1 / 50

Clinical research and the electronic medical record: Interdisciplinary research agendas

Clinical research and the electronic medical record: Interdisciplinary research agendas. Michael G. Kahn MD, PhD Biomedical Informatics Core Director Colorado Clinical and Translational Sciences Institute (CCTSI) Professor , Department of Pediatrics University of Colorado

elise
Download Presentation

Clinical research and the electronic medical record: Interdisciplinary research agendas

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. Clinical research and the electronic medical record: Interdisciplinary research agendas Michael G. Kahn MD, PhD Biomedical Informatics Core Director Colorado Clinical and Translational Sciences Institute (CCTSI) Professor, Department of Pediatrics University of Colorado Director, Clinical Informatics The Children’s Hospital, Denver Michael.Kahn@ucdenver.edu

  2. T1 Biomedical Research Investigator Initiated T1  T2 Translational Research Industry Sponsored Commercialization Basic Research Data Pilot Studies New Research Questions Study Setup Study Design & Approval Outcomes Research Clinical Practice Clinical Trial Data Recruitment & Enrollment Evidence-based Patient Care and Policy EMR Data Submission & Reporting Evidence-based Review Study Execution Required Data Sharing Outcomes Reporting Public Information A Lifecycle View of Clinical Research

  3. The Promise of the Electronic Medical Record • Merging prospective clinical research & evidence-based clinical care • A “front-end” focus • Improving care one patient at a time (decision support) • Merging clinical care and clinical research data collection • Clinically rich database for retrospective clinical research • A “back-end” focus • Making discoveries across populations of patients • Improving care at the population / policy level

  4. Grand Vision: Any clinical investigator can “belly up to the bar” for research-quality data

  5. The Tale of A Trivial Data Request • The original data request: “For an upcoming grant application, how many patients were seen recently with neurofibromatosis-1 (NF-1) and scoliosis?” • “Recently seen” = an encounter of any type since 1/1/2008 • NF-1: ICD-9 code starts with “237.7” • Scoliosis: ICD-9 code starts with “737.3” • Result: N=15

  6. N(Pt) Dx1 = NF-1 Encounter Dx2 = Scoliosis 1/1/2008 - today The Tale of A Simple Data Query • Drilling down: • This query required both diagnoses to be coded on the same encounter (event).

  7. N(Pt) Dx1 = NF-1 Encounter Encounter Dx2 = Scoliosis 1/1/2008 - today The Tale of A Simple Data Query • Second query: • NF-1 and Scoliosis diagnoses can be coded on different encounters, both within time window • N= 28

  8. N(Pt) Dx1 = NF-1 Encounter Encounter Dx2 = Scoliosis 1/1/2008 - today The Tale of A Simple Data Query • Investigator still did not like the answer: • NF-1 is a life-long genetic illness • Scoliosis develops as a complication. • Therefore: NF-1 diagnosis at any time Only scoliosis need to be “recently seen” • N= 47

  9. One Question  Three temporal structures Three different answers N = 15 N = 28 N = 47

  10. Days(Antibiotics) Abx Start Abx Stop CRP test No Abx 2+ days 2 days 2 days Tale of a research query • Use of C-Reactive Protein as a marker of clinical infection in the NICU • First Temporal Structure:

  11. Days(Antibiotics) Abx Start Abx Stop CRP test No Abx 2+ days 2 days 2 days Tale of a research query • This is not right! Abx Stop could occur during 2-day window for CRP test, as long as CRP test occurred before CRP test

  12. Days(Antibiotics) CRP test  Abx Stop No Abx 2+ days 2 days 2 days Abx Start Tale of a research query • Does this capture the desired relationship? Want to allow for Abx Stop to occur within the 2-day CRP window but only if after CRP test. But do not want to require Abx Stop in the 2-day window

  13. Days(Antibiotics) CRP test  Abx Stop No Abx 2+ days 2 days 2 days Abx Start Abx Start Days(Antibiotics) CRP test  Abx Stop No Abx 2+ days 2 days 2 days Tale of a research query • What if I do want to constraint Abx Stop to the 2-day window? • What does that look like? Is the difference visually obvious?

