Data Analysis, New Knowledge, and then What? Perspectives on Mobilizing Computable Biomedical Knowledge Rachel Richesson, Duke University Allen Flynn, University of Michigan Chris Dymek, AHRQ Gerald Perry, University of Arizona #MobilizeCBK
Panelists #MobilizeCBK Rachel Richesson, PhD, MPH, Duke University @rrichesson MCBK Steering Committee Allen Flynn, PharmD, PhD, University of Michigan MCBK Standards Workgroup Chris Dymek, EdD, Agency for Healthcare Research and Quality MCBK Sustainability for Mobilization and Inclusion Workgroup Gerald (Jerry) Perry, MLS, University of Arizona MCBK Sustainability for Mobilization and Inclusion Workgroup
The Triple Aim… Better Better Health Care Lower … Cost Knowledge Information Data
Better Health Requires This
Not Just This Journals
Knowledge to Practice
Knowledge should be FAIR* Metadata • F indable Libraries • A ccessible Data standards • I nteroperable • R eusable • Descriptive attributes • Provenance • Licensing info. • Implementation guidance • Performance Data • Monitoring *FAIR: https://www.force11.org/group/fairgroup/fairprinciples
Vol. 366(6464):447-453 October 25, 2019
Impact of Bias and Missing Data Knowledge is inappropriate • Incomplete data or harmful for some patients • Under-representation of populations • Misclassification • Measurement errors Interventions propagate • Missing data for certain disparity… groups Some groups denied access to procedures; or receive inappropriate care These patients do worse Data not captured on some groups
“FAIRness” Enables Innovation Research, discovery, Data generation of evidence Knowledge Applications/Action -- targeted, personalized, useful, usable, …
Mobilizing Computable Biomedical Knowledge (MCBK): A multi-stakeholder movement Mission and Vision: A Manifesto Interim Home: The University of Michigan Governance: Steering Committee Activities to Date: Public meetings (2018, 2019) Four workgroups Web resources Webinars National and global collaborations (connections to Learning Health Systems initiatives and communities)
MCBK Manifesto www.MobilizeCBK.org
Highlights of MCBK Mission and Vision It is no longer sufficient to represent knowledge only in words and pictures Decisions should be informed by the best available knowledge MCBK is committed to making use of knowledge to improve health MCBK is committed to upholding the integrity, reliability, and validity of computable knowledge MCBK is committed to open, transparent, equitable, and inclusive approaches to making computable knowledge FAIR
MCBK Workgroups and Co-Chairs Standards for MCBK Robert Greenes and Bruce Bray Technical Infrastructure for MCBK Leslie McIntosh and Chris Shaffer Policy and Coordination to Ensure Quality and Trust Jodyn Platt and Blackford Middleton Sustainability for Mobilization and Inclusion Chris Dymek and Gerald (Jerry) Perry Steering Committee : Julia Adler-Milstein, Bruce Bray, Milton Corn, Chris Dymek, Peter Embi, Charles Friedman, Bob Greenes, Stan Huff, Dipak Kalra, Nancy Lorenzi, Leslie McIntosh, Blackford Middleton, Mark Musen, Jodyn Platt, Jerry Perry, Rachel Richesson, Chris Shaffer, Umberto Tachinardi, John Wilbanks
2nd Public Meeting – July 2019 July 18-19, 2019 Natcher Conference Center National Institutes of Health 190+ registrants 160+ participants 24 posters 17 technical demonstrations 4 workgroup sessions 17
#MobilizeCBK www.MobilizeCBK.org
Panelists and Topics • Allen Flynn , PharmD, PhD, Univ. of Michigan CBK Artifact Lifecycle • MCBK Standards Workgroup • Chris Dymek , EdD, Agency for Healthcare AHRQ experience Research and Quality with CDS & CBK • MCBK Sustainability for Mobilization and Inclusion Workgroup • Jerry Perry , MLS, University of Arizona CBK as Scholarly Communication • MCBK Sustainability for Mobilization and Inclusion Workgroup • Questions and Discussion
CBK A RTIFACT L IFECYCLE Allen Flynn, University of Michigan PART of PANEL: Data Analysis, New Knowledge, and then What? Perspectives on Mobilizing Computable Biomedical Knowledge
