MMFP-Tableau: enabling precision mitochondrial medicine through integration, visualization, and analytics of clinical and research health system electronic data

Objective To describe a novel data integration workflow developed to automate clinical and research electronic health system data integration and harmonization from siloed sources for centralized access, visualization and analysis by clinicians and researchers in an end user-friendly customized analytic platform. Materials and Methods A centralized, semi-automated framework provides data provenance and user access to integrated data sources. Data models are implemented leveraging a centralized server (Alteryx) for high-level analytics including scheduling, integration, and modeling. Data are then sent to a secure Tableau instance for end-user visualization and interaction, with minimal software development required. Results MMFP-Tableau, named for its origin in the Mitochondrial Medicine Frontier Program (MMFP) at the Children’s Hospital of Philadelphia (CHOP), has advanced efforts to realize precision medicine by facilitating expert clinician and researcher end-user direct access to integrated, highly robust health system datasets. This scalable data solution enables translational researchers to link subject and cohort clinical and research parameters with research samples; enhances external biopharma collaborations for clinical trial design, subject recruitment, and data tracking; accelerates retrospective clinical cohort data analysis; and improves complex data visualization for clinicians and researchers. Discussion MMFP-Tableau promotes complex data integration, visibility, and advanced analytic capabilities to facilitate seamless multidisciplinary research, benefitting clinical care and research in rare disease patients and cohorts. Conclusion The MMFP-Tableau data platform integrates multiple data sources across various siloed data platforms to transform complex data into readily accessible datasets. This approach represents a generalizable workflow concept readily adaptable to implement across diverse fields of medicine. Lay Summary A wealth of healthcare information is collected on patients as part of their clinical care management and clinical research engagement. As this information often exists across disconnected data platforms, a major healthcare system challenge is how to integrate diverse data types in an effective manner that allows clinicians and researchers to visualize data, draw conclusions, and apply learnings from individual patients and across patient cohorts to meaningfully inform clinical care management and research developments.