  14. Different temporal structures - Different answersDifferent Clinical Meanings/Interpretations

  15. Representing Meaningful Temporal Relationships • Three weeks prior to admission, a bright red patch appeared under the patient's eye. • The patient developed a maculopapular rash that spread to her hands and then her knees the following day • On admission, she began having fever to 40oC which resolved by HD #2 • She was discharged on HD #8

  16. Original Assertions 7 6 1 1 Red Patch appeared 5 2 Hospital Admission 3 Rash over Hands 2 4 Rash over Knees 5 Fevers 6 Fever resolved 7 Hospital Discharge • Explosive number of derived temporal concepts (full transitive closure) • Not all of them are useful. But which ones? 3 4

  17. Full Temporal Closure 7 6 1 1 Red Patch appeared 5 2 Hospital Admission 3 Rash over Hands 2 4 Rash over Knees 5 Fevers 6 Fever resolved 7 Hospital Discharge • Explosive number of derived temporal concepts (full transitive closure) • Not all of them are useful. But which ones? 3 4

  18. Eight (of 10) clinically-meaningful time intervals Which ones are clinically relevant? Which ones have recommendations? Which ones can we extract? 1 2 3 4 5 6 7 8 Abx d/c time Surgical cut time Abx redose time Abx stop time Abx start time Time Milestones Associated with Surgical Antibiotics Prophylaxis

  19. Supporting Ad-Hoc Queries: Who is the User? • Clinically-knowledgable but data-naive clinicians • Goal: To ensure underlying temporal assumptions are explicit • What type of user interface visual paradigm would support this type of interactive queries? • What meta-data support is needed for clinically-meaningfulderived temporal concepts

  20. PatternFinder (Lam: University of Maryland) www.cs.umd.edu/hcil/patternfinder From: Lam. Searching Electronic Health Records for Temporal Patterns. A Case Study with Azyxxi, 2008.http://www.cs.umd.edu/hcil/ehrviz-workshop/

  21. Key Querying Features • Relational operators • “relative increase greater than X” • “relative increase greater than X%” • “relative decrease greater than X” • “relative decrease greater than X%” • “less than value in event X” • “equal to value in event X • “not equal to value in event X” • “within X prior to (relative)” • “within X following (relative)” • “after X (relative)” • “before X (relative)” • “is equal to (relative)” • “equal to value in event X” • “not equal to value in event X” From:Lam. Searching Electronic Health Records for Temporal Patterns. A Case Suty with Azyxxi, 2008.http://www.cs.umd.edu/hcil/ehrviz-workshop/ 22

  22. PatternFinder Interface Patients with increasing dosages of Remeron followed by a heart attack within 180 days From: Wang, Plaisant, Shneiderman. Workshop: Interactive Exploration of Electronic Health Records, 2008.http://www.cs.umd.edu/hcil/ehrviz-workshop/

  23. Patients with increasing dosages of Remeron followed by a heart attack within 180 days SELECT P.* FROM Person P, Event E1, Event E2, Event E3, Event E4 WHERE P.PID = E1.PID AND P.PID = E2.PID AND P.PID = E3.PID AND P.PID = E4.PID AND E1.type = “Medication” AND E1.class = “Anti Depressant” AND E1.name = “Remeron" AND E2.type = “Medication” AND E2.class = “Anti Depressant” AND E2.name = “Remeron“ AND E3.type = “Medication” AND E3.class = “Anti Depressant” AND E3.name = “Remeron" AND E2.value > E1.value AND E3.value >= E2.value AND E2.date > E1.date AND E3.date >= E2.date AND E4.type = “Visit” AND E4.class = “Hospital” AND E4.name = “Emergency" AND E4.value = "Heart Attack" AND E4.date >= E3.date AND 180 <= (E4.date – E3.date) From: Wang, Plaisant, Shneiderman. Workshop: Interactive Exploration of Electronic Health Records, 2008.http://www.cs.umd.edu/hcil/ehrviz-workshop/

