1 / 46

SMART Platform and API for Clinical Genomic Apps

SMART Platform and API for Clinical Genomic Apps. Gil Alterovitz Director, Biomedical Cybernetics Laboratory Assistant Professor, Harvard Medical School. http ://genomics-advisor.smartplatforms.org:4000/. Vendor-specific apps: calendar, calculator, etc.

radha
Download Presentation

SMART Platform and API for Clinical Genomic Apps

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. SMART Platform and API for ClinicalGenomicApps Gil Alterovitz Director, Biomedical Cybernetics Laboratory Assistant Professor, Harvard Medical School

  2. http://genomics-advisor.smartplatforms.org:4000/

  3. Vendor-specific apps: calendar, calculator, etc. Apps did not work with other systems and did not evolve much over time. No long-tail/custom applications- e.g. family history app Independent apps Developer and user community is engaged Long-tail apps available

  4. Plug doesnot fit

  5. Issues in Communicating Genetic Information • No simple standard API (Application Programming Interface) • Contents are essentially the same • Sequences (ATGC..) and genetic files • But, data are structured differently • Different approaches of authentication

  6. SMART Provides a Solution • Substitutability Medical Applications Reuseable Technology • Simple design of API • Geared toward developers and users • Integration with clinical data

  7. Three Crystallizing Events eMERGE Network (Electronic Medical Records and Genomics) SMART Platform (Substitutable Medical Apps Reusable Technology) CCDA/MU 2.0 (Consolidated Clinical Document Architecture/Meaningful Use 2.0)

  8. eMERGE Network Electronic Medical Records and Genomics (eMERGE)

  9. What is SMART? • Substitutable Medical Apps Reusable Technology • Accelerate medical application innovation and research • Develop medical app community • Remove developer roadblocks

  10. Substitutability = Re-Use Got Statins? BP Centiles CardiacRisk SMART - AMIA 2012 - 04Nov2012 SMART-Enabled PCHR SMART-Enabled HIE SMART-Enabled EMR

  11. Substitutable Apps Needs API Resource oriented, everything a URL Data Model Context (container, user, patient) Medical (problems, allergies, …) Authentication Consistent delegation, web standards (OAuth) UI Standards-based integration (HTML5) SMART - AMIA 2012 - 04Nov2012

  12. App Platform

  13. SMART-Enabling i2b2 Add: SMART cell Mapper cell Patient-Centric View app Patient-Centric View App i2b2 Hive SMART Cell CRC Mapper Cell Ontology Any SMART App SMART - AMIA 2012 - 04Nov2012

  14. Boston Children’s Hospital Cerner EMR 16 Months SMART - AMIA 2012 - 04Nov2012

  15. SMART Genomics API • Enables integration of genomic data fromheterogeneous sources • Enables integration of clinical and genomic data • Re-usability eliminates developer barriers • Promotes the use of genetic data for research

  16. SMART Genomics Platform

  17. SMART Genomics Advisor App Integration 24Oct2012 Pop-Up→ Top-Level Genomics Advisor Displays

  18. SMART Genomics Advisor App Integration 24Oct2012 Genomics Advisor: Detailed Pop-Up

  19. SMART - AMIA 2012 - 04Nov2012

  20. Problem: High cost of chronic disease management and issues with long-term patient compliance in diabetes, especially in pediatric cases. Solution: Increase compliance by integrating toy bear from Sproutelwith SMART EMR for physicians and to provide parent/child feedback. Details: Integrated bear with the Telecare glucose meter / pump technology to provide clinical data to SMART EMR* Provides kids with a “fun” way to measure glucose and take insulin. Provide live data for clinicians/patients to view. * Interactive bear avatargives feedback to patients. * Engages patients to increases their likelihood to comply with their diabetes treatment. Example App: Dbear SMART EMR

  21. iPad Apps

  22. DB EMRFirst program to integrate genomic, device, EMR/Personal Health Record information. First program to integrate patient, patient devices (e.g. bear/glucose meter), care giver, and physician data into a unified view to facilitate collaboration on patient care. First mobile app to integrate genomics/sequence information and clinical information.

  23. What is FHIR FHIR is an API that allows for exchange of health records Resources are exchanged using XMLs and JSON, for ease of parsing, and ease of implementation Enables document sharing, and documents can be stored on the server It is a draft specification undergoing development, and will ballot as a full HL7 Standard

  24. Why Integrate into FHIR • Faster adoption • It is easier for developers to handle XMLs and JSON without a incorporating a whole suit of libraries • Open source, extensible API • To create a more complete standard • FHIR is developing for medical record exchange, and lack model representations for clinical genomics

  25. SMART FHIR Resource Examples New resources to add to FHIR, with automatically generated graphs, documentation, XML and JSON objects, and backend C# and Java for server

  26. SMART FHIR Resource Examples

  27. SMART FHIR Resource Examples These newly created resources easily integrates into the existing FHIR framework

  28. Integrating DAM to FHIR Resources Translates rather smoothly Speeds up the information transfer between the DAM Stakeholder Groups

  29. Example - DAM DAM’s object model of elements contained within the genetic results message

  30. Example - FHIR

  31. Example - FHIR

  32. Example - FHIR Automatically generated XML and JSON templates created along with example objects Automatically generated C# and Java for server Automatically created documentation

  33. Acknowledgements Rachel Ramoni, David Kreda, Josh Mandel, Isaac Kohane, Tom Chen, Jason Evans, Jenny Cheng, Ziou Zheng, Yao Chen, Yidan Pan, Karen Xin Office of National Coordinator Grant: - Strategic Health IT Advanced Research Project (Kohane) NIH Grants: - 5R21DA025168-02 (G. Alterovitz) - 1R01HG004836-01 (G. Alterovitz) - 4R00LM009826-03 (G. Alterovitz) Email Contact: gil@mit.edu

More Related