Develop insights for the COVID-19 crisis
The MIT COVID-19 Datathon is a week-long virtual event where teams of data scientists, clinicians, public health professionals and other subject matter experts come together to develop meaningful insights leveraging existing datasets to influence policy and decision making in the public and private sector.
— Continuing Projects —
— Participant Map —
297 participants and 77 mentors from 44 countries
— Research Tracks —
- Track A: Measuring the Impact of Policies around COVID-19
In this track, we are interested in assessing the (causal) effect of various Non-Pharmaceutical interventions (NPIs) such as school closure and shelter-in-place order on the epidemic trajectory. First, staying home may induce changes in human mobility patterns, which in turn may imply a reduction of the growth in infections and deaths. How to quantify the first stage? I.e., the (causal) effect of policies on mobility changes? How to quantify the second stage? I.e., the (causal) effect on reduced human mobility on a decrease in new infections and additional deaths? We are aiming to answer these questions at different geographical scales (country-level, state-level, county-level), using techniques from econometrics and causal inference.
- Track B: Misinformation during the Pandemic
The COVID-19 pandemic has been described as the first “infodemic,” where an overabundance of information makes it challenging for people to find reliable sources when they need it most. Social media in particular can create a rabbit hole effect that allows users to fall deeper and deeper into misinformation. At a time when people’s lives and our public health depend on scientific truth, it becomes more important than ever to identify and stop how societies perpetuate misinformation. In this track, you will use datasets from social media and online news to explore key drivers of misinformation during the pandemic. Ideal mentors include experts from the social sciences and clinicians in public-facing roles. Data scientists will have experience using text, network, and other social media data.
- Track C: Disparities in Health Outcomes from COVID-19
COVID-19 is not the “great equalizer” that some may claim it to be, with preliminary data from the United States and other jurisdictions indicating that the burden of the pandemic is falling disproportionately upon certain marginalized groups. In this track, the goal is to perform data-driven analyses to characterize and understand the nature and magnitude of these disparities, as well as their structural and policy determinants. We will be analyzing datasets related to the prevalence of COVID-19 among different populations, the outcomes of cases in those populations, and structural determinants such as socio-economic status and food security.
- Track D: Epidemiology of COVID-19
The COVID-19 Pandemic is the greatest global public health crisis during the past century adversely impacting millions of people’s health and economies. The world must come together to address this global challenge and develop healthcare, scientific, technical, social, and economic solutions. In order to do this effectively, it is important to understand the scale of the problem, sociodemographic and clinical characteristics of people affected, as well as risk factors for infection, mortality and other adverse health outcomes. This track focuses on generating insights from public data sources to address these issues in order to guide decision-making and the development of effective solutions.
- Track E: Megacity Pandemic Response in NYC
Megacities have become the “locus of risks” during the COVID-19 pandemic, requesting data scientists, health researchers, and urban domain experts to work together. This track focuses on New York City (NYC) as the current epicenter in the U.S. You will explore data-driven insights or possible solutions for better response, management, and operation in NYC during the COVID-19 pandemic. As one of the “first-wave cities” and most “data-rich cities” in North America, NYC can provide valuable insights on critical information, missing data, and analytical routines for the urban-scale pandemic response for other cities.
— Mentors —
Mentors were matched with one team each to support with ideation, dataset review and research guidance for the duration of the event.
Interested in sharing data sets or other resources?
— Agenda —
Sunday, May 10, 2020
Event kickoff and team formation (2:00 PM EST)
May 11 – May 15, 2020
Teams collaborate to develop new insights on existing datasets,
Mentor check-ins + support programming
Saturday, May 16, 2020
Final presentations (11:00 AM EST)
Winners announced + next steps
— Frequently Asked Questions —
WHAT IS THE COVID-19 DATATHON CHALLENGE?
The MIT COVID-19 Datathon is a week-long virtual event where teams of data scientists, clinicians, public health professionals and other subject matter experts come together to develop meaning insights leveraging existing datasets to influence policy and decision marking in the public and private sector.
WHERE IS THE DATATHON TAKING PLACE?
This is a virtual event. Teams will work together throughout the 6-day event using tools such as Github, Zoom, Google Drive, and/or Slack.
WHEN WILL THE CHALLENGE TAKE PLACE?
