Identifying RA patients from the electronic medical records at Partners HealthCare Robert Plenge, M.D., Ph.D. VA Hospital July 20, 2010 HARVARD MEDICAL.

Slides:



Advertisements
Similar presentations
Population Trends in the Incidence and Outcomes of Acute Myocardial Infarction Robert W. Yeh, MD MSc Massachusetts General Hospital Alan S. Go, MD Kaiser.
Advertisements

PREDICTIVE MODELING IN E-HEALTH USING ARTIFICIAL INTELLIGENCE MARK HOOGENDOORN (AND MANY OTHERS INCLUDING MICHEL KLEIN) MARK HOOGENDOORN (AND MANY OTHERS.
Efficacy of Methotrexate and/or Etanercept for treatment of RA Rheumatoid Arthritis:
A quantitative approach to accurate classification of RA. Tom Huizinga.
Pragmatic use of data for research, audit and revalidation Will Dixon Health Informatics Unit 10 th anniversary Royal College of Physicians, 15 th Sept.
The Relationship Between Repeat Infections and Behavioral Risk Factors and Clinician Counseling: Findings from a Philadelphia STD Clinic M. Eberhart 1,
STUDY DESIGN CASE SERIES AND CROSS-SECTIONAL
Inappropriate clopidogrel adherence explains stent related adverse outcomes Leonardo Tamariz, MD, MPH University of Miami.
The Role of Human Genetics in Drug Discovery
Reuse of Electronic Medical Records for Research Our architecture Two examples.
Department of Health and Human Services Measuring Clinical Lab Ordering Quality: Theory and Practice Steven M. Asch MD MPH VA, RAND, UCLA April 29, 2005.
Biostatistics ~ Types of Studies. Research classifications Observational vs. Experimental Observational – researcher collects info on attributes or measurements.
Model and Variable Selections for Personalized Medicine Lu Tian (Northwestern University) Hajime Uno (Kitasato University) Tianxi Cai, Els Goetghebeur,
Variable Selection for Optimal Decision Making Lacey Gunter University of Michigan Statistics Department Michigan Student Symposium for Interdisciplinary.
Study: Statins increase life expectancy Detroit News, Associated Press
Cohort Studies Hanna E. Bloomfield, MD, MPH Professor of Medicine Associate Chief of Staff, Research Minneapolis VA Medical Center.
Measuring Signs and Symptoms in Rheumatoid Arthritis David R. Karp, MD, PhD Chief, Rheumatic Diseases UT Southwestern Medical Center David R. Karp, MD,
Electronic Medical Record Use and the Quality of Care in Physician Offices National Conference on Health Statistics August 17, 2010 Chun-Ju (Janey) Hsiao,
Electronic Medical Record Vincent N. Carrasco, MD LAIR MSIS ‘14.
1 Demographic and Clinical Characteristics of Rheumatoid Arthritis patients in some Arab States: Preliminary analysis Mohammed Hammoudeh,M.D Division of.
Opportunities for Big Data in Medical Records Mike Conlon, PhD
Therapeutic algorithms for Crohn’s disease: Where are we in 2012?
Pharmacogenomics: Studies in Breast Cancer Lynn C. Hartmann MD Mayo Clinic Cancer Center.
Elizabeth Karlson, MD Associate Professor of Medicine
LARA MANGRAVITE SAGE BIONETWORKS ON BEHALF OF THE RA CHALLENGE ORGANIZING TEAM The DREAM Rheumatoid Arthritis Responder Challenge: Motivation, Data, Scoring.
Research Techniques Made Simple: Databases for Clinical Research Katrina Abuabara, MD MA David Margolis, MD PhD University of Pennsylvania.
Preventive Health Care Use in Elderly Uterine Cancer Survivors Division of Health Policy and Management School of Public Health University of Minnesota.
1 Demographic and Clinical Characteristics of Rheumatoid Arthritis patients in some Arab States: Preliminary analysis Mohammed Hammoudeh Division of Rheumatology,
Butte Lab Journal Club 16 Aug 2010 Alexander A. Morgan.
Crowdsourcing pharmacogenomic data analysis: PGRN-Sage RA Responder Challenge PGRN Spring Meeting April 30, 2013 HARVARD MEDICAL SCHOOL.
A 1 Alosetron /26 Elizabeth B. Andrews, Ph.D., M.P.H. Director, Worldwide Epidemiology.
PGPop: PharmacoGenomic discovery and replication in very large patient POPulations PGPop: SUMMARY PGPop was conceived as a network resource to provide.