What is a CBK artifact? A single instance of machine-executable knowledge packaged for use GENERAL EXAMPLES An implementation of a machine-learning algorithm with documentation in a ZIP file A computable guideline with user instructions available in an online repository A software container with a set of production rules and a rules engine to execute them A risk model implemented in a text file using a high-level programming language In the sense of 1s and 0s, these things can be seen as “data”, but in the MCBK movement we consider their meaning as computable knowledge
What is a lifecycle? A series of changes in form that unfold over time, returning to a starting state An array of ordered steps spanning the life of some thing A repeating cycle of birth, life, and death
CBK Artifact Lifecycle in 9 Segments Objective: Mobilize CBK artifacts by turning them into shareable, safe, and effective computable knowledge products
1. Create a CBK Artifact DATA Computable Knowledge Evidence Recommendations Rules SCIENTIFIC WORK TECHNICAL WORK
To what degrees do the 2. Validate a CBK Artifact logic and related outputs of a CBK artifact have … face validity? content validity? criterion validity? construct validity? statistical validity? external validity? SCIENTIFIC WORK
3. Harden & Optimize a CBK Artifact HARDEN Original Fail-safe + Robust OPTIMIZE Original Highly performant TECHNICAL WORK
4. Test & Certify a CBK Artifact CBK Artifact Test/Certify (Review) Certified & Badged SCIENTIFIC WORK TECHNICAL WORK
5. Localize & Calibrate a CBK Artifact Certified Artifact Localize & Calibrate Useful OPERATIONAL WORK SCIENTIFIC WORK TECHNICAL WORK
6. Deploy a CBK Artifact Useful Artifact Made to Run Locally TECHNICAL WORK
7. Integrate a CBK Artifact Useful Artifact that Runs Connected to a source of input DATA and a target for output DATA TECHNICAL WORK
8. Use & Evaluate a CBK Artifact Use Operational CBK Impact DATA Implement in Practice OPERATIONAL WORK SCIENTIFIC WORK
9. Withdraw a CBK Artifact Use Not in Use Anymore OPERATIONAL WORK SCIENTIFIC WORK
Examples of Real CBK Artifacts • Computable guidelines > Pharmacogenomic guidelines > Preventive medical service guidelines > Vaccination schedule guidelines • Computable risk scores > Surgery risk score > Lung cancer diagnosis risk score THESE LIFE CYCLES CAN UNFOLD IN BROAD CONTEXTS > Cardiovascular disease risk score THE GO BEYOND THE SCOPE OF A SINGLE ORGANIZATION. • Computable complexity scores > Medication-regimen complexity score
Various Uses for CBK Artifacts • Clinical decision support • Biomedical research and discovery • Population and public health analyses and science • Education of health stakeholders, including all providers CBK ARTIFACTS GET USED FOR A WIDE VARITEY OF PURPOSES. • Engineering work to make better CBK artifacts
Bringing Computable Knowledge to the Point of Care Chris Dymek, EdD Director, Digital Healthcare Research Division Health Datapalooza February 10, 2020
Agenda • Background ► AHRQ ► Digital Healthcare Research ► Vision for the Future • A Focus on Clinical Decision Support (CDS) • Learnings from AHRQ’s CDS Efforts to date • Related Efforts • MCBK and Sustainability
AHRQ Mission To produce evidence to make health care safer, higher quality, more accessible, equitable, and affordable, and to work within HHS and with other partners to make sure that the evidence is understood and used 37
Digital Healthcare Research How can the various components of the ever evolving digital healthcare ecosystem best come together to positively affect healthcare quality, safety and effectiveness? https://digital.ahrq.gov/
Vision for the Future • Clinical & Contextual My Data • Patient- generated • Guidelines Current • Relevant Biomedical research Knowledge findings 39
Vision for the Future • Clinical & Contextual My Data • Patient- Needs to be generated computable and FAIR! • Guidelines Current • Relevant Biomedical research Knowledge findings 40
Recommend
More recommend
