Considerations, Good Practices, Risks and Pitfalls in Developing AI Solutions Against COVID-19

The COVID-19 pandemic has been a major challenge to humanity, with 12.7 million confirmed cases as of July 13th, 2020 [1]. In previous work, we described how Artificial Intelligence can be used to tackle the pandemic with applications at the molecular, clinical, and societal scales [2]. In the present follow-up article, we review these three research directions, and assess the level of maturity and feasibility of the approaches used, as well as their potential for operationalization. We also summarize some commonly encountered risks and practical pitfalls, as well as guidelines and best practices for formulating and deploying AI applications at different scales.

[1]  Alejandro Lopez-Rincon,et al.  Classification and specific primer design for accurate detection of SARS-CoV-2 using deep learning , 2020, Scientific Reports.

[2]  Guo-Wei Wei,et al.  Potentially highly potent drugs for 2019-nCoV , 2020, bioRxiv.

[3]  Mihaela van der Schaar,et al.  AutoPrognosis: Automated Clinical Prognostic Modeling via Bayesian Optimization with Structured Kernel Learning , 2018, ICML.

[4]  Shayakhmetov Rim,et al.  Potential COVID-2019 3C-like Protease Inhibitors Designed Using Generative Deep Learning Approaches , 2020 .

[5]  K. Cao,et al.  Using Artificial Intelligence to Detect COVID-19 and Community-acquired Pneumonia Based on Pulmonary CT: Evaluation of the Diagnostic Accuracy , 2020 .

[6]  Alexandra Luccioni,et al.  Mapping the Landscape of Artificial Intelligence Applications against COVID-19 , 2020, J. Artif. Intell. Res..

[7]  K. Cao,et al.  Artificial Intelligence Distinguishes COVID-19 from Community Acquired Pneumonia on Chest CT , 2020, Radiology.

[8]  David C. Kale,et al.  Do no harm: a roadmap for responsible machine learning for health care , 2019, Nature Medicine.

[9]  Manlio De Domenico,et al.  Assessing the risks of "infodemics" in response to COVID-19 epidemics , 2020, medRxiv.

[10]  A. Echenique,et al.  Chest X-Ray Findings in 636 Ambulatory Patients with COVID-19 Presenting to an Urgent Care Center: A Normal Chest X-Ray Is no Guarantee , 2020 .

[11]  Eric J Topol,et al.  Harnessing wearable device data to improve state-level real-time surveillance of influenza-like illness in the USA: a population-based study. , 2020, The Lancet. Digital health.

[12]  Dinggang Shen,et al.  Severity Assessment of Coronavirus Disease 2019 (COVID-19) Using Quantitative Features from Chest CT Images , 2020, ArXiv.

[13]  N. F. Johnson,et al.  Hate multiverse spreads malicious COVID-19 content online beyond individual platform control , 2020, 2004.00673.

[14]  Artem Cherkasov,et al.  Rapid Identification of Potential Inhibitors of SARS‐CoV‐2 Main Protease by Deep Docking of 1.3 Billion Compounds , 2020, Molecular informatics.

[15]  George Barbastathis,et al.  Neural Network aided quarantine control model estimation of COVID spread in Wuhan, China , 2020 .

[16]  Ingemar J. Cox,et al.  Tracking COVID-19 using online search , 2020, npj Digital Medicine.

[17]  A. Phelan,et al.  Baricitinib as potential treatment for 2019-nCoV acute respiratory disease , 2020, The Lancet.

[18]  Dong Xu,et al.  AI-aided design of novel targeted covalent inhibitors against SARS-CoV-2 , 2020, bioRxiv.

[19]  Yaozong Gao,et al.  Lung Infection Quantification of COVID-19 in CT Images with Deep Learning , 2020, ArXiv.

[20]  Richard D Riley,et al.  Prediction models for diagnosis and prognosis of covid-19 infection: systematic review and critical appraisal , 2020 .

[21]  Weiya Shi,et al.  A deep learning-based quantitative computed tomography model for predicting the severity of COVID-19: a retrospective study of 196 patients , 2020, Annals of translational medicine.