Your SlideShare is downloading. ×
0
CER HUB An Informatics Platform for Conducting Compartive Effectiveness with EMR HAZLEHURST
CER HUB An Informatics Platform for Conducting Compartive Effectiveness with EMR HAZLEHURST
CER HUB An Informatics Platform for Conducting Compartive Effectiveness with EMR HAZLEHURST
CER HUB An Informatics Platform for Conducting Compartive Effectiveness with EMR HAZLEHURST
CER HUB An Informatics Platform for Conducting Compartive Effectiveness with EMR HAZLEHURST
CER HUB An Informatics Platform for Conducting Compartive Effectiveness with EMR HAZLEHURST
CER HUB An Informatics Platform for Conducting Compartive Effectiveness with EMR HAZLEHURST
CER HUB An Informatics Platform for Conducting Compartive Effectiveness with EMR HAZLEHURST
CER HUB An Informatics Platform for Conducting Compartive Effectiveness with EMR HAZLEHURST
CER HUB An Informatics Platform for Conducting Compartive Effectiveness with EMR HAZLEHURST
CER HUB An Informatics Platform for Conducting Compartive Effectiveness with EMR HAZLEHURST
CER HUB An Informatics Platform for Conducting Compartive Effectiveness with EMR HAZLEHURST
CER HUB An Informatics Platform for Conducting Compartive Effectiveness with EMR HAZLEHURST
CER HUB An Informatics Platform for Conducting Compartive Effectiveness with EMR HAZLEHURST
CER HUB An Informatics Platform for Conducting Compartive Effectiveness with EMR HAZLEHURST
CER HUB An Informatics Platform for Conducting Compartive Effectiveness with EMR HAZLEHURST
CER HUB An Informatics Platform for Conducting Compartive Effectiveness with EMR HAZLEHURST
CER HUB An Informatics Platform for Conducting Compartive Effectiveness with EMR HAZLEHURST
CER HUB An Informatics Platform for Conducting Compartive Effectiveness with EMR HAZLEHURST
CER HUB An Informatics Platform for Conducting Compartive Effectiveness with EMR HAZLEHURST
CER HUB An Informatics Platform for Conducting Compartive Effectiveness with EMR HAZLEHURST
CER HUB An Informatics Platform for Conducting Compartive Effectiveness with EMR HAZLEHURST
CER HUB An Informatics Platform for Conducting Compartive Effectiveness with EMR HAZLEHURST
CER HUB An Informatics Platform for Conducting Compartive Effectiveness with EMR HAZLEHURST
CER HUB An Informatics Platform for Conducting Compartive Effectiveness with EMR HAZLEHURST
CER HUB An Informatics Platform for Conducting Compartive Effectiveness with EMR HAZLEHURST
CER HUB An Informatics Platform for Conducting Compartive Effectiveness with EMR HAZLEHURST
CER HUB An Informatics Platform for Conducting Compartive Effectiveness with EMR HAZLEHURST
CER HUB An Informatics Platform for Conducting Compartive Effectiveness with EMR HAZLEHURST
CER HUB An Informatics Platform for Conducting Compartive Effectiveness with EMR HAZLEHURST
CER HUB An Informatics Platform for Conducting Compartive Effectiveness with EMR HAZLEHURST
CER HUB An Informatics Platform for Conducting Compartive Effectiveness with EMR HAZLEHURST
CER HUB An Informatics Platform for Conducting Compartive Effectiveness with EMR HAZLEHURST
CER HUB An Informatics Platform for Conducting Compartive Effectiveness with EMR HAZLEHURST
CER HUB An Informatics Platform for Conducting Compartive Effectiveness with EMR HAZLEHURST
Upcoming SlideShare
Loading in...5
×

Thanks for flagging this SlideShare!

Oops! An error has occurred.

×
Saving this for later? Get the SlideShare app to save on your phone or tablet. Read anywhere, anytime – even offline.
Text the download link to your phone
Standard text messaging rates apply

CER HUB An Informatics Platform for Conducting Compartive Effectiveness with EMR HAZLEHURST

509

Published on

Comparative Effectiveness Research

Comparative Effectiveness Research

0 Comments
0 Likes
Statistics
Notes
  • Be the first to comment

  • Be the first to like this

No Downloads
Views
Total Views
509
On Slideshare
0
From Embeds
0
Number of Embeds
0
Actions
Shares
0
Downloads
4
Comments
0
Likes
0
Embeds 0
No embeds

Report content
Flagged as inappropriate Flag as inappropriate
Flag as inappropriate

Select your reason for flagging this presentation as inappropriate.

