Social and Ethical Responsibilities of Computing
A multidisciplinary project from researchers across MIT and the University of Chicago building on experience in epidemic modeling, large-scale data analysis and machine learning, and public policy related to healthcare. The project has three main goals: (1) to better understand what drives differences in outcomes and forecasts among various commonly-deployed epidemic models; (2) to refine techniques for parameter estimation under uncertainty, using all available data including new data streams and proxies; and (3) to analyze efficacy of possible control strategies via socioeconomic recommendations, which can guide public health decisions on effective sampling, testing, and intervention strategies within heterogeneous populations.
Jonathan Gruber (Economics); Simon Johnson (Sloan); Alberto Abadie and Devavrat Shah (IDSS); Vikash Mansinghka (CSAIL); Luis Bettencourt and Anup Malani (University of Chicago); Julie Shah (AeroAstro, CSAIL); David Kaiser (STS, Physics)
Computer Science and Artificial Intelligence Laboratory (CSAIL)
Professor David Gifford is building off of his group's existing work to try to develop peptide vaccine designs that could be used to immunize against Covid-19. His team is also working on developing a system that could predict the disease severity of Covid-19 cases based on HLA type.
Professor Alan Edelman and his collaborators at the Julia Lab are working on multiple projects, including an effort to speed up the drug approval process, a new approach for modeling infectious disease transmission, and a new MIT course on applying computational thinking to COVID-19.
Researchers are also joining larger global efforts to study the virus. Professor Ankur Moitra is part of a global team of 40 principal investigators from more than a dozen universities to conduct computational epidemiology research related to COVID-19. Based out of the University of Virginia, the project recently received a $10 million NSF Expeditions Grant for its work.
Professor Ron Rivest and senior research scientist Daniel Weitzner are working on an opt-in, privacy-preserving smartphone-based method of “contact tracing” (identifying people who have had close contact with infected individuals).
Professor Daniel Jackson and colleagues have developed HandToHold, an online service that connects people within existing circles of friends or colleagues and encourages regular, serendipitous connections via text message.
Professor David Sontag and his Clinical Machine Learning group have started working with Beth Israel Deaconness Medical Center's Emergency Department to help them predict which patients need to be tested.
An initiative of Jameel Clinic, AI Cures is a group of machine learning and life science researchers who are collaborating on developing machine learning methods for finding promising antiviral molecules for Covid-19 and other emerging pathogens. The first open task of AI Cures aims to find drugs that can alleviate secondary effects of Covid-19 on patients affected by pneumonia. A new screening dataset has been released and current results on this benchmark can be found at aicures.mit.edu.
Operations Research Center (ORC)
Professor Dimitris Bertsimas and 20 ORC graduate students are rapidly developing COVID Analytics — a tool for use by hospitals, government officials, and healthcare institutions in the US to combat the spread of Covid-19.
MIT BLOSSOMS, an open source tool for blended learning founded by Professor Richard Larson, is focusing on STEM education for at-home high school students. BLOSSOMS will begin airing in the Bay Area on local TV station KMTP as an educational resource for low-income households that may not have internet access but are likely have a television.
Led by Professors Retsef Levi, Vivek Farias, and Simon Johnson, the Covid-19 Policy Alliance is mapping high-risk sites, counties, and zip codes based on known Covid-19 factors through interactive data tools. The alliance, composed of over 70 MIT faculty, experts, and students from across multiple programs, including nine ORC PhD students, is also supporting state-level triage and allocation of testing and hospital resources with a load-balancing optimizer API that is already integrated to the New Hampshire emergency management system. In addition, the group is engaging with manufacturing companies to build local production capacity of PPEs and is providing ongoing research insights related to the Covid-19 outbreaks in other countries with implications to the US, among numerous other activities.
Researchers from the Laboratory for Financial Engineering headed by Professor Andrew Lo, are applying their healthcare-related work to infectious diseases in an effort to help find solutions to address the Covid-19 crisis and prevent future disasters through the Project Alpha initiative.
