Greater Plains Collaborative Hackathon PCORNet Act One Russ Waitman, PhD Director of Medical Informatics, Director, Frontiers Biomedical Informatics Assistant Vice Chancellor, Enterprise Analytics Associate Professor, Department of Internal Medicine University of Kansas Medical Center Kansas City, Kansas February 24, 2014 This project is supported in part by NIH grant UL1TR000001 and NSF Award CNS- 1258315
42
Embed
Greater Plains Collaborative Hackathon PCORNet Act One
Greater Plains Collaborative Hackathon PCORNet Act One. This project is supported in part by NIH grant UL1TR000001 and NSF Award CNS - 1258315. Three Analogies, Introductions. Part 1: “ Hooking ” People on Informatics - PowerPoint PPT Presentation
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Greater Plains Collaborative HackathonPCORNet Act One
Bonneville Hatchery: Trout, Salmon, Sturgeon, Columbia River, Oregon
I want to go fishing, not fill a fish tank (REDCap) Use HERON: a managed fishery
• Get a License: Develop business agreements, policies, data use agreements and oversight.
• Get a Fishing Rod and Bass Boat: Implement open source NIH funded (i.e. i2b2 https://www.i2b2.org/) initiatives for accessing data.
• Know what your catching: Transform data into information using the NLM UMLS Metathesaurus as our vocabulary source.– Secondary goal; mostly irrelevant at one site
• Stock Different Tasty Fish: link clinical data sources to enhance their research utility.
Central CTSA Informatics Aim: Create a data “fishing” platform: HERON, https://heron.kumc.edu
• Fill out System Access Agreements to sponsor students/staff• Fill out Data Use Agreement to request data export• No Limit!!! IRB Protocol Not Required to view or pull de-
identified data• Must be on campus or use VPN or https://access.kumed.com • Check http://frontiersresearch.org/frontiers/HERON-Introduction
• Kansas City: a city of contrasts as illustrated by alcohol• Kansas: Carrie Nation, temperance society• Missouri: “Boss” Tom Pendergast, prohibition what?
Part 2, Integrated Data Repositories: “A Cocktail Drinker’s Perspective”
Repurposing i2b2 Clinical Research Infrastructure for Inpatient Quality Improvement
• i2b2 “largely” ambulatory or population/genomics focused • Is i2b2 version 1.6 with same financial encounter and modifiers
now useful for inpatient research and precise attribution?
Initial GPC task is to set up the bar: clear bottles, clean glasses, bartender’s guide, and honest pour• Southern Bible Belt had social clubs where the bottle belonged to
members• Hospital, clinic, university, payor, and patient data
• Reproducible science: clear attribution wrt how data was obtained• i2b2: an open source “clear glass” to transparently hold data• ETL: stage bottles, clear recipes for cocktails into i2b2 glass • Defining site/GPC oversight (HERON as basis) to oversee the pour
Reproducible Research: Modifiers, Concept Paths and sharing ETL code
• Clear attribution likely as important as data standards• Billing, EMR, problem list, administration versus dispense?
• Load with the local terminology first; don’t miss unmapped observations. • Map to standards secondarily in the concept space.• Works around mapping challenges with contributing organizations;
support multiple organizing hierarchies
• Evidence Generation: Trials post Electronic Health Records (EHR)– Learning Healthcare System Institute of Medicine Reports: 2006 onward. – 2011 Report: Digital Infrastructure for the Learning Health System: The
Foundation for Continuous Improvement in Health and Health Care• “Information Technology (IT) serves as the functional engine for the
continuous learning system”• Effective Biomedical Research Organizations will integrate Medical
Informatics and Clinical Research Informatics capabilities with Operational Clinical Systems of the Healthcare Systems– EHR Standardization and collection of data becomes critical to the cost
effective research capacity of the University.– EHRs (Cerner/Epic), clinical research systems like (REDCap/Oncore/Velos),
and ultimately translational bioinformatics systems will need to be managed holistically as opposed to siloed.
Part 3: a Learning Healthcare System
PCORI
CoordinatingCenter
Steering CommitteeScientific Advisory Board
Special Expert Group
CDRN
CDRNCDRN
CDRN
CDRN
CDRN
PPRN
PPRN
PPRN
PPRN
PPRN
PPRN
PPRN
PPRN
PPRN
PPRN
Patient-Centered Outcomes Research InstituteClinical Data Research Network Announcement
component networks: systems-generated and patient driven networks
• Active involvement of health care systems, of clinicians and of patients
• A commitment to establishing inter-operability and data sharing across networks and ready collaboration with the larger research community
What Do They Want the Network to Do?
Joe V. Selby, MD, MPH, Executive Director ONC HITCP June 5, 2013
COOPERATIVE AGREEEMENT AWARD 18 MONTHS LATER
• At least two health care systems engaged• Willingness and capacity to work toward
data standardization with other awardees• Willingness to participate in collaborative
studies with data sharing as part of a national research infrastructure
• > 1,000,000 patients enrolled• Data standardized within network and with
other awardee networks• Patients, system, and clinicians engaged in
governance & use• Capable of implementing clinical trials
Capabilities: • Rich clinical data from electronic health records and other data sources stored in
standardized, interoperable formats. • Capacity to conduct both observational studies and randomized trials embedded in clinical
settings• Rigorous practices for data security and confidentiality• Appropriate IRB and human subjects oversight• Utility for CER, safety studies, surveillance, etiologic research, and potentially for pre-
approval trials
The “Greater Plains Collaborative” Awarded December! Part of pcornet.org
• KS, the University of Kansas Medical Center (KUMC)
• MO, Children’s Mercy Hospital • IA, University of Iowa Healthcare • WI, the University of Wisconsin-
Madison, the Medical College of Wisconsin, and Marshfield Clinic
• MN, the University of Minnesota Medical Center
• NE, the University of Nebraska Medical Center
• TX, the University of Texas Health Sciences Center at San Antonio and the University of Texas Southwestern Medical Center.
• Selected in July to submit full proposal in September, award in December, funding January?– $7 million total costs over 18 months
• Lek: gather in the the Spring on a Booming Ground to attract female Greater Prairie Chickens
• If you dance by yourself, you’re not attracting researchers interested in generalizable results
• GPC: CTSAs create ideal habitat for clinical researchers to come and study our state’s populations and develop methods to improve our communities health outcomes
• Get i2b2 foundation in place so we can next tackle RCT interventions and PROM collection
Greater Plains Collaborative Objective
• 11.8 Million Covered Lives• 13 hospitals, 430 clinics, 1800
primary care providers, 7600 specialists
• Establish Governance• Measure EHR Meaningful Use
standardization and align for 3 use cases:– Breast Cancer– ALS (Lou Gerhig’s Disease)– Obesity (Pediatric Inpatient Focus)
• Develop Comparative Effectiveness Research Trial infrastructure embedded in EHRs
• Enhance Patient Recruitment• Support Biospecimen Requests
The “Greater Plains Collaborative”Size, Goals, Structure
Goal: lifetime data density; data standardization and interoperability between systems and networks
Figure 3.1. Comprehensive and complete data example from KUMC: heat map of percentage of proposed data elements from the HER and billing sources recorded in six month intervals surrounding the data of breast cancer diagnosis specified by the hospital tumor registry.
Introductions, what you hope to get out of Hackathon (needs may vary)