Cancel
No notes for slide

Transcript

  • 1. The CER Hub: An Informatics Platform for Conducting Comparative Effectiveness Research with Comprehensive Electronic Medical Record Data Brian Hazlehurst, PhD Kaiser Permanente Northwest Center for Health Research© 2012, KAISER PERMANENTE CENTER FOR HEALTH RESEARCH
  • 2. Outline  Why do we need the CER Hub?  The CER Hub extends and makes available an automated medical record classifier (MediClass)  The development of projects using the CER Hub  The current CER Hub members and projects under way© 2012, KAISER PERMANENTE CENTER FOR HEALTH RESEARCH
  • 3. CER requires LOTS of data  Diverse populations, many topic areas  Increasing adoption of EMR systems provides an emerging opportunity for developing large databases  KP covers ~9M lives @ 4 encounters/yr, roughly 100,000 encounters per day captured in the EMR  A vast amount of this data is captured in unstructured (non- coded) text© 2012, KAISER PERMANENTE CENTER FOR HEALTH RESEARCH
  • 4. Example clinical encounter record segments addressing family and personal hx for cancer Clinical note segment written Relevant ICD9 dx code applied Med Hx:Asthma-Azmacort, Ventolin, rarely prednisone1 Surg Hx:neg None Family Hx:Fa-aodm, pgf colon ca, mgm bone marrow ca ------------------------------------------------------------------------ ------------------------------------------ Last Mammogram: 1 yr ago. None Previous Paps have been normal2 There is a strong family hx of breast cancer.(M, MGM,Aunt) ------------------------------------------------------------------------ ------------------------------------------ RN noted S OB comma asked that I see pt. 174.9 CA FEMALE BREAST, She has invasive ductal CA of the breast, and is getting INFILTRATING DUCTAL3 chemo. Has today become more acutely SOB. ------------------------------------------------------------------------ ------------------------------------------ ROS: neg for exertional chest pain or pressure, shortness V16.0 FAMILY HX breath, changes inbowel habits. MALIGNANCY GI TRACT4 Fam Hx: + early MI, colon cancer-- sister in her 50s© 2012, KAISER PERMANENTE CENTER FOR HEALTH RESEARCH
  • 5. Coverage of the RAND QA measures by standardized CODED data 1 0.9 0.8 Claims % of QA measures 0.7 Claims+Lab 0.6 Claims+Proced 0.5 Claims+Vitals 0.4 Claims+S/S 0.3 0.2 Claims+All 0.1 0 Data Sources The remainder necessary for comprehensive quality assessment is found in either the templated- or free-text clinical notes of the EMR!© 2012, KAISER PERMANENTE CENTER FOR HEALTH RESEARCH
  • 6. The CER HUB  A web-based platform for collaborative development of study-specific, standardized, processors of comprehensive electronic medical record data.  Site data is extracted locally in industry standard form (HL7 CDA)  Centrally developed processor of entire medical record creates a standardized and reusable/extensible resource for CER Hub users  Sensitive source clinical data (e.g., text progress notes) remain under local control and is extracted on demand for specific projects  Standardized (study-specific) datasets that are generated by applying the processor locally are pooled to answer targeted study questions centrally and these remain under study-team’s control© 2012, KAISER PERMANENTE CENTER FOR HEALTH RESEARCH
  • 7. Why do we need the CER Hub?  EMR adoption promises LOTS of data, but the data are heterogeneous both across and within institutions  EMR’s are variable (diverse representation of events)  Clinical practices are variable (diverse priorities and capture of events)  Patients are variable (diverse conditions and needs)  Need scalable informatics solutions allowing assignment of consistent (and specific) meanings to highly heterogeneous data  want to remove spurious variation to highlight the “real” variation specific to a study question© 2012, KAISER PERMANENTE CENTER FOR HEALTH RESEARCH
  • 8. Outline  Why do we need the CER Hub?  The CER Hub extends and makes available an automated medical record classifier (MediClass)  The development of projects using the CER Hub  The current CER Hub members and projects under way© 2012, KAISER PERMANENTE CENTER FOR HEALTH RESEARCH
