How AI and machine learning are helping to fight COVID-19
Cutting-edge technology is helping to turn the tide on coronavirus and its impacts Image: Fusion Medical Animation on Unsplash
- Organizations have been quick to apply their AI and machine learning know-how in the fight to curb this pandemic.
- These technologies are being deployed in areas from research to healthcare and even agriculture.
As the world grapples with COVID-19, every ounce of technological innovation and ingenuity harnessed to fight this pandemic brings us one step closer to overcoming it. Artificial intelligence (AI) and machine learning are playing a key role in better understanding and addressing the COVID-19 crisis. Machine learning technology enables computers to mimic human intelligence and ingest large volumes of data to quickly identify patterns and insights.
In the fight against COVID-19, organizations have been quick to apply their machine learning expertise in several areas: scaling customer communications, understanding how COVID-19 spreads, and speeding up research and treatment.
Every kind of organization, whether small or large, public or private, is finding new ways to operate effectively and to meet the needs of their customers and employees as social distancing and quarantine measures remain in place. Machine learning technology is playing an important role in enabling that shift by providing the tools to support remote communication, enable telemedicine, and protect food security.
For healthcare and government institutions, that includes using machine learning-enabled chatbots for contactless screening of COVID-19 symptoms and to answer questions from the public. One example is Clevy.io, a French start-up and AWS customer, which has launched a chatbot to make it easier for people to find official government communications about COVID-19. Powered by real-time information from the French government and the World Health Organization, the chatbot assesses known symptoms and answers questions about government policies. With almost 3 million messages sent to-date, this chatbot is able to answer questions on everything from exercise to an evaluation of COVID-19 risks, without further straining the resources of healthcare and government institutions. French cities including Strasbourg, Orléans and Nanterre are using the chatbot to decentralize the distribution of accurate, verified information.
To avoid any disruption to the food supply chain, food processors and governments need to understand the current state of agriculture. Agri-tech start-up Mantle Labs, another AWS customer, is offering its cutting-edge AI-driven crop-monitoring solution to retailers free of charge for a period of three months to provide additional resiliency and certainty to supply chains in the UK. The technology works to assess satellite images of crops to flag potential issues to farmers and retailers early on so they can better manage supply, procurement and inventory planning. The platform deploys custom machine learning models to mix imagery from multiple satellites, enabling a near real-time assessment of agricultural conditions.
What is the World Economic Forum doing about fighting pandemics?
Machine learning is also helping researchers and practitioners analyze large volumes of data to forecast the spread of COVID-19, in order to act as an early warning system for future pandemics and to identify vulnerable populations. Researchers at the Chan Zuckerberg Biohub in California have built a model to estimate the number of COVID-19 infections that go undetected and the consequences for public health, analyzing 12 regions across the globe. Using machine learning and partnering with the AWS Diagnostic Development Initiative, they have developed new methods to quantify undetected infections – analyzing how the virus mutates as it spreads through the population to infer how many transmissions have been missed.
At the beginning of this pandemic, BlueDot, a Canadian start-up and AWS customer that uses AI to detect disease outbreaks, was one of the first to raise the alarm about a worrisome outbreak of a respiratory illness in Wuhan, China. BlueDot uses AI to detect disease outbreaks. Using their machine learning algorithms, BlueDot sifts through news reports in 65 languages, along with airline data and animal disease networks to detect outbreaks and anticipate the dispersion of disease. Epidemiologists then review those results and verify that the conclusions make sense from a scientific standpoint. BlueDot provides those insights to public health officials, airlines and hospitals to help them anticipate and better manage risks.
Machine learning is helping leaders make more informed decisions in the face of COVID-19. In March, a group of volunteer professionals, led by former White House Chief Data Scientist DJ Patil, reached out to AWS for help supporting a scenario-planning tool that modelled the potential impact of COVID-19 in order to answer questions like: “How many hospital beds will we need?” or “For how long should we issue a shelter-in-place order?” They needed to scale their open-source model so governors across the US could understand the volume of exposure, infection and hospitalization to better inform their response plans. In close partnership with AWS and Johns Hopkins Bloomberg School of Public Health, the group moved the model to the cloud, allowing them to run multiple scenarios in just hours and to roll out the model to all 50 states and internationally to help with making decisions that directly impact the global spread of COVID-19.