  24. Result Set Visualization: Ball and Chain From: Wang, Plaisant, Shneiderman. Workshop: Interactive Exploration of Electronic Health Records, 2008.http://www.cs.umd.edu/hcil/ehrviz-workshop/

  25. LifeLines2: Align-Rank-Filter www.cs.umd.edu/hcil/lifelines2 From: Wang, Plaisant, Shneiderman. Workshop: Interactive Exploration of Electronic Health Records, 2008.http://www.cs.umd.edu/hcil/ehrviz-workshop/

  26. From: Wang, Plaisant, Shneiderman. Workshop: Interactive Exploration of Electronic Health Records, 2008.http://www.cs.umd.edu/hcil/ehrviz-workshop/

  27. Study-specific Dates Maximum Follow-up Date Accrual Window Time Look-back Window Observation Window End of Observation Date Index Event Date Patient-specific Dates Health Services Research Temporal Templates? From A. Forster. The Ottawa Hospital-Data Request Form 2009

  28. Data quality – Dirty Laundry • Suppose the previous issues were solved and investigators can easily construct complex temporal and atemporal queries…… …..what is the quality of the results that come back?

  29. Let’s assume the query interface issue is solved!Would this result be worrisome?

  30. It’s tough being 6 years old…….

  31. Should we be worried? • No • Large numbers will swamp out effect of anomalous data or use trimmed data • Simulation techniques are insensitive to small errors • Yes • Public reporting could highlight data anomalies • Genomic associations look for small signals (small differences in risks) amongst populations

  32. Research Challenge • Can we create a dynamic measure of data quality that is provided with the results of all queries? • Query  Results, quality measure

  33. What would be the elements of QM? Book cover images from Amazon.com

  34. Measuring Data Quality • Observed versus expected distributions • Outliers • Missing values • Performance on data validitychecks • Single attribute analysis • Double- / triple- / higher level attributes correlations • Physical / logical domain impossibilities

  35. Defining data quality: The “Fit for Use” Model • Borrowed from industrial quality frameworks • Juran (1951): “Fitness for Use” • design, conformance, availability, safety, and field use • Multiple adaptations by information science community • Not all adaptations are clearly specified • Not all adaptations are consistent • Not linked to measurement/assessment methods

  36. How to measure data quality? • Need to link conceptual framework with methods • Maydanchik: Five classes of data quality rules • Attribute domain: validate individual values • Relational integrity: accurate relationships between tables, records and fields across multiple tables • Historical: time-vary data • State-dependent: changes follow expected transitions • Dependency: follow real-world behaviors Maydanchik, A. (2007). Data quality assessment. Bradley Beach, NJ, Technics Publications.

  37. Data Quality Assessment METHODS • Five classes of data quality rules  30 assessment methods • Attribute domain rules (5 methods) • Relational integrity: (4 methods) • Historical: (9 methods) • State-dependent: (7 methods) • Dependency: (5 methods) Time and change assessments dominate!!

  38. Dimension 1: Attribute domain constraints

  39. Dimension 2: Relational integrity rules

  40. Dimension 4: State-dependent rules

  41. Dimension 5:Attribute dependency rules

  42. Implementing the Framework in SAFTINet • One of three AHRQ Distributed Research Network grants • SCANNER (UCSD) • SPAN (KPCO) • Focused on safety net healthcare providers • Includes financial/clinical data integration with Medicaid payments • Using Ohio State /TRIAD grid-technologies

  43. SAFTINet: Distributed research network Grid Portal

  44. Related DQ Work: Visualizing Data Quality

  45. Related DQ Work: Visualizing Data Quality

  46. Michael.Kahn@ucdenver.edu

More Related