Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2022 Jul 29;3(4):272-289.
doi: 10.1109/TTS.2022.3195114. eCollection 2022 Dec.

Assessing Trustworthy AI in Times of COVID-19: Deep Learning for Predicting a Multiregional Score Conveying the Degree of Lung Compromise in COVID-19 Patients

Himanshi Allahabadi  1 , Julia Amann  2 , Isabelle Balot  3 , Andrea Beretta  4 , Charles Binkley  5 , Jonas Bozenhard  6 , Frederick Bruneault  7   8 , James Brusseau  9 , Sema Candemir  10 , Luca Alessandro Cappellini  11   12 , Subrata Chakraborty  13   14 , Nicoleta Cherciu  15 , Christina Cociancig  16 , Megan Coffee  17 , Irene Ek  18 , Leonardo Espinosa-Leal  19 , Davide Farina  20 , Genevieve Fieux-Castagnet  21 , Thomas Frauenfelder  22 , Alessio Gallucci  23 , Guya Giuliani  24 , Adam Golda  25 , Irmhild van Halem  26 , Elisabeth Hildt  27 , Sune Holm  28 , Georgios Kararigas  29 , Sebastien A Krier  30 , Ulrich Kuhne  31 , Francesca Lizzi  32 , Vince I Madai  33   34 , Aniek F Markus  35 , Serg Masis  36 , Emilie Wiinblad Mathez  26 , Francesco Mureddu  37 , Emanuele Neri  38 , Walter Osika  39 , Matiss Ozols  40   41   42 , Cecilia Panigutti  43 , Brendan Parent  44 , Francesca Pratesi  4 , Pedro A Moreno-Sanchez  45 , Giovanni Sartor  46   47 , Mattia Savardi  48 , Alberto Signoroni  48 , Hanna-Maria Sormunen  49 , Andy Spezzatti  50   51 , Adarsh Srivastava  52 , Annette F Stephansen  53 , Lau Bee Theng  54 , Jesmin Jahan Tithi  55   56 , Jarno Tuominen  57 , Steven Umbrello  58 , Filippo Vaccher  20 , Dennis Vetter  59 , Magnus Westerlund  19   60 , Renee Wurth  61 , Roberto V Zicari  19   62
Affiliations

Assessing Trustworthy AI in Times of COVID-19: Deep Learning for Predicting a Multiregional Score Conveying the Degree of Lung Compromise in COVID-19 Patients

Himanshi Allahabadi et al. IEEE Trans Technol Soc. .

Abstract

This article's main contributions are twofold: 1) to demonstrate how to apply the general European Union's High-Level Expert Group's (EU HLEG) guidelines for trustworthy AI in practice for the domain of healthcare and 2) to investigate the research question of what does "trustworthy AI" mean at the time of the COVID-19 pandemic. To this end, we present the results of a post-hoc self-assessment to evaluate the trustworthiness of an AI system for predicting a multiregional score conveying the degree of lung compromise in COVID-19 patients, developed and verified by an interdisciplinary team with members from academia, public hospitals, and industry in time of pandemic. The AI system aims to help radiologists to estimate and communicate the severity of damage in a patient's lung from Chest X-rays. It has been experimentally deployed in the radiology department of the ASST Spedali Civili clinic in Brescia, Italy, since December 2020 during pandemic time. The methodology we have applied for our post-hoc assessment, called Z-Inspection®, uses sociotechnical scenarios to identify ethical, technical, and domain-specific issues in the use of the AI system in the context of the pandemic.

Keywords: Artificial intelligence; COVID-19; Z-Inspection®; case study; ethical tradeoff; ethics; explainable AI; healthcare; pandemic; radiology; trust; trustworthy AI.

PubMed Disclaimer

Figures

Fig. 1.
Fig. 1.
Z-Inspection® process in a nutshell (adapted from [5]).
Fig. 2.
Fig. 2.
Brixia score. (a) six zones definition and (b) and (c) examples of scores (either defined by the radiologist or estimated from the AI). In (b), confidence values generated by the AI prediction are shown (modified version of the figure in [1]).
Fig. 3.
Fig. 3.
COVID-19 reporting form.
Fig. 4.
Fig. 4.
Distribution of patients’ age (left) and sex (right) in the training dataset.
See this image and copyright information in PMC

References

    1. Borghesi A.et al., “Chest X-ray severity index as a predictor of in-hospital mortality in coronavirus disease 2019: A study of 302 patients from Italy,” Int. J. Infect. Dis., vol. 96, pp. 291–293, Jul. 2020, doi: 10.1016/j.ijid.2020.05.021. - DOI - PMC - PubMed
    1. Signoroni A.et al., “BS-Net: Learning COVID-19 pneumonia severity on a large chest X-ray dataset,” Med. Image Anal., vol. 71, Jul. 2021, Art. no. 102046, doi: 10.1016/j.media.2021.102046. - DOI - PMC - PubMed
    1. (AI HLEG) High-Level Expert Group on Artificial Intelligence. “Ethics Guidelines for Trustworthy AI.” European Commission. Apr. 2019. [Online]. Available: https://op.europa.eu/en/publication-detail/-/publication/d3988569-0434-1... (Accessed: Oct. 26, 2020).
    1. (Eur. Commission, Brussels, Belgium). Laying Down Harmonised Rules on Artificial Intelligence (Artificial Intelligence Act) and Amending Certain Union Legislative Acts. (Apr. 2021). Accessed: Nov. 30, 2021. [Online]. Available: https://eur-lex.europa.eu/legal-content/EN/TXT/?uri=CELEX:52021PC0206
    1. Zicari R. V.et al., “Z-inspection®: A process to assess trustworthy AI,” IEEE Trans. Technol. Soc., vol. 2, no. 2, pp. 83–97, Jun. 2021, doi: 10.1109/TTS.2021.3066209. - DOI

LinkOut - more resources