Thanks to a grant from the National Science Foundation, this project will conduct experiments with user communities to determine what motivates them to contribute metadata enhancements to archived data.
The study will carry out predictive analytics (using traditional statistical and machine learning tools) and geospatial analyses, to identify high risk individuals as well as those with identifiable kidney disease, and the geographic areas they live in, to better understand risk and progression factors for kidney disease.
With a grant from the Andrew W. Mellon Foundation, Paul Conway aims to create modularlized learning resources that support standards-based digitization of cultural heritage resources (still image, audio, video).
Creating credentialing infrastructure to enable collaboration, facilitate data reuse, make researchers' credentials more transparent, and make data accessible while respecting the privacy of data users.
The study aims to a) develop a high fidelity acute kidney injury (AKI) risk prediction model for hospitalized Veterans; and b) develop an accompanying clinical decision support system (CDSS) to provide management recommendations for patients identified as being at higher risk for AKI.