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

IEEE Trans Technol Soc. 2022 Jul 29;3(4):272-289. doi: 10.1109/TTS.2022.3195114. eCollection 2022 Dec.

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.

Grants and funding

The work of Julia Amann was supported by the European Union’s Horizon 2020 Research and Innovation Program under Grant 777107 (PRECISE 4Q). The work of Andrea Beretta, Cecilia Panigutti, and Francesca Pratesi was supported by the ERC Advanced through XAI Science and Technology for the Explanation of AI Decision Making under Grant 2018-834756. The work of Walter Osika was supported by the European Union’s Horizon 2020 Research and Innovation Program under Grant 101016233 (PERISCOPE). The work of Matiss Ozols was supported by the Wellcome Trust under Grant 206194. The work of Giovanni Sartor was supported by the European Union’s Justice Programme (2014– 2020) through the H2020 ERC Project “CompuLaw” under Grant 833647. The work of Mattia Savardi, Alberto Signoroni, Filippo Vaccher, and Davide Farina was supported by the Italian Ministry of University and Research (“ResponsiX: Responsible and Deployable AI-Driven Evaluation of COVID- 19 Disease Severity on Chest X-Rays”) under Grant FISR2020IP_02278. The work of Dennis Vetter was supported in part by the European Union’s Horizon 2020 Research and Innovation Program under Grant 101016233 (PERISCOPE), and in part by the Connecting Europe Facility of the European Union under Grant INEA/CEF/ICT/A2020/2276680 (xAIM).