In this session, we will demonstrate how you can build a query to quickly obtain a "synthetic" dataset similar to one described in a peer-reviewed publication, without IRB approval. The dataset can be obtained without IRB approval because synthetic data do not contain PHI so their use is not classified as human subject research. The publication used for this demonstration will be:
Guo A, Mazumder NR, Ladner DP, Foraker RE. (2021). Predicting mortality among patients with liver cirrhosis in electronic health records with machine learning. PLoS ONE 16(8): e0256428. https://doi.org/10.1371/journal.pone.0256428.
MDClone is a new campus resource from the Institute for Informatics' (I2) Center for Population Health Informatics. MDClone is a free, secure, self-service platform for building queries and downloading computationally derived ("synthetic") data from the I2 Research Data Core (RDC).
If you do not already have access to MDClone please complete the I2 Request Help or Services Survey.
Please email Chris Sorensen at sorensenc@wustl.edu if you have questions about this session.
United States