Goal: Come up with ideas and build applications to help the communities in tackling Covid-19 crisis. Sign up form
Join Slack Channel for Discussion
Upcoming Online Hackathon events:
Covid-19 Online Hackathon Saturday April 18, 2020 at 10 am Pacific Time
Cough Against Covid-19 https://www.coughagainstcovid.org/ Jigar Doshi from Wadhwani AI will present about this project to build AI-powered cough analysis technology that could assist in rapid and early diagnosis of COVID-19. This project is sponsored by Bill & Melinda Gates Foundation in collaboration with Stanford University.
Ivana Williams Staff Research Scientist at Chan Zuckerberg Initiative will give an intro on Exploration of the CORD-19 data set (papers from Pubmed, BioRxiv, MedRxiv, etc.) including document/sentence embeddings to serve IR or QA, clustering, visualization, and key phrase extraction.
One of the hackathon teams led by Matt Rubashkin, Rachael Creager and fellows from Insight Data Science will be giving a demo of their hackathon project, a Better Search Engine for Covid-19 Researchers.
Past Online Hackathon events:
Covid-19 Online Hackathon, Saturday March 14, 2020
Covid-19 Online Hackathon: Work on COVID-19 Open Research Dataset, Saturday March 21, 2020 Main Topic: Mining Medical Literature using AI
Covid-19 Online Hackathon Saturday April 4, 2020 at 10 am Pacific Time
Quick Start Data Exploration Notebook:
- Quick Start Covid-19 Cases Data Exploration Colab Notebook provided by AI For Mankind
Exploratory Data Analysis Notebooks Built by Hackathon Participants
State by state ICU Beds Availability and Capacity Study: When do ICU’s get too full? by Dave Selinger, Roger Stager, and Jerry Kurata.
collab-covid19-analysis by Abhishek Ghosh Moumita Mukherjee, and Avinash Anantharamu.
Baby Births Data Exploration to understand the number of births/pregnant women across counties in upcoming months during this Coronavirus outbreak.
Applications Built by Participants
A Better Search Engine for Covid-19 Researchers Led by Matthew Rubashkin
Covid19Hotspot.org to crowdsource Covid-19 symptoms at the zipcodes level. It would be great if we have a map of Covid-19 hotspots and symptoms across every zipcode in the United States. This service is built to crowdsource Covid-19 symptoms information from public to build out this hotspot map. The data collected could potentially be used by researchers in understanding the spread.
- Text us your symptoms and zipcode to 415-200-2449
- WaitTimeNow.org to crowdsource wait time to enter store or checkout from the public through text messaging. As many stores start to limit the number of people in their stores to enforce social distancing and prevent the spread of Covid-19, the queue to enter the store is getting longer. Many of us would like to get near real time infos about the wait time for stores before heading out.
- Share the wait time by TEXTing it to (415)319-9114
- Where to Buy to crowdsource items (hand sanitizer, wipes etc) availability in stores during Coronavirus outbreak using Slack channel and share the infos widely to all on the project web page.
- Join this https://tinyurl.com/u845wb4 channel to share infos about where to buy items like hand sanitizer, wipe, toilet paper, and other essential items.
Add Your Ideas Below
- Proposed by Wei Shung Chung: Realtime monitoring of temperature. A way to proactively monitor the temperature of everyone and show a heatmap. Build a REST API to accept geo location and temperature. Users can submit via their phones/web. Users do not need to login. Consider using Twitter. Good news ! Similar tracking app was built by Pinterest CEO and a team of leading scientists.
Quick Start Covid-19 Cases Data Exploration Colab Notebook Proposed by Jared Yu: Determine the spread of the disease. For example, I think there are some best/worse case scenarios to consider per country/globally. I think the growth in some places like Italy, Iran, and S. Korea have surprised people. Also try to rank country preparedness and see which countries are in need and what can be done.
State by state ICU beds availability and capacity study: When do ICU’s get too full? contributed by Dave Selinger and team
A Better Search Engine for Covid-19 Researchers Led by Matthew Rubashkin
Mental Health During Coronavirus Outbreak.
Proposed by Mennatullah Siam: Build maps for potential places for the spread of the virus. In Seattle it was mainly seniors and in general it was found people with less immune system. So if there is a way we can crawl based on locations of hospital/senior homes/ but also proximity to previous places with infections and tracks of each individual found with a virus + amount of time taken to actually have that virus. Building this heatmap might help them trackdown the virus better not sure the applicability though of the idea. I am guessing already govt in developed countries are doing that. The problem is that these tools are probably private. Community effort to build this open source tool will help underdeveloped countries much more at least as warnings for citizens with lower immune system to stay away from these potential places.
Where-To-Buy Project Page Proposed by Wei Shung Chung: Can someone tell me where I can find a mask and any essential items during outbreak/quarantine ? A website driven by communities to post/share infos about the availability of items (Suggested by Anna)
Proposed by Wei Shung Chung: A way for parents to know who is sick in the daycare/school. Need more infos and visibility.
Proposed by Wei Shung Chung: Scan latest papers about Covid-19 from NEJM, JAMA, Lancent, etc and provide summaries of the papers. Find out the treatment plans per individual types (Suggested by Anna). We will form some teams to participate in CORD-19-research-challenge
Proposed by Sambit Das. Handle misinformation
Proposed by Aruj Mahajan: Build a knowledge graph aggregating infos from wikipedia, JHU Covid-19 cases dataset and other data sources.
Understand and find out more infos about the risk to pregnant women.
Proposed by David Selinger: Work on Covid-19 Primers Design: Technical Problems with Existing CDC COVID-19 Primers, and an Improved Set of Primers
Proposed by Anna T and Jean-Philippe Monfet: Tracking those who might have come into contact with a newly confirmed case or suspected case, etc
Proposed by Anna T: Mobile health project that helps people to keep track of their health conditions, e.g. vital signs, symptoms etc.
Train a CT Scan model to diagnose Coronavirus.
- Proposed by Abhay Agarwal :- (a) Develop a mobile application to track locations and path taken by people to reach their destinations. Application will raise a red flag advising not to take particular path and in case if somebody is infected but clinically not yet confirmed so at least we can know their travel history to save other people as soon as initial person’s symtoms get confirmed.
(b) Make a mobile application to strategically place vaccines (when available but need to be prepared in advance) and other medical products to reach to majority of people so they don’t have to travel too much and get benefitted asap.
- Proposed by Kaniska Mandal :-
Analyze Social Network Feeds in order to implement following usecases
(a) find what kind of symptoms are showing up and collect symptom data
(b) find outbreak in new areas and drill down data by location
(c) check if someone is asking for covid-19 help
(d) analyze user sentiment and spread of anxiety
(e) extract geocode and real-time map of users
(f) find availability of testing kits and other critical equipments
(g) create outbreak feature set (location, daily moving average, season) against historical data and predic outbreak for a given location
(h) alert on reaching threshold of outbreak feeds
(i) extract positive and uplifiting news on improvement of situation
Mentors For Hackathon
- Ivana Williams Staff Research Scientist at Chan Zuckerberg Initiative
Existing Useful Applications Built to Combat Covid-19
You can draw some inspirations from the following impactful applications built and deployed by other organizations in combating Covid-19
- Social Distancing Scoreboard
- Quick Start Covid-19 Cases Data Exploration Colab Notebook
- Stanford HAI Covid-19 and AI Virtual Conference
- World Health Organization (WHO) Advice for Public
- CDC Coronavirus Disease 2019 (COVID-19) Situation Summary
- World Health Organization (WHO)
- WHO on LinkedIn
- Coronavirus COVID-19 Global Cases by Johns Hopkins CSSE
- Worldometers Coronavirus Cases in USA
- Facebook & Carnegie Mellon University COVID-19 Symptom Map
- Centers of Disease Control and Prevention (CDC)
- Singapore Covid-19 Dashboard
Datasets and Analysis
- Johns Hopkins University Center for Systems Science and Engineering
- Covid-19 Analysis
- Individual Hospital Statistics for California
- California Health and Human Services Open Data Portal
- Predictive Monitoring of COVID-19
- The New England Journal of Medicine
- The Lancent: Infectious Diseases
- JAMA Network: Covid-19 Collection
Note: If you wish to keep your idea/project private, please do not enter this hackathon.
By participating in this hackathon, participants agree to be bound by all of the terms and conditions as set out below.
Teams must be comprised of 1-5 people.
You have to create a public github repository for your entry with the MIT License.
Participants are not allowed to enter in projects containing confidential information or subject to the proprietary rights of any person or entity.
How Will My Entry be Potentially Used?
By participating in the hackathon, you agree to ALL of the following statements:
You understand and acknowledge that your entry/submission in their entirety will become open source (MIT License) and made publicly available to everyone. You agree to make any code produced/submitted for the hackathon (your entry’s github repository) available under the terms of The MIT License and other created works under the terms of the CC BY-SA 4.0 licence. Participant hereby irrevocably licenses all Work Product under the MIT License located at https://opensource.org/licenses/MIT. “Work Product” means all ideas, concepts, proposals, materials, and all other work product of any nature whatsoever, that are created, prepared, produced, conceived, or reduced to practice by Participant solely or jointly with others during the Hackathon. Participant represents and warrants that, to the best of his or her knowledge, the Work Product is and will be Participant’s own original work and does not and will not infringe the intellectual property or proprietary rights of any third party, including, without limitation, any third party patents, copyrights or trademarks.
- You understand and acknowledge that after the submission deadline has passed, your project (github repository) that has been submitted to the hackathon cannot be deleted or made private. Your project repository will also be featured on the AI For Mankind Covid-19 hackathon github page after the hackathon has concluded.
- You understand and acknowledge that others may have developed or commissioned materials similar or identical to your entry and you waive any claims you may have resulting from any similarities to your entry.
- You understand that you will not receive any compensation for use of your entry.
Note: If you do not agree to above and want to keep your idea/project private, please do not enter this hackathon.
Rules of Conduct
- Respect each other.
- Do not violate copyrights, trademarks, or other such rights.
- Observe data protection legislation.
Note: Teams can be disqualified from the competition at the organizer’s discretion. Reasons might include but are not limited to breaking the Hackathon Rules or other unsporting behavior.
- The MIT License
- CC BY-SA 4.0 Licence
- Chinese Hospitals Deploy AI to Help Diagnose Covid-19
- COVID-19 and artificial intelligence: protecting health-care workers and curbing the spread
- Correlation of Chest CT and RT-PCR Testing in Coronavirus Disease 2019 (COVID-19) in China: A Report of 1014 Cases
- Sensitivity of Chest CT for COVID-19: Comparison to RT-PCR
- Alibaba develops AI system for Covid-19 diagnosis
If you have any questions, please feel free to
Email us at email@example.com