The virtual datathon will take place Sunday, May 10 through Saturday, May 16.
HOW MUCH TIME DO I NEED TO COMMIT?
Since the goal is to rapidly develop meaningful insights on the current crisis, participants should expect to commit at least 3-5 hours per day for the duration of the event. Participants do not need to be available 24/7 for the duration of the event but should communicate their availability to team members.
WHAT DO WINNING TEAMS GET?
Winning teams will receive computing resources, organizational support and direct access to key partners to further develop, validate and implement solutions developed.
WHO OWNS THE PRODUCT/SOLUTIONS TEAMS CREATE?
In an effort to expedite the development and implementation of solutions developed in this event, all products and solutions developed in this event will be subject to the terms below:
The following terms apply to participation in this hackathon (“Hackathon”). Entrants may create original solutions, prototypes, datasets, scripts, or other content, materials, discoveries or inventions (a “Submission”). The Hackathon is organized by the MIT COVID-19 Datathon organizing team.
Entrants retain ownership of all intellectual and industrial property rights (including moral rights) in and to Submissions.
As a condition of submission, Entrant grants the Hackathon Organizer, its subsidiaries, agents and partner companies, without restrictions, a perpetual, irrevocable, worldwide, royalty-free, and non-exclusive license to use, reproduce, adapt, modify, publish, distribute, publicly perform, create a derivative work from, and publicly display the Submission.
Entrants provide Submissions on an “AS IS” BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied, including, without limitation, any warranties or conditions of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A PARTICULAR PURPOSE.
Entrant represents and warrants that, to the best of his or her knowledge, any work product is Entrant’s own original work and is not within the intellectual property rights of any third party, including any former or current employers. If you are unsure, you should consult any former or current employment agreement to which you are a party. Under no circumstances will Hackathon Organizer be liable to you or any third party for any damages, direct or otherwise, arising out of use of this hackathon work product.
WHO IS ELIGIBLE TO PARTICIPATE?
We are seeking a diverse group of participants. Students and professionals with data science, epidemiology, clinical or public health experience are encouraged to apply.
DO I HAVE TO BE AN MIT STUDENT OR MIT AFFILIATED TO PARTICIPATE?
No! Participants do not need to be affiliated with MIT, just need to be eager to take on COVID-19.
WILL THE EVENT BE HELD IN ENGLISH?
Yes, the event, along with the final presentations, will be held fully in English.
HOW DO I APPLY?
Please complete the application form found here.
Applications are due by May 7 at 11:59 PM EST.
HOW ARE APPLICATIONS EVALUATED?
Applications will be reviewed on a rolling basis. Emphasis will be placed on ensuring a diversity of skill sets and demographics are represented among participants. You will receive an email from the organizing team by May 8 at 11:59pm EST with an update regarding your acceptance.
HOW ARE TEAMS FORMED?
Participants will work together in teams of 4-5 members. Teams will be formed organically at the start of the event based on interests and experience.
DO I NEED TO COME WITH AN RESEARCH QUESTION?
The event will provide a number of sample research questions per research track to worked on. You and your team may draft a new research question, but you will need to receive approval from the organizing team.
WHAT TOOLS/RESOURCES WILL BE PROVIDED?
Teams will be connected with technical resources, data sets, developer platforms and experienced mentors throughout the weekend to help them create, iterate, build, and develop solutions as quickly as possible.
WILL YOU BE PROVIDING CERTIFICATES TO PARTICIPANTS?
Unfortunately, the organizing team cannot provide certificates to participants.
HOW DO I BECOME A MENTOR?
Please complete the form here.
WHAT IS EXPECTED OF MENTORS?
Mentors will be assigned one team to work with based on their experience and expertise. Mentors do not need to be available for the entire weekend. Mentors are expected to provide 1-hour support per day during the duration of the event.
HOW DOES MY ORGANIZATION/ COMPANY BECOME A PARTNER?
Thank you for your interest! Please email email@example.com. A member of the organizing team will contact you to determine how your organization’s expertise, resources, and reach can be most effectively utilized as part of this effort.
WHAT IF I HAVE OTHER QUESTIONS THAT HAVE NOT BEEN ANSWERED?
If you have additional questions or press inquiries, please email: firstname.lastname@example.org