  • 9. MediClass (Medical Classifier)  Utilize a standard representation for electronic medical record data (HL7 Clinical Document Architecture, CDA- CCD)  potential to process records of any EMR.  Process both text and coded data in the EMR  potential to process any type of data captured in the EMR.  Allow for modular definition of measures or study variables (classifications determined by plug-in “knowledge modules”)  potential to apply any specific measure.  Capable of local installation and operation  potential to create shareable, standardized research data© 2012, KAISER PERMANENTE CENTER FOR HEALTH RESEARCH
  • 10. MediClass System CDA Medical CDA EMR Record(XML) Parser EMR Integration System (data CDA Medical Recordwarehouse) ( Java object model) Concept CDA w/Free Identifier Text Concepts Unified Medical Concept Language Coded Data CDA w/Free Text Identification System Concept Concepts& Structured (UMLS) Data Concepts Knowledge Mapper Module Event Classifier Clinical Event Classification Rulebase CDA w/Free Text Classification Concepts& Structured Data Concepts & Event Classification Results JAMIA Sep-Oct, 2005 Repository
  • 11. Summary of MediClass study results Project Title Funder Description Key Results Automated Assessment of Use of electronic medical Asthma Incidence and Sensitivity, 62-95%; CDC records for surveillance of Prevalence (manuscript in Specificity, 90-100% asthma in an HMO preparation) Development of Sensitivity(1), 62-92%; Automating Assessment of comprehensive automated Specificity(1), 75-93%. Asthma Care Quality (in AHRQ assessment of outpatient Sensitivity(2), 35-69% press, AJMC) asthma care quality Specificity(2), 69-95% Vaccination Safety Datalink: Detection of possible Adverse Vaccine Event vaccine-related adverse Sensitivity, 75-81%; CDC Detection (Hazlehurst et al, events in large-linked Specificity, 97-98%; 2009 -- Vaccine) databases Identifying Family and Identification of Personal History of Cancer in breast/ovarian and other Sensitivity, 62-98%; the EMR (Hazlehurst et al, NCI cancer family and Specificity, 97-99% 2005 HMORN research conf personal history in poster) progress notes HMO Interventions in Assessing compliance Sensitivity, 64-100%; Tobacco (Hazlehurst et al, NCI with the 5A’s guideline in Specificity, 82-100% 2005 – AJPM) four HMO’s (four HMO’s)© 2012, KAISER PERMANENTE CENTER FOR HEALTH RESEARCH
  • 12. Outline  Why do we need the CER Hub?  The CER Hub extends and makes available an automated medical record classifier (MediClass)  The development of projects using the CER Hub  The current CER Hub members and projects under way© 2012, KAISER PERMANENTE CENTER FOR HEALTH RESEARCH
  • 13. The CER HUB  A web-based platform for collaborative development of study-specific, standardized, processors of electronic clinical datasets.  A web site with functions related to building, testing, sharing, study-specific processors of heterogeneous clinical data.© 2012, KAISER PERMANENTE CENTER FOR HEALTH RESEARCH
  • 14. The CER HUB: Building  A set of tools for collaborative development of study-specific data processors.  Operationalizing study variables in terms of concepts identified in clinical records  These variables may involve concepts identified in text and/or structured data elements of clinical records.  Eg., “persistent asthma” can be operationalized in terms of sequences of asthma medication fills, exacerbation visits, and clinician assessment in the progress note.© 2012, KAISER PERMANENTE CENTER FOR HEALTH RESEARCH
  • 15. The CER HUB: Testing  Developed processors can be run on the HUB against (de-identified) test datasets to evaluate the data processor.  Allows for rapid development of knowledge modules through iterative test-refine cycles.  Creates validation metrics that provide a “profile” about the data processor that is retained in the library.© 2012, KAISER PERMANENTE CENTER FOR HEALTH RESEARCH
  • 16. The CER HUB: Sharing  A web site hosting virtual communities of researchers with shared interests (i.e., organized around a shared study topic).  A library of study-specific data processors are available for download as applications addressing a range of research questions.  Researchers who join the consortium build out the library over time through their activities using the HUB for their research.© 2012, KAISER PERMANENTE CENTER FOR HEALTH RESEARCH
  • 17. The CER HUB workflow1) Develop 2) Develop and validate 3) Configure thea study protocol a standardized data processor for your site processor(define study measures (operationalize (defines site-specificand populations of study measures based parametersinterest) on concepts in data) for the processor) De-identified Download Pop def samples processor1a) Data extraction 4) Apply processor 5) Pool standardized, to local data sharable data for analysis(extract data in astandard format)
  • 18. 1a) Data Extraction (EMR Integration) Study Protocol Clinical Study pop and data Research Data elements Dictionary HL7 EMRAdapter CDA (Schema Schema EMR Site specific Site Specific Mapper) schema CRD Warehouse schema (CSV or XML) Schema Schema mapping EMR-to-CDA mapping De-identify and upload to Hub E M R D a ta s e t S ite S p e c ific (C S V , X M L ) EMR W a re h o u s e EM R D a ta (RD B M S ) D a ta s e t Dataset Adapter CD A XML Publish (Runtime Engine) MediClass Application© 2012, KAISER PERMANENTE CENTER FOR HEALTH RESEARCH
  • 19. 2) Data Processor Development and Validation F ro m S te p 1 a n d 1 a Study Protocol w/ Uploaded de - operationalized identified data measures Chart Define/ abstraction Mediclass refine using Processes Job concepts Manual Job and rules Coder tool • Direct Inspection of Development classification results data • Comparison to Manual Validation Data Coding (development ) • Comparison to Gold No Gold Standard (validation) Std Aggregate Done. manual Processor is coding using ready for Gold download Standard Satisfactory Maker Performance ? Yes© 2012, KAISER PERMANENTE CENTER FOR HEALTH RESEARCH Processor building tools Processor Validation Tools
  • 20. CER HUB Study Protocol Population and data Knowledge module Application specific element selection for and Configuration for extraction filter for study encounter -based specific application specific (and sharable ) extraction events Study variables operationalized in terms of temporally located events MediClass EventsDataset EMRAdapter Post-Processor Application Processor CDA CDA w/ MediClass EventsDataset StudyData Warehouse (XML) Classifications (Flat file ) Measures (XML) Data Extraction Event Identification Study Analyses Local Site Local Site DCC
  • 21. Outline  Why do we need the CER Hub?  The CER Hub extends and makes available an automated medical record classifier (MediClass)  The development of projects using the CER Hub  The CER Hub project: members and studies under way© 2012, KAISER PERMANENTE CENTER FOR HEALTH RESEARCH
  • 22. The CER HUB Project  A consortium of researchers from 6 health systems  KPNW, KPGA, KPHI,  VA PugetSound,  Baylor HealthCare System,  OCHIN (consortium of FQHCs mostly on west coast)  Developing and using the CER HUB to address effectiveness questions in asthma control therapy and smoking cessation services© 2012, KAISER PERMANENTE CENTER FOR HEALTH RESEARCH
  • 23. CER HUB Project Specific Aims 1. Develop, operate, and evaluate a centralized CER service on the Internet that provides automated tools, methods, and support for generating standardized datasets to answer CER questions. 2. Utilize the CER HUB to develop and validate an EMR-based measure of “asthma control" in accord with established national guidelines, and evaluate effectiveness of treatment intensification options on asthma control. 3. Utilize the CER HUB to assess implementation of the US Preventive Services Task Force evidence-based tobacco treatment guideline (the 5A’s) in the six participating organizations, and evaluate the comparative effectiveness of smoking cessation services on quitting in whole populations of patients in the course of real-world, routine clinical care.© 2012, KAISER PERMANENTE CENTER FOR HEALTH RESEARCH
  • 24. Asthma Control Impairment Risk  Asthma-related steroid use –  Asthma symptoms (wheezing, chest orders or dispensings consistent cough, chest tightness, or shortness of with 2 or more courses in past 12 breath) > two days per week; months;  Experiencing night-time awakening one or  ED visits or hospitalizations – 2 or more in past 12 months; more per week;  Progressive loss of pulmonary  Using reliever medications more than two function over time (by spirometry days per week; or peak flow testing);  Symptoms interfere with normal activity;  Medication side effects, such as dysphonia, thrush, osteoporosis  Reporting unacceptable control; (for inhaled corticosteroids),  Low asthma questionnaire score (e.g., ACT nervousness and tachydysrhythmia (for beta-2- score < 19); agonists)  FEV1< 80% predicted and/or PEFR <80% best;© 2012, KAISER PERMANENTE CENTER FOR HEALTH RESEARCH