ORC graduate students and alumni, under the guidance of Professor Georgia Perakis, are applying methods developed in past research that combines ideas from machine learning, optimization and econometrics, to estimate the probability of Covid-19 transmission and predict how severe the disease will be for patients. The team is also analyzing data from across the world to assess the impact of government strategies, such as social distancing, stay-in orders and lock downs, in order to recommend optimal interventions that minimizes deaths related to Covid-19 without severely impacting the economy.
Institute for Data, Systems, and Society (IDSS)
IDSS COVID-19 Collaboration (Isolat) is an initiative organized by IDSS that takes a data-driven approach to addressing the COVID-19 pandemic. This volunteer effort brings together the broader community affiliated with IDSS and aims at providing systematic and rigorous analyses of data associated with this crisis in order to inform policy makers. While the specific questions are evolving as more data is collected, there are three broad areas that this group is addressing: 1) creating a data structure of heterogeneous data sets (e.g., spread of virus, mobility, interventions), 2) performing prediction of various critical time-dependent variables, and 3) understanding the effects of intervention and policies on the spread of this virus. We recognize that much of the data is noisy and that testing is evolving slowly, hence the quantification of uncertainty of our results is key to providing actionable outcomes.
Laboratory for Information & Decision Systems (LIDS)
LIDS principal investigator Cathy Wu is collaborating with a team on designing city-level decision support for institutional management to mitigate the spread of Covid-19. Wu, an assistant professor in the department of Civil and Environmental Engineering and in the Institute for Data, Systems, and Society, is also working on city-level estimation of Covid-19 case numbers for predicting disease transmission and herd immunity.
MIT-IBM Watson AI Lab
10 research projects funded by the MIT-IBM Watson AI Lab aimed at addressing the health and economic consequences of the pandemic.
Sepsis is a deadly complication of Covid-19, the disease caused by the new coronavirus SARS-CoV-2. About 10 percent of Covid-19 patients get sick with sepsis within a week of showing symptoms, but only about half survive. Identifying patients at risk for sepsis can lead to earlier, more aggressive treatment and a better chance of survival. Early detection can also help hospitals prioritize intensive-care resources for their sickest patients. In a project led by Deputy Dean of Research Daniela Rus, researchers will develop a machine learning system to analyze images of patients’ white blood cells for signs of an activated immune response against sepsis.
Proteins are the basic building blocks of life, and with AI, researchers can explore and manipulate their structures to address longstanding problems. Take perishable food: The MIT-IBM Watson AI Lab recently used AI to discover that a silk protein made by honeybees could double as a coating for quick-to-rot foods to extend their shelf life. In a related project led by MIT professors Benedetto Marelli and Markus Buehler, researchers will enlist the protein-folding method used in their honeybee-silk discovery to try to defeat the new coronavirus. Their goal is to design proteins able to block the virus from binding to human cells, and to synthesize and test their unique protein creations in the lab.
In a project led by MIT professors Daron Acemoglu, Simon Johnson, and Deputy Dean of Academics Asu Ozdaglar will model the effects of targeted lockdowns on the economy and public health. In a recent working paper co-authored by Acemoglu, Victor Chernozhukov, Ivan Werning, and Michael Whinston, MIT economists analyzed the relative risk of infection, hospitalization, and death for different age groups. When they compared uniform lockdown policies against those targeted to protect seniors, they found that a targeted approach could save more lives. Building on this work, researchers will consider how antigen tests and contact tracing apps can further reduce public health risks.
In a project led by MIT Associate Professor Lydia Bourouiba, researchers are developing a rigorous set of methods to measure how well homemade and medical-grade masks do at blocking the tiny droplets of saliva and mucus expelled during normal breathing, coughs, or sneezes. The researchers will test materials worn alone and together, and in a variety of configurations and environmental conditions. Their methods and measurements will determine how well materials protect mask wearers and the people around them.
