articles

Related articles are currently not available for this article.