Confirmed cases data consists of accumulated covid19 cases, including confirmed and suspected, at 9 counties in Greater Houston between 03/01/2020 and 09/06/2020. In addition, longitude, latitude, and FIPS are provided, which may serve as foreign keys to query mask survey data.
\n\nDeceased data consists of accumulated deceased cases at 9 counties in Greater Houston between 03/01/2020 and 09/06/2020. In addition, longitude, latitude, and FIPS are provided, which may serve as foreign keys to query mask survey data.
\n\nCOVID-19 mask usage survey conducted by The New York Times to estimate the mask usage by county in the United States. Data comes from over 250,000 online interviews between 07/02/2020 and 07/14/2020. Specifically, each interview involves how often the participant wears a mask publicly when he or she expects to be within six feet of another person.
\n\nThe hospitalization data in TX includes total general beds in use, including Covid19 and other types of patients, Covid19 patients in general bed, including confirmed and suspected, ICU Covid19 patients, and total hospital patients census at 8 counties (except Waller county) in greater Houston area.
\n\nFIPS data is used to check county code and population. It’s in a single csv file.
\n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Description", "content": "The COVID-19 Houston Datathon is an online challenge to predict the regional hospitalization and mortality patterns of COVID-19 in Houston, Texas. This Datathon is jointly organized and sponsored by the Center for Secure Artificial intelligence For hEalthcare at the UTHealth School of Biomedical Informatics, and Data to Knowledge lab at Rice University. Undergraduate, master, and doctoral students from the institutes within the Gulf Coast Consortia (including UTHealth, MDACC, UH, Rice, TAMU, UTMB, IBT, and Baylor) and colleges near TMC are highly encouraged to apply.
**The event will have up to $1,500 in prizes for the winners. This is an individual-based event (no team participation).**\n\nThe goal is to develop a prediction model using local county-level data to estimate the changes in Covid19 hospitalization (general beds + icu beds) and mortality case numbers in the greater Houston area encompassing 8 counties (Harris, Fort Bend, Montgomery, Brazoria, Galveston, Liberty, Chambers, and Austin) in the state of Texas, USA.
\n\nAccurate and timely prediction of local trends for pandemics will have profound implications to medical resource preparation and policy adjustment evaluation. In this Datathon, we will focus on predicting daily hospitalization cases and cumulative mortality cases based on previous observations. We will provide daily hospitalization and mortality statistics (together with infection cases, recovery cases, active cases, test cases) for eight counties (Harris, Fort Bend, Montgomery, Brazoria, Galveston, Liberty, Chambers, and Austin) in Texas. In addition, we will provide data related to population mobility, demographics, mask usage, which might contain features related to behavioral patterns affecting the transmission.
\n\n\n\nData will be updated daily until end of the competition.
\n- County-level mortality, infection, recovery, active cases, test counts, hospitalization: John Hopkins COVID-19 tracking data, USA Today, and Setrac Regional Healthcare\n- County-level mask usage: New York time\n- County-level population mobility: Google Mobility Report\n- County-level data dashboard: School of Public Health, UTHealth\n- (optional) COVID-19 Control Policies KFF\n- (optional) Demonstration and protest\n- (optional) Weather\n\nFor detailed data description and link of optional data, please refer to:
[SBMI Datathon Dashboard](https://sbmi.uth.edu/datathon/index.htm)\n\n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Performance Evaluation", "content": "\n\nThe Datathon will involve two rounds of competition; one for each week after 09/07/2020. The participants will have 2 weeks to prepare and fine-tune their model.
\n\nIn the first round, the evaluation will use data between 09/07/2020(beginning of the competition) and 09/13/2020 (2 weeks after the start) and top candidates’ performance will be published on a dashboard. Participants should only use data on or before 09/06/2020 to predict the incoming week.
\n\nIn the second round, participants can update their model and incorporate data from the first period to make predictions for the next week (09/14/2020 - 09/20/2020). Similarly, participants should only use data on or before 09/14/2020. The submitted solutions will be evaluated based on the ranking score (elaborated in the next section).