As Covid-19’s global death toll mounts, researchers are racing to find a cure among already-approved drugs. Machine learning can expedite screening by letting researchers quickly predict if promising candidates can hit their target. In a project led by MIT Assistant Professor Rafael Gomez-Bombarelli, researchers will represent molecules in three dimensions to see if this added spatial information can help to identify drugs most likely to be effective against the disease. They will use NASA’s Ames and U.S. Department of Energy’s NSERC supercomputers to further speed the screening process.
Smartphone data can help limit the spread of Covid-19 by identifying people who have come into contact with someone infected with the virus, and thus may have caught the infection themselves. But automated contact tracing also carries serious privacy risks. In collaboration with MIT Lincoln Laboratory and others, MIT researchers Ronald Rivest and Daniel Weitzner will use encrypted Bluetooth data to ensure personally identifiable information remains anonymous and secure.
In a project led by MIT professors Anthony Sinskey and Stacy Springs, researchers will build data-driven statistical models to evaluate tradeoffs in scaling the manufacture and supply of vaccine candidates. Questions include how much production capacity will need to be added, the impact of centralized versus distributed operations, and how to design strategies for fair vaccine distribution. The goal is to give decision-makers the evidence needed to cost-effectively achieve global access.
In a project led by MIT professors Roy Welsch and Stan Finkelstein, researchers will use statistics, machine learning, and simulated clinical drug trials to find and test already-approved drugs as potential therapeutics against Covid-19. Researchers will sift through millions of electronic health records and medical claims for signals indicating that drugs used to fight chronic conditions like hypertension, diabetes, and gastric influx might also work against Covid-19 and other diseases.
In collaboration with IBM researchers Zach Shahn and Daby Sow, MIT researchers Li-Wei Lehman and Roger Mark will develop an AI tool to help doctors find better ventilator settings for Covid-19 patients and decide how long to keep them on a machine. Shortened ventilator use can limit lung damage while freeing up machines for others. To build their models, researchers will draw on data from intensive-care patients with acute respiratory distress syndrome, as well as Covid-19 patients at a local Boston hospital.
In a project led by MIT Professor Dimitris Bertsimas, researchers will study the effects of lockdowns and other measures meant to reduce new infections and deaths and prevent the health-care system from being swamped. In a second phase of the project, they will develop machine learning models to predict how vulnerable a given patient is to Covid-19, and what personalized treatments might be most effective. They will also develop an inexpensive, spectroscopy-based test for Covid-19 that can deliver results in minutes and pave the way for mass testing. The project will draw on clinical data from four hospitals in the United States and Europe, including Codogno Hospital, which reported Italy’s first infection.
AI Education for K-12
In light of the recent events surrounding Covid-19 and the impact it has had on learning for grades K-12, a team led by Media Lab Associate Professor Cynthia Breazeal has launched aieducation.mit.edu to share a variety of online activities for students to learn about artificial intelligence, with a focus on how to design and use it responsibly. The website, a collaboration between the Media Lab, MIT Schwarzman College of Computing, and MIT Open Learning, serves as a hub to highlight diverse work by faculty, staff, and students across the MIT community at the intersection of AI, learning, and education.
MIT Emergency Ventilator (E-Vent) Project
A rapidly assembled volunteer team of engineers, physicians, computer scientists, and others, centered at MIT, is working to implement a safe, inexpensive alternative for emergency use, which could be built quickly around the world. The team is releasing design guidance (clinical, mechanical, electrical/controls, testing) on a rolling basis as it is developed and documented at e-vent.mit.edu.
Covid-19 High Performance Computing Consortium
MIT joined the White House supercomputing effort to speed up the search for Covid-19 solutions. The consortium is a collaboration among various industry, government, and academic institutions which will aim to make their supercomputing resources available to the wider research community. MIT is bringing two systems to the effort: Supercloud, an unclassified system run by Lincoln Laboratory, and Satori, a supercomputer donated by IBM as part of the launch of the MIT Schwarzman College of Computing.