1 / 16

Secondary Use of EHR Data (SHARPN)

Secondary Use of EHR Data (SHARPN). Christopher G. Chute, MD DrPH , Mayo Clinic Stan Huff, MD, Intermountain Healthcare Hongfang Liu, Mayo Clinic Guergana Savova , PhD, Harvard Childrens Hospital Boston Jyotishman Pathak , PhD, Mayo Clinic Kent Bailey, PhD, Mayo Clinic

pauline
Download Presentation

Secondary Use of EHR Data (SHARPN)

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. Secondary Use of EHR Data (SHARPN) Christopher G. Chute, MD DrPH, Mayo Clinic Stan Huff, MD, Intermountain Healthcare Hongfang Liu, Mayo Clinic GuerganaSavova, PhD, Harvard Childrens Hospital Boston JyotishmanPathak, PhD, Mayo Clinic Kent Bailey, PhD, Mayo Clinic Marshall Schor, TJ Watson Research Lab IBM Calvin Beebe, Mayo Clinic Office of the National Coordinator for Health Information Technology

  2. Secondary Use of EHR Data (SHARPN) Participating Institutions: • Agilex Technologies • CDISC (Clinical Data Interchange Standards Consortium) • Centerphase Solutions • Deloitte • Group Health, Seattle • IBM Watson Research Labs • University of Utah • University of Pittsburgh • Harvard University • Intermountain Healthcare • Mayo Clinic • Mirth Corporation, Inc. • MIT • MITRE Corp. • Regenstrief Institute, Inc. • SUNY • University of Colorado Office of the National Coordinator for Health Information Technology

  3. Clinical Databases Medical Knowledge Expert Systems From Practice-based Evidenceto Evidence-based Practice Inference Data Registries et al. Comparable and Consistent Standards Patient Encounters Vocabularies & Terminologies Decision support Knowledge Management Clinical Guidelines “Secondary Use” Office of the National Coordinator for Health Information Technology

  4. TheChallenge • Most clinical data in the United States is heterogeneous – non-standard • Within Institutions • Between Institutions • Meaningful Use is mitigating, but has not yet “solved” the problem • Achieving standardization in Meaningful Use is sometimes minimized

  5. Secondary Use of EHR Data (SHARPn) Leverage health informatics to: • generate new knowledge • improve care • address population needs Develop, evaluate, deploy open-source tools for: • Data Normalization (DN) - semantic and syntactic • Natural Language Processing (NLP) of Clinical Text • High-throughput Phenotyping (HTP) from EHR data Office of the National Coordinator for Health Information Technology

  6. Secondary Use of EHR Data (SHARPN) Cross-Integrated Suite of Projects and Products: Office of the National Coordinator for Health Information Technology

  7. ClinicalData Normalization • Data Normalization • Comparable and consistent data is foundational to secondary use • Clinical Data Models – Clinical Element Models (CEMS) • Basis for retaining computable meaning when data is exchanged between heterogeneous computer systems. • Basis for shared computable meaning when clinical data is referenced in decision support logic.

  8. Data Element Harmonization • Stan Huff – CIMI • Clinical Information Model Initiative • http://informatics.mayo.edu/CIMI/ • NHS Clinical Statement • CEN TC251/OpenEHR Archetypes • HL7 Templates • ISO TC215 Detailed Clinical Models • CDISC Common Clinical Elements • Intermountain/GE CEMs CEM Session Jun 11: 8:30AM, RM 414

  9. NormalizationPipelines • Input heterogeneous clinical data • HL7, CDA/CCD, structured feeds • Output Normalized CEMs • Create logical structures within UIMA CAS • Serialize to a persistence layer • SQL, RDF, “PCAST like”, XML • Robust Prototypes exist • Early version production Q3 2012

  10. DataNormalization Target Value Sets Information Models Normalization Targets Intro Session Jun 11: 10:30AM, RM 414 Tooling Raw EMR Data Normalized EMR Data Normalization Process

  11. NaturalLanguage Processing • Information extraction (IE): transformation of unstructured text into structured representations and merging clinical data extracted from free text with structured data • Entity and Event discovery • Relation discovery • Normalization template: Clinical Element Model • Improving the functionality, interoperability, and usability of a clinical NLP system(s) Intro Session Jun 11: 8:30AM, RM 417

  12. NLPDeliverables and Tools Look for several tool Sessions • cTAKES Releases • Smoking Status Classifier • Medication Annotator • Integrated cTAKES(icTAKES) • an effort to improve the usability of cTAKES for end users • NLP evaluation workbench • the dissemination of an NLP algorithm requires performance benchmarking. The evaluation workbench allows NLP investigators and developers to compare and evaluate various NLP algorithms. • SHARPn NLP Common Type • SHARPn NLP Common Type System is an effort for defining common NLP types used in SHARPn; UIMA framework. • cTAKES Side Effects module • Modules for relation extraction

  13. High-Throughput Phenotyping • Phenotype - a set of patient characteristics : • Diagnoses, Procedures • Demographics • Lab Values, Medications • Phenotyping – overload of terms • Originally for research cohorts from EMRs • Obvious extension to clinical trial eligibility • Quality metric Numerators and denominators • Clinical decision support - Trigger criteria Intro Session Jun 11: 1:00PM, RM 414

  14. PhenotypingActivities • DROOLS • Prioritize “Drools-izing” eMERGE algorithms (Diabetes, PAD and Hypothyroidism) and PGRN algorithms • Role of Drools for implementing the quality measures • Phenotyping Workbench / PhenoPortal • develop an implementation independent, phenotyping logic representation template for algorithm design • Role of CEMs and NQF Quality Data Model (QDM) • Publicly accessible Web-based library for phenotyping algorithms • PhenotypingGraphical User Interface or “plug & play” workbench for algorithm design and evaluation • Just-In Time Phenotyping • Apply algorithms as “data sniffers” that can be plugged within an UIMA pipeline • Online, real-time phenotyping (e.g., for clinical decision support) • Machine Learning Phenotyping • leverage machine learning methods for rule/algorithm development, and validate against expert developed ones Tool Session Jun 12: 1:00PM, RM 415

  15. SHARP and Beacon Synergies • SHARP will facilitate the mapping of comparable and consistent data into information and knowledge • SE MN Beacon will facilitate the population-based generation of best evidence and new knowledge • SE MN Beacon will allow the application of Health Information Technology to primary care practice • Informing practice with population-based data • Supporting practice with knowledge 14

  16. SHARPn Journey TOMORROW: Robust Deployment TODAY:Iterative Pilots • tools incorporating national standard data models & value sets • real-world deployment of tools in HIEs and Beacons • open library of phenotyping algorithms for healthcare quality (NQF), clinical decision support & individualized medicine research • software releases • clinical models • data normalization pipelines • phenotyping algorithms • scientific contribution (27publications) Partnerships/Alliances & Adopters Office of the National Coordinator for Health Information Technology

More Related