The Center of Excellence for Mobile Sensor Data-to-Knowledge (MD2K) will generate generalizable methods, tools, and software, to address major barriers to processing complex mobile sensor data and use it for biomedical discovery. It will develop and implement a standards-based, interoperable, extensible and open-source big data software platform for efficient implementation of MD2K data analytics, and make it freely available for use by the scientific community. The MD2K Center will demonstrate the feasibility, utility, and generalizability of the MD2K approach by implementing the entire MD2K data analytics system in the context of two biomedical applications - reducing relapse among abstinent daily smokers and reducing readmission among congestive heart failure (CHF) patients. While other ongoing efforts have resulted in significant progress in standards and procedures for data and analytics integration in the areas of genomics, imaging, and EHR, mobile health is a young discipline where there is a tremendous opportunity to establish common procedures, and standards, and to minimize the data fragmentation common to more established data systems like EHRs. The Consortium Core will lead the standardization and outreach activities for MD2K data types and analytics tools, and its integration with those developed by other Centers for data types such as genomics, imaging, and EHRs. It will convene BD2K consortium members to jointly define and prioritize the development and standardization work to have greatest impact on consortium research. It will disseminate specific mobile sensor data streams and modular analytics developed within MD2K Center to other consortium members to evaluate and integrate MD2K in their biomedical applications. It will enable consortium members to incorporate data streams and modular analytics into the MD2K platform using the Open mHealth architecture and open source software to expand the impact of BD2K consortium. Finally, it will integrate MD2K with clinical data streams by by making relevant patient clinical data importable from EHRs, and making clinically-relevant data and insights derived from mHealth sensor data streams exportable back to EHRs.
Showing the most recent 10 out of 108 publications