\n\n| Phase | Timeline |\n| --- | --- |\n| Model preparation |08/25/2020 - 09/06/2020 |\n|Round 1 evaluation|\t09/07/2020 - 09/13/2020|\n|Round 2 evaluation|09/14/2020 - 09/20/2020|\n\nWe will use mean squared logarithmic error (MSLE) of hospitalization and deceased case prediction to evaluate the performance of submitted models on each county. Final scores will be evaluated based on the sum of ranking (10 to 1 points for ranking 1 to 10) regarding MSLE in each county. The scores at 8 counties (Harris, Fort Bend, Montgomery, Brazoria, Galveston, Liberty, Chambers, and Austin) will be calculated for final ranking, since Waller county maintains missing data issue, currently we do not consider Waller county. We will provide evaluation codes.
\n\nMSLE stands for the mean over the observed data of the squared differences between the log-transformed true and predicted values, or writing as a formula:
\n\n\\[ MSLE(y,\\hat{y}) = \\frac{1}{N} \\sum_{i=0}^{N} ((log(H_i +1) - log(\\hat{H}_i +1))^2 + (log(D_i +1) - log(\\hat{D}_i +1))^2) \\]
\n\nIn case of there is a tire in the leaderboard, we will apply a secondary evaluation metric -- mean squared error (MSE) of hospitalization and deceased case prediction.
\n\nMSE stands for the mean over the observed data of the squared differences between the targets and predicted values, or writing as a formula:
\n\n\\[ MSE(y,\\hat{y}) = \\frac{1}{N} \\sum_{i=0}^{N} ((H_i - \\hat{H}_i )^2 + (D_i - \\hat{D}_i)^2) \\]
\n\n\nIn each competition round, participants are asked to provide 8 counties' (Harris, Fort Bend, Montgomery, Brazoria, Galveston, Liberty, Chambers, and Austin) predictive hospitalization and mortality cases for the next 7 days (56 rows in total, except header). The test/submission file format is identical in both competition rounds.
\n\nFor hospitalization (Covid19 general beds + Covid19 ICU) prediction, we would like to receive daily active cases, like the training data format. And for mortality, we would like to receive cumulative Covid19 death counts, like the training data format.
\n\nParticipants can make predictions with any computational method(s). Test data contains an ID date column with format (county_name+date), a hospitalization column, and a mortality column that we’d like to compute the error. Note that the ID column is necessary as it decides how to match submission results and actual data. The default hospitalization and mortality values in the file are all set as 0. It is a .csv file (test.csv) with the format below:\n
\n\n\n\nInvolving eight counties (i.e. Harris, Fort Bend, Montgomery, Brazoria, Galveston, Liberty, Chambers, and Austin) in Texas, the submission file should be saved as one csv file (submissions.csv) with format below:
\n\n\n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "rules", "content": "\n - Participants are asked to submit source codes (e.g., Jupyter Notebook as a kernel) in a self-contained way.\n - Use of external data is encouraged, and the goal is predicting future trends.\n - Top contestants are asked to prepare summary slides to describe their models at the end of the Datathon and make a presentation to other contestants in a virtual session.", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "How To Participate", "content": "- Participants are asked to submit source codes (e.g., Jupyter Notebook as a kernel) in a self-contained way.\n- Use of external data is encouraged, and the goal is predicting future trends.\n- Top contestants are asked to prepare summary slides to describe their models at the end of the Datathon and make a presentation to other contestants in a virtual session.\n\nA total of $1,500
\n- First place: $500\n- Second place: $300\n- Third Place: $200\n\nInstitution Specific Prizes:
\n- Top Rice Student: $250\n- Top UTHealth Student: $250\n\nPlease refer to:
[SBMI Datathon Dashboard](https://sbmi.uth.edu/datathon/index.htm)", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false } ] }