Artificial Intelligence and COVID-19: How Technology Can Understand, Track, and Improve Health Outcomes – Stanford University News
On April 1, nearly 30 artificial intelligence (AI) researchers and experts met virtually to discuss ways AI can help understand COVID-19 and potentially mitigate the disease and developing public health crisis.
COVID-19 and AI: A Virtual Conference, hosted by the Stanford Institute for Human-Centered Artificial Intelligence, brought together Stanford faculty across medicine, computer science, and humanities; politicians, startup founders, and researchers from universities across the United States.
“In these trying times, I am especially inspired by the eagerness and diligence of scientists, clinicians, mathematicians, engineers, and social scientists around the world that are coming together to combat this pandemic,” Fei-Fei Li, Denning Family Co-Director of Stanford HAI, told the live audience.
COVID-19: What is Working?
As the virus envelops the world, South Korea, China, Hong Kong, and Singapore have been able to drastically flatten their curves, says Michele Barry, Stanford University professor of medicine. To begin, these countries were quick to enact strong containment, social-distancing or quarantine rules, rigorous and free testing and tracking, and far-reaching communication strategies. Why else were they so successful? All were highly prepared to meet this health crisis as a result of prior experience confronting the 2002 SARS epidemic, she notes.
Jason Wang, director of Stanford’s Center for Policy, Outcomes, and Prevention, pointed to Taiwan as another leader in this space. Taiwan focused on tracking health supplies, coordinating government agencies, regulating transportation, and amending laws for violating quarantine. Both Taiwan and South Korea implemented aggressive technologies, including thermal imaging. If your temperature reading was too high, for example, you were denied entry to an office building or restaurant.
In the United States, early focus has shifted from containment to quarantine and testing. “We’re paying attention to Korea, China, and Singapore and other places that are a month ahead of us,” says U.S. Rep. Ami Bera. Serological testing — used to diagnose the presence of antibodies in the blood — will help us understand who has immunity and when we can reopen parts of the community, he adds.
The Fight Against Misinformation
Managing the scope of this global pandemic has been made more difficult and complicated by the spread of disinformation, misinformation, and conspiracy theories.
In times of crisis, University of Washington associate professor Kate Starbird explains, people come together to seek information and take psychological comfort. But “sensemaking” can also lead to false rumors. Disinformation — false information that’s spread intentionally — causes confusion and even panic and can divert resources to the wrong areas, says Stanford Health Communication Initiative director Seema Yasmin. Both disinformation and misinformation (any information that’s inaccurate) can breed xenophobia. Eram Alam, Harvard University assistant professor, notes a recent uptick in hate crimes and racist incidents as references to the “Chinese virus” or “Wuhan virus” peppered articles and government news conferences.
To maintain trust, says Starbird, political leaders must be mindful that their statements not contribute to the spread of misinformation or cast doubt on science; crisis communicators must be transparent about the rationale for their actions (while acknowledging that facts may change as we learn more).
Researchers’ Roles in Fighting COVID-19
Across disciplines, researchers are finding ways to fight COVID-19, by sharing data and building new tools. Infectious diseases data scientist Lucy Li of the Chan Zuckerberg Biohub says her organization is developing a tool to estimate unreported infections. At Stanford, associate professor of medicine Nigam Shah and colleagues are honing in on ways data science can respond both operationally (How many patients will our region have? How many ICU beds do we need?) and clinically (Whom do we test?), while pointing to critical areas for further research (What drugs can help us?). Harvard Medical School pediatrician John Brownstein and his team are tracking all coronavirus infections worldwide and partnering with organizations designing tools around the information — together with the CDC, for example, they are working to analyze the efficacy of various social-distancing policies.
At Carnegie Mellon, statistics and machine learning associate professor Ryan Tibshirani’s epidemiological forecasting team has shifted from studying flu to COVID-19 to predict short-term forecasts that will inform public health officials in making policy decisions. Meanwhile, Tina White, a Stanford mechanical engineering PhD candidate, designed an open-source app to track the spread of COVID-19, using anonymized Bluetooth data. HAI co-director Fei-Fei Li’s research offers an AI approach to helping senior citizens stay in their homes: sensors and cameras could send valuable information about sleep or dietary patterns, for instance, to clinicians in a secure and ethical way.
Meanwhile, startups are playing a role. Curai co-founder Xavier Amatriain says his company’s machine learning tools create personalized diagnostic assessments, while Anthony Goldbloom’s company, Kaggle, offers the machine-learning community ways to share data and review each other’s work.
Finding a Cure
Tools are essential weapons for tracking and better understanding the disease, but vaccines and drugs are the pathway to an eventual cure. Binbin Chen, Stanford genetics MD and PhD student, says vaccines are among the most powerful ways to curb a pandemic and prevent its recurrence. His team uses artificial intelligence to examine fragments of SARS-CoV-2 to determine how they might apply to COVID-19 vaccines. These tools, says Chen, can “give us a better educated guess and increase our chances of finding an effective vaccine.” Meanwhile, Stanford bioengineering research engineer Stefano Rensi is examining existing drugs that can be repurposed to combat the disease. He and his team use natural language processing, protein structure prediction, and biophysics to identify potential drugs. According to preliminary results, the team has classified several candidates, including one undergoing clinical testing in Japan.