Organizations are also examining ways to limit the spread of COVID-19, particularly among vulnerable populations. Closedloop, an AI start-up that we work with, is using their expertise in healthcare data to identify those at the highest risk of severe complications from COVID-19. Closedloop has developed and open-sourced a COVID vulnerability index, an AI-based predictive model that identifies people most at-risk of severe complications from COVID-19. This 'C-19 Index' is being used by healthcare systems, care management organizations and insurance companies to identify high-risk individuals, then calling them to share the importance of handwashing and social distancing, and also offering to deliver food, toilet paper, and other essential supplies so they can stay at home.
Healthcare providers and researchers are faced with an exponentially increasing volume of information about COVID-19, which makes it difficult to derive insights that can inform treatment. In response, AWS launched CORD-19 Search, a new search website powered by machine learning, that can help researchers quickly and easily search for research papers and documents and answer questions like “When is the salivary viral load highest for COVID-19?”
Built on the Allen Institute for AI’s CORD-19 open research dataset of more than 128,000 research papers and other materials, this machine learning solution can extract relevant medical information from unstructured text and delivers robust natural-language query capabilities, helping to accelerate the pace of discovery.
In the field of medical imaging, meanwhile, researchers are using machine learning to help recognize patterns in images, enhancing the ability of radiologists to indicate the probability of disease and diagnose it earlier.
UC San Diego Health has engineered a new method to diagnose pneumonia earlier, a condition associated with severe COVID-19. This early detection helps doctors quickly triage patients to the appropriate level of care even before a COVID-19 diagnosis is confirmed. Trained with 22,000 notations by human radiologists, the machine learning algorithm overlays x-rays with colour-coded maps that indicate pneumonia probability. With credits donated from the AWS Diagnostic Development Initiative, these methods have now been deployed to every chest x-ray and CT scan throughout UC San Diego Health in a clinical research study.
Machine learning can also help accelerate the discovery of drugs to help treat COVID-19. BenevolentAI, a UK AI company and AWS customer, turned its platform toward understanding the body’s response to the coronavirus. They launched an investigation using their AI drug discovery platform to identify approved drugs which could potentially inhibit the progression of the novel coronavirus. They used machine learning to help derive contextual relationships between genes, diseases and drugs, leading to the proposal of a small number of drug compounds. In just days, BenevolentAI found that Baricitinib (a drug currently approved for rheumatoid arthritis, owned by Eli Lilly) proved the strongest candidate. Baricitinib is now in late-stage clinical trials with the US National Institute for Allergies and Infectious Diseases (NIAID) to investigate its efficacy and safety as a potential treatment for COVID-19 patients. The speed with which the drug entered clinical trials reflects the urgency of the global pandemic and the significance of AI in facilitating the discovery of new treatments.
I'm inspired and encouraged by the speed at which these organizations are applying machine learning to address COVID-19. I have always believed in the potential of machine learning to help solve the biggest challenges in our world - and that promise is now coming to fruition as organizations respond to this crisis. It is my hope that in this difficult time we can work together on a global scale to innovate and find new ways machine learning can contribute in the fight against COVID-19.
Don't miss any update on this topic
Create a free account and access your personalized content collection with our latest publications and analyses.
License and Republishing
World Economic Forum articles may be republished in accordance with the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International Public License, and in accordance with our Terms of Use.
The views expressed in this article are those of the author alone and not the World Economic Forum.
Stay up to date:
COVID-19
The Agenda Weekly
A weekly update of the most important issues driving the global agenda
You can unsubscribe at any time using the link in our emails. For more details, review our privacy policy.
More on Health and Healthcare SystemsSee all
Naoko Tochibayashi and Mizuho Ota
November 7, 2024