Andy Ilachinski and David Broyles, co-hosts of AI with AI, CNA’s popular podcast on artificial intelligence, have compiled a timely, annotated list of AI developments and resources related to COVID-19. Entries are cross-referenced with the podcast episodes in which Dave and Andy discussed them.

COVID-19 and AI-Related News, Research, and Resources

Boston Children’s Hospital Uses Machine Learning to Help Track Coronavirus

The Innovation & Digital Health Accelerator at Boston Children’s Hospital has developed a dashboard that uses machine learning and social media data to track COVID-19. John Brownstein, chief innovation officer at Boston Children's Hospital and director of the HealthMap program: “Whether it's social media, online news reports, blogs, chat rooms — we're looking for clues about symptoms, reports of disease that tell us something unique is happening.” 

Discussed on “AI with AI” Podcast 3.20


COVID-19 Open Research Dataset (CORD-19) and Open Research Dataset Challenge

The COVID-19 Open Research Dataset (CORD-19) is a free resource of over 29,000 scholarly articles for the global research community about COVID-19 and the coronavirus family of viruses. More than 13,000 are available with full text. Created by the Allen Institute for AI at the request of the White House Office of Science and Technology Policy in partnership with Georgetown University’s Center for Security and Emerging Technology, the Chan Zuckerberg Initiative, Microsoft Research and the National Institute of Health.

The CORD-19 dataset is the most extensive machine-readable coronavirus literature collection available for data mining.

Additional resources include a full-text search engine (CORD-19 Explorer) and CoViz, an interactive, AI-powered graph visualization tool to explore associations between scientific concepts in the CORD-19 corpus.

Discussed on "AI with AI" Podcast 3.21

New England Complex Systems Institute: Coronavirus Pandemic Resources

The New England Complex Systems Institute (NECSI) is an independent academic research and educational institution with students, postdoctoral fellows and faculty. NESCI’s research team includes co-faculty, students and affiliates from MIT, Harvard, Brandeis University and other national and international universities. NESCI’s coronavirus resources are updated daily and include analyses and visualizations (e.g., guides to action, COVID-19 guidelines, and recommendations for policy makers), position statements, exploration of innovative ideas, and links to other resources.

Discussed on “AI with AI” Podcast 3.21

Dedicated page:

Anodot Launches Public ML-Driven Service to Track COVID-19

Anodot, headquartered in Silicon Valley and specializing in providing autonomous monitoring services, offers a public service including a machine-learning-driven analytics dashboard that monitors locally reported COVID-19 cases and notifies users when a region’s numbers change significantly. Algorithms are based on publicly available data derived from The Center for Systems Science and Engineering CSSE at Johns Hopkins University.

Discussed on “AI with AI” Podcast 3.21

Mapping the Landscape of AI Applications Against COVID-19

Researchers from the World Health Organization, Mila/Quebec AI Institute (University of Montreal), and the United Nations Global Pulse (the UN Secretary General’s initiative on big data and AI) have compiled a 14-page survey of AI applications currently being developed to help fight COVID-19.

There is a broad range of potential applications of AI covering medical and societal challenges created by the COVID-19 pandemic; however, few of them are currently mature enough to show operational impact.

Discussed on “AI with AI” Podcast 3.22

AI Firm Launches US Community Vulnerability Map for COVID 

Healthcare AI company Jvion, founded around 2010 to develop “prescriptive analytics for preventable harm,” offers an online mapping tool that allows people to view regions of the United States by county to identify areas most vulnerable to negative outcomes caused by COVID-19. 

Jvion‘s Community Vulnerability Map divides the U.S. into hundreds of different regions based on census data that users can click on to view:  a community vulnerability score (ranging from very low to extremely high), and socioeconomic factors (such as low unemployment or environmental health hazards) driving that risk. Users select a geographic location (or enter a specific reference point) in the search bar to drill down to census block level information.