Square wheels: electronic medical records for discovery research in rheumatoid arthritis Robert M. Plenge, M.D., Ph.D. October 30, 2009 NCRR sponsored.
Genetic Analysis in Human Disease Nataly Manjarrez, PhD GENETIC ANALYSIS IN HUMAN DISEASE Nataly Manjarrez Orduño, PhD Assistant Investigator, Feinstein.
EMR use is not associated with better diabetes care Patrick J. O’Connor, MD, MPH, A. Lauren Crain, PhD, Leif I. Solberg, MD, Stephen E. Asche, MA, William.
LEADING RESEARCH… MEASURES THAT COUNT Challenges of Studying Cardiovascular Outcomes in ADHD Elizabeth B. Andrews, MPH, PhD, VP, Pharmacoepidemiology and.
Melanie Dunn 9/20/2011.  Rheumatoid arthritis (RA) is a chronic disease that leads to inflammation of the joints and surrounding tissues that can also.
Risk assessment for VTE Dr Roopen Arya King’s College Hospital.
Copyright © 2015 Lippincott Williams & Wilkins. Unauthorized commercial reproduction of this slide is prohibited Supplemental PowerPoint Slides Reoperation.
Relational Discord at Conclusion of Treatment Predicts Future Substance Use for Partnered Patients Wayne H. Denton, MD, PhD; Paul A. Nakonezny, PhD; Bryon.
Consultant Rheumatologist
A Claims Database Approach to Evaluating Cardiovascular Safety of ADHD Medications A. J. Allen, M.D., Ph.D. Child Psychiatrist, Pharmacologist Global Medical.
Regulatory Guidance for Genetic Testing. Three Specific Areas Laboratory tests Results of genetic testing – Clinical – Research GenomeWide Association.
GRAPPA Guidelines for PsA: Considerations GRAPPA Guidelines Mission Statement: “To develop guidelines, based upon the best scientific evidence, for the.
Uses of the NIH Collaboratory Distributed Research Network Jeffrey Brown, PhD for the DRN Team Harvard Pilgrim Health Care Institute and Harvard Medical.
Consequences Of Non-Compliance To Osteoporosis Medication Among Osteoporotic Women Ankita Modi, Ph.D, M.D. 1, Jackson Tang, M.Sc. 2, Shuvayu Sen, Ph.D.
WHO-Collaborating Centre in Calgary Thursday May 14 th, 2015 in Calgary, Alberta, Canada Dr. Bedirhan Ustun from the WHO attended and presented Dr. Hude.
Getting the detail right Standardisation and SNOMED CT © Nottingham University Hospitals NHS Trust.
Opiate use in patients with inflammatory bowel disease
Assessment of Injection Drug Use Based on Diagnostic Codes in Administrative Datasets M Kuo 1, NZ Janjua 1,2, AYW Yu 1, N Islam 1,2, H Samji 1, JA Buxton.
Ulcerative Colitis (UC)-Associated Colorectal Cancer (CRC) Patients Who Receives Colorectal Surgery More Likely Receive Blood Transfusion Than Crohn’s.
Medical Care Cost of Medicare/Medicaid Beneficiaries with Vision Loss
Development and Validation of HealthImpactTM: An Incident Diabetes Prediction Model Based on Administrative Data Rozalina G. McCoy, M.D.1, Vijay S. Nori,
Cough WORKING GROUP MEETING
How do we improve the “sufficiency” of the FDA’s Sentinel System?
Introduction to Health Insurance
ICD-10 and Clinical Documentation
Roland C. Merchant, MD, MPH, ScD
Decision-making in the eRA of Treating to Target
Division of Viral Hepatitis, CDC
Impact of Hepatitis C, HIV, or Both on Survival in Veterans in Care Before and After the Introduction of HAART (1996) SL Fultz, MD, MPH CH Chang, PhD AA.
Clinical Research Informatics: From Bedside to Silicon and Back
Discovery From Data Repositories H Craig Mak  Nature Biotechnology 29, 46–47 (2011) 2013 /06 /10.
A Population Level Analysis of Statewide Claims Data
Digital Biomarkers – Patient data mining & precision medicine Stefan Schulz, Medical University of Graz Donausymposium Vienna, March 14, 2018.
SYNOPSIS OF THE PROTOCOL
Regulatory Perspective of the Use of EHRs in RCTs
Presentation data from US VICTORY Consortium
Genetic Basis of Autoantibody Positive and Negative Rheumatoid Arthritis Risk in a Multi-ethnic Cohort Derived from Electronic Health Records  Fina Kurreeman,
Presentation transcript:

Identifying RA patients from the electronic medical records at Partners HealthCare Robert Plenge, M.D., Ph.D. VA Hospital July 20, 2010 HARVARD MEDICAL SCHOOL

genotype phenotype clinical care

genotype phenotype clinical care bottleneck

July 2010: >30 RA risk loci PTPN “shared epitope” hypothesis HLA DR PADI4CTLA4 TNFAIP 3 STAT4 TRAF1- C5 IL2-IL21 CD40 CCL21 CD244 IL2RB TNFRSF 14 PRKCQ PIP4K2C IL2RA AFF3 Latest GWAS in 25,000 case-control samples with replication in 20,000 additional samples 2009 REL BLK TAGAP CD28 TRAF6 PTPRC FCGR2A PRDM1 CD2- CD58 Together explain ~35% of the genetic burden of disease IL6ST SPRED2 5q21 RBPJ IRF5 CCR6 PXK 2010 (Q2)

genotype phenotype clinical care bottleneck

Genetic predictors of response to anti-TNF therapy in RA PTPRC/CD45 allele n=1,283 patients P= Cui et al (2010) Arth & Rheum

How can we collect DNA and detailed clinical data on >20,000 RA patients?

What are the options for collecting clinical data and DNA for genetic studies?

Options for clinical + DNA designClinical data DNASample size cost clinical trial +++ +$$$ registry $$ claims data +n/a+++$ EMR $

Narrative data = free-form written text –info about symptoms, medical history, medications, exam, impression/plan Codified data = structured format –age, demographics, and billing codes Content of EMRs EMRs are increasingly utilized!

Gabriel (1994) Arthritis and Rheumatism This is not a new idea… Sens: 89% PPV: 57% Sens: 89% PPV: 57%

Gabriel (1994) Arthritis and Rheumatism Conclusion: The sole reliance on such databases for the diagnosis of RA can result in substantial misdiagnosis. …but EMR data are “dirty”

Partners HealthCare: 4 million patients

Partners HealthCare: linked by EMR

Partners HealthCare: organized by i2b2

4 million patients 31,171 patients ICD9 RA and/or CCP checked (goal = high sensitivity) 3,585 RA patients Classification algorithm (goal = high PPV)

Natural language processing (NLP) –disease terms (e.g., RA, lupus) –medications (e.g., methotrexate) –autoantibodies (e.g., CCP, RF) –radiographic erosions Codified data –ICD9 disease codes –prescription medications –laboratory autoantibodies Our library of RA phenotypes Qing Zeng Concept/termAccuracy of concept presence of erosion88% seropositive96% CCP positive98.7% RF positive99.3% etanercept100% methotrexate100% Guergana Savova

Natural language processing (NLP) –disease terms (e.g., RA, lupus) –medications (e.g., methotrexate) –autoantibodies (e.g., CCP, RF) –radiographic erosions Codified data –ICD9 disease codes –prescription medications –laboratory autoantibodies Our library of RA phenotypes Shawn Murphy

‘Optimal’ algorithm to classify RA: NLP + codified data Regression model with a penalty parameter (to avoid over-fitting) Codified dataNLP data Tianxi Cai, Kat Liao

High PPV with adequate sensitivity ✪ 392 out of 400 (98%) had definite or possible RA!

This means more patients! ~25% more subjects with the complete algorithm: 3,585 subjects (3,334 with true RA) 3,046 subjects (2,680 with true RA)

Liao et (2010) Arth. Care Research Characteristicsi2b2 RACORRONA total number 3,5857,971 Mean age (SD) 57.5 (17.5)58.9 (13.4) