{"642638":{"#nid":"642638","#data":{"type":"news","title":"Georgia Tech Research Team Wins Two Covid-19 Challenges in One Week","body":[{"value":"\u003Cp\u003ESchool of Computational Science and Engineering (CSE) Ph.D. student\u0026nbsp;\u003Cstrong\u003EAlexander Rodriguez\u003C\/strong\u003E\u0026nbsp;and\u0026nbsp;Associate Professor\u0026nbsp;\u003Cstrong\u003EB. Aditya Prakash\u003C\/strong\u003E\u0026nbsp;are enabling new data-driven solutions for pandemic response. Their research, which focuses on influenza-like illnesses (ILI) and Covid-19, garnered global attention by securing two awards for Covid-19-related challenges within the same week in mid-December.\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003ERodriguez and Prakash joined CSE a little over one year ago while working on\u0026nbsp;data science and artificial intelligence research with epidemiological applications, including the development of historical models for influenza forecasting.\u0026nbsp;Shortly after their move to Georgia Tech, the Covid-19 outbreak began.\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003EFor nearly a year since, Prakash\u0026rsquo;s group has led the charge on numerous\u0026nbsp;\u003Ca href=\u0022https:\/\/www.cc.gatech.edu\/~badityap\/covid.html\u0022\u003ECovid-19 research endeavors\u003C\/a\u003E.\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003EOf these endeavors, their work with the\u0026nbsp;\u003Ca href=\u0022https:\/\/www.cdc.gov\/\u0022\u003ECenters for Disease Control and Prevention\u003C\/a\u003E\u0026nbsp;(CDC) using deep learning\u0026nbsp;models to forecast Covid-19 spread, such as hospitalizations and mortalities, may be one of the most prominent efforts.\u0026nbsp;These models\u0026rsquo; predictions are currently being used by public officials and healthcare providers across the country to help track and combat the novel coronavirus.\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003E[Related News:\u0026nbsp;\u003C\/strong\u003E\u003Ca href=\u0022https:\/\/www.cc.gatech.edu\/news\/635849\/team-using-deep-learning-forecast-pandemic-us\u0022\u003E\u003Cstrong\u003ETeam Using Deep Learning to Forecast Pandemic in the U.S.]\u003C\/strong\u003E\u003C\/a\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003E[Related News:\u0026nbsp;\u003Ca href=\u0022https:\/\/www.cc.gatech.edu\/news\/637102\/scientists-collaborating-new-data-driven-approach-covid-19-intervention\u0022\u003EScientists Collaborating on New Data-Driven Approach to Covid-19 Intervention\u003C\/a\u003E]\u003C\/strong\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003ENow, the team is expanding their work with the CDC to apply their research to broader challenges including the\u0026nbsp;\u003Ca href=\u0022https:\/\/c3.ai\/c3-ai-covid-19-grand-challenge\/\u0022\u003EC3.ai Covid-19 Grand Challenge\u003C\/a\u003E\u0026nbsp;and the\u0026nbsp;\u003Ca href=\u0022https:\/\/www.symptomchallenge.org\/\u0022\u003EFacebook Covid-19 Symptom Data Challenge\u003C\/a\u003E.\u003C\/p\u003E\r\n\r\n\u003Cp\u003EBoth challenges asked teams to create innovative approaches for enabling new solutions to pandemic response using proprietary data sets.\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026ldquo;We have been exploring data-driven methods for public health broadly, including for disease forecasting. Given that both of these competitions focused on leveraging novel data sources, it seemed like a very good fit for what we were working on,\u0026rdquo; said Prakash.\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026ldquo;But we wanted to take it one step further because we also wanted to bring our flu-forecasting experience into this.\u0026rdquo;\u003C\/p\u003E\r\n\r\n\u003Cp\u003EAccording to Prakash, the team has gained a wealth of knowledge and experience from working on these real-time data competitions.\u003C\/p\u003E\r\n\r\n\u003Cp\u003EHe said, \u0026ldquo;It\u0026rsquo;s one thing to write a nice academic research paper about a clean problem \u0026ndash; but in a real-time pandemic-emerging scenario where you don\u0026rsquo;t know what is going to happen, when there is so much uncertainty, there is so much more to navigate. And fundamentally, we felt we were well-placed to tackle these challenges.\u0026rdquo;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003EPreparing Hospitals for Covid-19 and Flu Season\u003C\/strong\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003EThe C3.ai\u0026nbsp;\u003Ca href=\u0022https:\/\/c3.ai\/c3-ai-announces-covid-19-grand-challenge-winners\/\u0022\u003Eglobal competition\u003C\/a\u003E\u0026nbsp;encouraged research teams to us the C3.ai data lake to drive fundamental change in building state-of-the-art data science methods to enhance Covid-19 response.\u003C\/p\u003E\r\n\r\n\u003Cp\u003EAccording to Prakash and Rodriguez, ILIs and Covid-19 exhibit symptomatic similarities which affect one another\u0026rsquo;s level of reported cases and therefore need to be taken into consideration when addressing disease spread. Given this consideration, they saw the C3.ai challenge as an opportunity to expand on their ILI and Covid-19 research with the new data provided.\u003C\/p\u003E\r\n\r\n\u003Cp\u003ETheir proposed framework,\u0026nbsp;\u003Ca href=\u0022https:\/\/www.cc.gatech.edu\/~acastillo41\/assets\/docs\/survey_slides.pdf\u0022\u003E\u003Cem\u003EDeepOutbreak\u003C\/em\u003E\u003C\/a\u003E\u003Cem\u003E,\u003C\/em\u003E\u0026nbsp;secured second place out of 777 participants by presenting a framework to better inform\u0026nbsp;response strategies using datasets provided by C3.ai. It accomplishes this by\u0026nbsp;modeling the progression of Covid-19 and symptomatically similar co-evolving ILIs to support optimal deployment of healthcare resources.\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026ldquo;Machine learning techniques allow us to directly ingest data signals that may be better representing what is happening on the ground. Our framework is useful in forecasting the spread of both Covid-19 and influenza in the chaotic circumstances we are facing. We found our predictions complement other, more traditional, approaches for epidemic forecasting,\u0026rdquo; said Rodriguez.\u003C\/p\u003E\r\n\r\n\u003Cp\u003EThe DeepOutbreak framework was developed with\u0026nbsp;\u003Cstrong\u003EBijaya Adhikari\u003C\/strong\u003E\u0026nbsp;from the University of Iowa, and\u0026nbsp;\u003Cstrong\u003EAnika Tabassum\u003C\/strong\u003E,\u0026nbsp;\u003Cstrong\u003ENikhil Muralidhar,\u003C\/strong\u003E\u0026nbsp;and\u0026nbsp;\u003Cstrong\u003ENaren Ramakrishnan\u0026nbsp;\u003C\/strong\u003Efrom Virginia Tech. This very same team continued on from the C3.ai challenge to take first place out of 55 organizations for the Facebook Covid-19 Symptom Data Challenge that same week.\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003EPredicting Covid-19 Trends Using Facebook Data\u003C\/strong\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003ESimilar to the C3.ai competition, the Facebook challenge asked teams from across the world to develop a novel analytic approach to enable earlier detection and improved situational awareness of the Covid-19 outbreak using Facebook Covid-19 data.\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003EThe Facebook Covid-19 data was gathered by administering a survey on the social media platform which asked respondents about symptoms.\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026ldquo;As it is well known, Covid-19 and the flu share similar symptoms, like a cough or a fever. So, we wanted to understand if their symptomatic data helps us to differentiate between these diseases because they can interact, have similar symptoms, and can contaminate each other\u0026rsquo;s surveillance systems,\u0026rdquo; said Prakash.\u003C\/p\u003E\r\n\r\n\u003Cp\u003EThe DeepOutbreak team secured a first-place victory in the challenge by characterizing different facets of the utility of the symptom survey data from Facebook.\u0026nbsp;\u003Ca href=\u0022https:\/\/www.youtube.com\/watch?v=0QsuacFnedE\u0022\u003EThey found\u003C\/a\u003E\u0026nbsp;the novel data could help in predictive accuracy and also to\u0026nbsp;anticipate changes in trends in the epidemic curves of both Covid-19 and ILIs.\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003EAs the winner, the team\u0026rsquo;s analytic design will be featured on the\u0026nbsp;\u003Ca href=\u0022https:\/\/dataforgood.fb.com\/\u0022\u003EFacebook Data for Good\u003C\/a\u003E\u0026nbsp;website and partner forums, including blogs and community websites.\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026ldquo;Our data collection pulls from Google, CDC, and other institutions. Complementing these data sets with the Facebook data helped us find these trends,\u0026rdquo; said Rodriguez.\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003EAccording to Rodriguez, the Facebook data helped fill the gap in symptomatic data by it being readily accessible to people who are experiencing symptoms but not going to healthcare providers or taking Covid-19 tests.\u003C\/p\u003E\r\n","summary":null,"format":"limited_html"}],"field_subtitle":"","field_summary":"","field_summary_sentence":[{"value":"Associate Professor Aditya Prakash and Ph.D. student Alexander Rodriguez won two Covid-19 related challenges."}],"uid":"34540","created_gmt":"2021-01-07 15:26:48","changed_gmt":"2021-01-07 15:33:15","author":"Kristen Perez","boilerplate_text":"","field_publication":"","field_article_url":"","dateline":{"date":"2021-01-07T00:00:00-05:00","iso_date":"2021-01-07T00:00:00-05:00","tz":"America\/New_York"},"extras":[],"hg_media":{"642636":{"id":"642636","type":"image","title":"Alex Rodriguez and Aditya Prakash","body":null,"created":"1610032965","gmt_created":"2021-01-07 15:22:45","changed":"1610032965","gmt_changed":"2021-01-07 15:22:45","alt":"Alexander Rodriguez and Aditya Prakash headshots","file":{"fid":"244066","name":"AlexandAditya.jpg","image_path":"\/sites\/default\/files\/images\/AlexandAditya.jpg","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/images\/AlexandAditya.jpg","mime":"image\/jpeg","size":1330445,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/images\/AlexandAditya.jpg?itok=gVyyJPnb"}}},"media_ids":["642636"],"groups":[{"id":"47223","name":"College of Computing"},{"id":"50877","name":"School of Computational Science and Engineering"}],"categories":[],"keywords":[{"id":"4305","name":"cse"},{"id":"276","name":"Awards"},{"id":"92811","name":"data science"},{"id":"186612","name":"Helping Stories"},{"id":"76231","name":"Computational Science and Engineering"}],"core_research_areas":[],"news_room_topics":[],"event_categories":[],"invited_audience":[],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[{"value":"\u003Cp\u003EKristen Perez\u003C\/p\u003E\r\n\r\n\u003Cp\u003ECommunications Officer\u003C\/p\u003E\r\n","format":"limited_html"}],"email":["kristen.perez@cc.gatech.edu"],"slides":[],"orientation":[],"userdata":""}}}