Clinical Research Informatics Training for Investigators Combining Applied Laboratories and Synthetic Internet-based Data Environments (CRITICAL SIDE) will enable Clinical and Translational Science Hubs to overcome the translational training barriers hindering Integrated Data Repository (IDR) adoption by educating investigators to a) understand regulatory and institutional concerns, b) gain familiarity with electronic health records (EHR) and clinically sources, c) gain confidence in the processes populating IDRs from underlying EHRs, and d) acquire skills to develop analysis ready datasets from heterogeneous data represented in IDRs.
Aim 1: Training in Applied Laboratories: Modeled after software carpentry workshops, we will deploy workshops where attendees specify their own research cohort using fully de-identified data, develop their analytical pipeline creating an analysis ready dataset, and conduct preliminary analysis based upon REDCap and SQL extracts from i2b2-based IDRs. CTSA Hub Participating investigators may use the workshop's data to catalyze their research project and attendees will also include other CTSA Hubs' informatics team in a "train the trainer" model to scale this approach across CTSA Hubs.
Aim 2: Create Synthetic Clinical Data: We will develop large, synthetic data for EHR and clinical registries analogous to synthetic data (DE-SynPUF) recently created by the Centers for Medicare and Medicaid Services (CMS) to support entrepreneurial and health systems research training in analyzing claims data.
Aim 3: Deploy a Synthetic Integrated Data Repository: We will deploy and support access to a synthetic i2b2-based IDR that will incorporate both synthetic claims data (DE-SynPUF) from CMS and the synthetic clinical data developed in Aim 2.
Aim 4: Online Training Supported by Open Data: We will develop online educational materials based upon the Applied Laboratory workshops curriculum development to provide didactic background materials for investigators attending CTSA Hub workshops. Complementary exercises will be designed to serve as approachable steps for investigators to acquire and test their informatics and data science competency. These datasets and exercises will also serve as quality assurance and quality control use cases for informatics teams developing CTSA IDRs.
Through these four aims, the CRITICAL SIDE initiative will address underappreciated translational training barriers to creating informatics conversant investigative teams that can fully exploit our nation's significant data infrastructure created through local, NCATS, and PCORI research investments as well as the much larger national investment in Meaningful Use compliant clinical systems.
Other Information: