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.

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.

Development of machine learning models to predict RT-PCR results for severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) in patients with influenza-like symptoms using only basic clinical data.

BACKGROUND: Reverse Transcription-Polymerase Chain Reaction (RT-PCR) for Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-COV-2) diagnosis currently requires quite a long time span. A quicker and more efficient diagnostic tool in emergency departments could improve management during this global crisis. Our main goal was assessing the accuracy of artificial intelligence in predicting the results of RT-PCR for SARS-COV-2, using basic information at hand in all emergency departments. METHODS: This is a retrospective study carried out between February 22, 2020 and March 16, 2020 in one of the main hospitals in Milan, Italy. We screened for eligibility all patients admitted with influenza-like symptoms tested for SARS-COV-2. Patients under 12 years old and patients in whom the leukocyte formula was not performed in the ED were excluded. Input data through artificial intelligence were made up of a combination of clinical, radiological and routine laboratory data upon hospital admission. Different Machine Learning algorithms available on WEKA data mining software and on Semeion Research Centre depository were trained using both the Training and Testing and the K-fold cross-validation protocol. RESULTS: Among 199 patients subject to study (median [interquartile range] age 65 [46-78] years; 127 [63.8%] men), 124 [62.3%] resulted positive to SARS-COV-2. The best Machine Learning System reached an accuracy of 91.4% with 94.1% sensitivity and 88.7% specificity. CONCLUSION: Our study suggests that properly trained artificial intelligence algorithms may be able to predict correct results in RT-PCR for SARS-COV-2, using basic clinical data. If confirmed, on a larger-scale study, this approach could have important clinical and organizational implications.

Effectiveness of infection-containment measures on SARS-CoV-2 seroprevalence and circulation from May to July 2020, in Milan, Italy.

OBJECTIVE: Through a hospital-based SARS-CoV-2 molecular and serological screening, we evaluated the effectiveness of two months of lockdown and two of surveillance, in Milan, Lombardy, the first to be overwhelmed by COVID-19 pandemics during March-April 2020. METHODS: All subjects presenting at the major hospital of Milan from May-11 to July-5, 2020, underwent a serological screening by chemiluminescent assays. Those admitted were further tested by RT-PCR. RESULTS: The cumulative anti-N IgG seroprevalence in the 2753 subjects analyzed was of 5.1% (95%CI = 4.3%-6.0%), with a peak of 8.4% (6.1%-11.4%) 60-63 days since the peak of diagnoses (March-20). 31/106 (29.2%) anti-N reactive subjects had anti-S1/S2 titers >80 AU/mL. Being tested from May-18 to June-5, or residing in the provinces with higher SARS-CoV-2 circulation, were positively and independently associated with anti-N IgG reactivity (OR [95%CI]: 2.179[1.455-3.264] and 3.127[1.18-8.29], respectively). In the 18 RT-PCR positive, symptomatic subjects, anti-N seroprevalence was 33.3% (95% CI: 14.8%-56.3%). CONCLUSION: SARS-CoV-2 seroprevalence in Milan is low, and in a downward trend after only 60-63 days since the peak of diagnoses. Italian confinement measures were effective, but the risk of contagion remains concrete. In hospital-settings, the performance of molecular and serological screenings upon admission remains highly advisable.