Discussed on “AI with AI” Podcast 3.23

COVID Symptom Tracker App

The COVID Symptom Tracker developed by King’s College London is an app available for both Android and iOS, designed to help researchers better understand COVID-19 by tracking its spread in real time. The app, which as of mid-April had recruited more than 1.5 million people in the UK, asks users to record health information on a daily basis, including their temperature, any tiredness and other potential symptoms of coronavirus infection. An analysis of the first batch of data recorded by the app, collected between March 24 and 29,  revealed that users who tested positive for COVID-19 were three times more likely to report losing their sense of smell and taste than were those who had symptoms of the virus but tested negative. Other common symptoms experienced by people who tested positive for COVID-19 were fever, persistent cough, fatigue, diarrhea, abdominal pain and loss of appetite.

Discussed on “AI with AI” Podcast 3.23



Crowdsourcing: Joint iOS and Android COVID-19 Tracking System

Apple and Google announced a system for tracking the spread of COVID-19, allowing users to share data through Bluetooth Low Energy transmissions and approved apps from health organizations. The system uses Bluetooth to establish a voluntary contact-tracing network, keeping extensive data on phones that have been in close proximity with each other. Phase one requires users willing to participate in the crowdsourced contact-tracing effort to download and install an Android or iOS app; phase two (scheduled for roll-out in a few months) will consist of building tracing functionality directly into the underlying operating systems.

Discussed on “AI with AI” Podcast 3.25


White paper:

Predictive Models for Diagnosis and Prognosis Systematically Reviewed 

The medical journal BMJ published a review and critical appraisal of published and preprint reports of prediction models for diagnosing COVID-19 in patients with suspected infection, for prognosis of patients with COVID-19, and for detecting people in the general population at risk of being admitted to hospital for COVID-19 pneumonia. Data sources include PubMed and Embase through Ovid, Arxiv, medRxiv, and bioRxiv up to 24 March 2020. The review found that “proposed models are poorly reported, at high risk of bias, and their reported performance is probably optimistic.”

Discussed on “AI with AI” Podcast 3.25

International Roundtable on AI and COVID-19

CIFAR, a Canadian global charitable organization chartered to address questions on the cusp of science and society, convened an International Roundtable on AI and COVID-19 on March 23, 2020. The group explored opportunities for collaboration and sharing of datasets between AI and infectious disease researchers. Participants included Yoshua Bengio (Université de Montréal), Yann LeCun (Facebook), and Joshua Vogelstein (Johns Hopkins University).

Discussed on “AI with AI” Podcast 3.23

Meeting summary:

CSH Covid-19 Control Strategies List (CCCSL)

CCCSL is a dataset of governmental measures against the spread of COVID-19. It has been compiled by the Complexity Science Hub Vienna, which operates within an international network including the Santa Fe Institute, the NTU Singapore Complexity Institute, Arizona State University, and the Institute of Advanced Studies Amsterdam. The database is the most comprehensive dataset on governmental measures against the spread of COVID-19. It includes more than 170 governmental measures and has data describing the implementation of these measures in 40 countries and on the Diamond Princess. It is continually updated and may be freely used for scientific analysis.

Discussed on "AI with AI" Podcast 3.23

COVID-19 State Policy Changes Database 

Julia Raifman, assistant professor of Health Law, Policy & Management at Boston University, has compiled an extensive database of the dates of state policy changes for researchers to start investigating health  economic effects.

Discussed on "AI with AI" Podcast 3.23

Virtual Conferences

COVID-19 and AI: A Virtual Conference

The Stanford Institute for Human-Centered Artificial Intelligence convened an international panel of experts to advance the understanding of the virus and its impact on society. Topics addressed include: AI applications in diagnostics and treatment, epidemiological tracking and forecasting of the spread of the virus, information and disinformation, and the broader human impact of COVID-19 and pandemics in general on economies, culture, government, and human behavior. 

Discussed on “AI with AI” Podcast 3.23


Video Proceedings (6 hours):

Conference resources:

Andrew Ilachinski is a principal research scientist for CNA's Special Activities and Intelligence program. He specializes in the mathematical and computer modeling of complex adaptive systems. He pioneered the application of agent-based modeling (ABM), and evolutionary programming techniques to military operations research problems, and developed two of the earliest ABMs of land warfare.