OHDSI Home | Forums | Wiki | Github

Pediatric COVID-19 Outcome Prediction Challenge

I thought this might be of interest to the Covid-19 predictive modelers in the community:

“Are you or someone you know able to develop machine learning/AI algorithms (computational models) that can predict which pediatric COVID-19 patients are likely to develop severe illness and complications, including conditions such as multi-system inflammatory syndrome in children (MIS-C)? Then check out the Pediatric COVID-19 Data challenge!

Challenge participants will be asked to develop, train, and validate computational models to predict pediatric patients at risk for hospitalization, need for ventilation, and cardiovascular interventions utilizing de-identified electronic health record data available through NCATS’ National COVID Cohort Collaborative (N3C) Data Enclave. Round 1 starts on September 15 and registration requires data use agreements and online training, so we recommend that you get started as soon as possible.

While most children with COVID-19 are asymptomatic or have mild symptoms, healthcare providers have difficulty determining which of these children will develop severe COVID-19 complications early in the progression. Some children even develop multisystem inflammatory syndrome in children (MIS-C), a life-threatening inflammation of organs and tissues, unless appropriate and timely interventions occur.

The winning computational models should accurately predict which pediatric patients are at risk for severe COVID-19 complications and be clinically useful.

The challenge is sponsored by the Biomedical Advanced Research and Development Authority (BARDA), and includes partnerships with two National Institutes of Health institutes - the National Center for Advancing Translational Sciences (NCATS) and the National Institute of Child Health and Human Development (NICHD) – and the Health Resources & Services Administration (HRSA) Maternal & Child Health Bureau (MCHB). The challenge will be administered by Sage Bionetworks.

The total cash prize purse is $200,000, split among up to three winners. Winners may also be eligible to apply for follow-on support from BARDA for further technology development and clinical evaluation.

Information about the challenge is available on challenge is available at Pediatric COVID-19 Data Challenge | Challenge.gov