Table 1.

Studies included in the review.

First author (year)	Area or specialty of AIa application	AI application method	Clinical benefit shown	Internal or external validation done
Hurt (2020) [19]	Diagnosis and clinical decision making	Using a deep learning approach to augment radiographs with color probability	Improved diagnostic accuracy of pneumonia and COVID-19 at point of care, triaged patient for CTb scan, helped physicians track evolution of pulmonary manifestation over length of hospitalization	No
Li (2020) [20]	Diagnosis	Deep learning–based computer-aided diagnostic system for pneumonia trained with CT scans of patients with COVID-19 suggested pneumonia in patients who received a negative reverse-transcription polymerase chain reaction test result	Improved accuracy of diagnosis	No
Li (2020) [21]	Diagnosis	AI 3D deep learning model to analyze CT scan	Improved diagnostic accuracy and differentiated from non–COVID-19 lung pathologies	Yes
Yang (2020) [22]	Public health	Recurrent neural network for AI-based prediction of epidemic trend	Good epidemiological modeling and prediction of trends relating to COVID-19	Yes
Al-Najjar (2020) [23]	Public health	AI-based classifier prediction model to determine the outcome of patients	Identified key factors influencing clinical outcome, guided public health decision making	No
Jiang (2020) [24]	Clinical decision making	Tool with AI capabilities that will predict patients at risk for more severe illnesses based on clinical parameters	AI tool predicted patients at risk for more severe illness on initial presentation, provided clinical decision support	Yes
Beck (2020) [25]	Therapeutics	Used pretrained deep learning–based system to identify commercially available drugs that could act on the viral proteins of SARS-CoV-2	Used AI to discover that atazanavir, an antiretroviral medication, is the best chemical compound due to its high inhibitory potency, among several other antiviral agents that could be used in the treatment of SARS-CoV-2	Yes
Kadioglu (2020) [26]	Therapeutics	AI combined with molecular docking to identify candidates suitable for drug repurposing via in silico methods	Supervised machine learning was used to study drug likeliness of candidate compounds, helped with evaluation of the potential of various agents	Yes
Richardson (2020) [27]	Therapeutics	Use of BenevolentAI's knowledge graph to search for approved drugs that can help treat COVID-19	Baricitinib was identified as a viable drug with tolerable side effects and potential therapeutic use in patients with COVID-19	No
Ton (2020) [28]	Therapeutics	Use of Deep Docking for accelerated screening of large chemical libraries for potential drugs against COVID-19	Screened through 1.3 billion compounds from the ZINC15 library to identify the top 1000 potential ligands against the main protease (Mpro) of SARS-CoV-2 and made them publicly available	Yes
Zhang (2020) [29]	Therapeutics	Use of AI-based dock analysis to determine whether the compounds listed in Traditional Chinese Medicine databases had potential for direct SARS-CoV-2 protein interaction	Identified 26 herbal plants containing compounds potentially active against SARS-CoV-2	No

^aAI: artificial intelligence.

^bCT: computed tomography.