Artificial Intelligence (AI) has played an important role in battling COVID-19 since the initial outbreak: HealthMap – an AI tool from Boston Children’s Hospital that scans news reports, social media, and other data for signs of disease outbreaks – first sounded the international alarm after picking up reports of an emerging virus in Wuhan, China. As the virus evolved into a global pandemic, scientists, researchers, and medical professionals have increasingly integrated AI into their efforts to combat the disease.

The following are just a few examples of recent AI developments and AI’s role in the fight against COVID-19.

AI as a Partner in COVID-19 Testing Efforts

AI might help leverage population data to help assess patients’ symptoms: A group of researchers from King’s College London, Massachusetts General Hospital, and health science company ZOE developed an AI tool that compares a patient’s symptoms against crowdsourced symptom data from the COVID Symptom Study app to predict whether that patient is likely to have COVID-19. This tool is set to enter clinical trials in the U.S. and U.K., and the researchers believe that this AI tool may be particularly useful for populations with limited access to testing.

AI also is being used to analyze medical imaging and differentiate between diagnoses with symptoms similar to those of COVID-19. Researchers from the University of Chicago and Argonne National Laboratory, relying on a grant from the new c3.ai Digital Transformation Institute, are developing an AI tool to analyze chest X-rays and thoracic CT scans in order to spot the disease and differentiate between its various stages. UCSD Professor Albert Hsiao has applied his own AI approach to chest X-rays from patients in a research study enabled by a cloud services provider. In China, radiologists are working on a learning model that can distinguish between COVID-19 and community-acquired pneumonia based on chest CT scans.

AI to Identify High-Risk Patients

As hospital systems face an influx of COVID-19 patients, major players in the healthcare industry are turning more and more to AI tools to assist with patient management. Of course, providers already use AI to offer clinical decision support: for example, in 2017, electronic health record vendor Epic released a “Deterioration Index” predictive model to identify patients whose condition is likely to deteriorate. With the onset of COVID-19, Stanford University Professor Ron Li and his team have begun to test the Deterioration Index for triage of COVID-19 patients.

On the payer side, Israel’s Maccabi Healthcare Services partnered with AI company Medial EarlySign to identify which of its 2.4 million members were high risk for severe COVID-19 complications so those patients could be fast-tracked for testing. The organization says it is currently talking to U.S. entities about using the system to fast-track their own patients.

AI as a Research Assistant

AI also can serve as a critical tool in the search for reliable treatments for COVID-19. A research team at Northwestern University developed a machine model that allows researchers to bypass conventional prediction markets and more quickly identify and dedicate resources to the most promising research studies for treatments and vaccines for COVID-19.

Researchers also are using AI to scour molecular modelling data and EHR data to evaluate whether existing drugs may be repurposed as treatments for COVID-19. AI already has identified at least one prospect. Specifically, BenevolentAI, a London startup, used AI to identify the rheumatoid arthritis drug baricitinib as a possible treatment for severe symptoms of COVID-19. Based on this research, a major pharmaceutical company announced that it will conduct a large-scale clinical trial of the drug as a treatment for COVID-19, in collaboration with the U.S. National Institute of Allergy and Infectious Diseases.

Creating Trustworthy AI

As AI development, already a high-activity sector pre-COVID-19, has ramped up further in the effort to battle the virus, stakeholders also continue to focus on AI trustworthiness. Lee Tiedrich and Lala R. Qadir share “10 Steps to Creating Trustworthy AI Applications” in an article for Law360. For more information about AI, please see our “AI Toolkit.”

This post was originally published on the Covington Digital Health blog.

Print:
EmailTweetLikeLinkedIn
Photo of Lee Tiedrich Lee Tiedrich

Lee Tiedrich brings together an undergraduate education in electrical engineering and over twenty years of legal experience to assist clients on a broad range of intellectual property and technology transaction matters. Her work spans several industries, including ehealth, life sciences, consumer products, communications…

Lee Tiedrich brings together an undergraduate education in electrical engineering and over twenty years of legal experience to assist clients on a broad range of intellectual property and technology transaction matters. Her work spans several industries, including ehealth, life sciences, consumer products, communications and media. She counsels both private and public companies, as well as venture capital firms and corporate venture groups in their investments. Ms. Tiedrich has extensive experience negotiating complex intellectual property acquisition, licensing, and development agreements, and regularly counsels clients on strategic issues, such as developing and maintaining intellectual property portfolios and evaluating and addressing intellectual property-related assets and risks.

Photo of James Ermilio James Ermilio

James Ermilio is an associate in the firm’s Corporate Practice Group and represents clients in a broad range of corporate transactions. Mr. Ermilio’s practice includes software and technology licensing agreements, content distribution and media rights agreements, and mergers and acquisitions.