  • 25. Compare effectiveness of step-up therapies for asthma control Main Asthma study CER question: For patients on low-dose inhaled corticosteroid therapy whose asthma is not well controlled (i.e., failed EPR-3 Step 2 therapy), we will investigate the comparative effectiveness of the following step-up therapies (i.e., EPR-3 recommended Step 3 therapies) (1) addition of a leukotriene modifier (2) addition of a long-acting beta-agonist (3) increase to medium-dose inhaled corticosteroids On the basis of efficacy studies, options 2 and 3 are considered ‘first-line’ options.© 2012, KAISER PERMANENTE CENTER FOR HEALTH RESEARCH
  • 26. CER Hub Study Protocol - Asthma Care Possible Asthma Definition “Possible Asthmatic" is defined by patient having received at least one ICD-9-CM diagnosis code at any visit during study period of 493.xx Study Inclusion Protocol We will include all patients, 12 years and older on 1/1/2006, identified as possible asthmatic (see definition above) during observation period (1/1/2006-12/31/2010) and also assess outcomes (2011-2012) Persistent Asthma Definition We will focus on patients whose asthma is “persistent” using the developed data processor that will consider medication usage (orders and dispenses), visits (inpatient, outpatient, and ED), and clinical judgement (clinician assessment that the patient has persistent asthma as documented in the progress note).© 2012, KAISER PERMANENTE CENTER FOR HEALTH RESEARCH
  • 27. CER Hub Possible Asthma Population TOTAL DISTINCT Study Sites 2006 2007 2008 2009 2010 PATIENTS Baylor 3166 6138 9836 6504 4850 30494 KPSE 9858 10224 10357 10917 5266 26756 KPHI 12637 12182 12227 12756 12324 33349 KPNW 21342 22495 23677 24741 24731 64764 OCHIN 1997 3870 6204 11260 15306 26922 VA-PS 1377 1668 1880 1972 2235 4667 TOTAL DISTINCT PATIENTS 50377 56577 64181 68150 64712 186952© 2012, KAISER PERMANENTE CENTER FOR HEALTH RESEARCH
  • 28. Asthma Investigators  Rich Mularski, MD (KPNW)  Michael Schatz, MD (KPSC)  Jerry Krishnan, MD, PhD (U of Chicago)  David Au, MD (VAPS)  Mark Millard, MD (Baylor)  Bob Davis, MD (KPGA)© 2012, KAISER PERMANENTE CENTER FOR HEALTH RESEARCH
  • 29. The 5 A’s of Smoking Cessation 5A step Operational Example in free-text definition section of EMR Ask Identify tobacco user “Patient smokes 1 ppd” status at every visit Advise Advise all tobacco “It is important for you users to quit to quit smoking now” Assess Determine patient’s “Patient not interested willingness to in quitting smoking” make a quit attempt Assist Aid the patient in “Started patient on quitting Zyban” Arrange Schedule follow-up “Follow-up in 2 weeks contact, in person for quit progress” or via telephone© 2012, KAISER PERMANENTE CENTER FOR HEALTH RESEARCH
  • 30. CER Hub Study Protocol-Smoking Cessation Smoker Definition "Current smoker" is defined on an annual basis as having received at least one of the following during a calendar year: 1) ICD-9-CM diagnosis code indicating “tobacco abuse” at any visit 2) An update of their social history to indicate "current smoker“ Additional measures are defined for “Quitter” (someone who recently quit) and “Former Smoker” (someone who has stayed quit). Study Inclusion Protocol Unique patients, 12 years and older, identified as: 1) current smoker and 2) having received primary care (one or more primary care visits) All such patients will be included in the study and will be flagged as to their status according to these measures in each of the study years (2006 – 2010) and outcomes assessed (2011 – 2012).© 2012, KAISER PERMANENTE CENTER FOR HEALTH RESEARCH
  • 31. CER Hub Smoker Population TOTAL DISTINCT Study Sites 2006 2007 2008 2009 2010 PATIENTS Baylor 2707 12338 22741 22162 24025 58616 KPSE 17385 16067 15188 13722 6534 37868 KPHI 19160 17849 17164 18406 20896 51847 KPNW 47202 47786 46375 50944 50630 120328 OCHIN 8489 14726 23769 39946 56340 78736 VA-PS 10944 12334 13570 15052 15860 30535 TOTAL DISTINCT PATIENTS 105887 121100 138807 160232 174285 377930© 2012, KAISER PERMANENTE CENTER FOR HEALTH RESEARCH
  • 32. Smoking Cessation Investigators  Victor Stevens, PhD (KPNW)  Rebecca Williams, PhD (KPHI)  Nancy Rigotti, MD (Harvard)  Leif Solberg, MD (Health Partners)  Andrew Williams, PhD (KPHI)  Andrew Massica, MD (Baylor)© 2012, KAISER PERMANENTE CENTER FOR HEALTH RESEARCH
  • 33. Informatics Investigators  Brian Hazlehurst, PhD (KPNW)  Yan Xiao, PhD (Baylor)  Jon Puro (OCHIN)  Paul Nichol, MD (VAPS)  MaryAnn McBurnie, PhD (KPNW)© 2012, KAISER PERMANENTE CENTER FOR HEALTH RESEARCH
  • 34. www.cerhub.org© 2012, KAISER PERMANENTE CENTER FOR HEALTH RESEARCH

×