Challenge Seeks Machine Learning Models to Predict COVID-19-Related Health Outcomes in Veterans
The U.S. veteran population has a higher prevalence than the general population of several of the known risk factors for severe COVID-19 illness, including advanced age, heart disease and diabetes. The Veterans Health Administration (VHA) Innovation Ecosystem has launched a COVID-19 Risk Factor Modeling Challenge to develop and evaluate computational models to predict COVID-19-related health outcomes in veterans.
The VHA noted that identifying and improving our understanding of the risk and protective factors for severe COVID-19 illness is crucial to better protect, triage, and treat at-risk individuals, and additional research is needed to better understand the impact these factors have on high-risk individuals. The VHA Innovation Ecosystem is calling upon the public to use the precisionFDA platform and synthetic veteran health records to develop machine learning and artificial intelligence models to predict health outcomes. The challenge submission period opens on June 2 and closes on July 3.
PrecisionFDA is described as providing the genomics community with a secure, cloud-based platform where participants can access and share data sets, analysis pipelines, and bioinformatics tools, in order to benchmark their approaches and advance regulatory science.
The U.S. Department of Veterans Affairs (VA) said it has implemented several measures in response to the pandemic to protect and care for veterans, including developing a COVID-19 response plan, administering more than 165,000 COVID-19 tests, implementing outreach, screening, and protective procedures to prevent transmission, and supporting non-VA healthcare facilities.
The challenge is calling upon the public to develop machine learning and AI models to predict COVID-19 related health outcomes, including COVID-19 status, length of hospitalization, and mortality, using synthetic health record data. Through this challenge, additional risk and protective factors will be investigated, including therapeutics prescribed for preexisting comorbidities, and treatment interactions.
Challenge participants are presented with a training data set and a test data set consisting of synthetic veteran patient health records. Participants will develop computational algorithms to model the risk of SARS-CoV-2 infection and severe outcomes of COVID-19 illness in the veteran population. The model will be used to predict COVID-19 status, days hospitalized, days in the ICU, controlled ventilation status, and mortality for each synthetic veteran in the test data set. The VHA is encouraging participants to use demographic data and the presence of comorbidities when developing their model to help precisionFDA and the VHA Innovation Ecosystem better understand how race, ethnicity, age, and comorbidities can affect the progression of COVID-19.
Selected participants will be publicly recognized and invited to contribute to a scientific manuscript describing the challenge and results. Selected participants may also have opportunities to present at a conference and continue solution development with the VHA Innovation Ecosystem.
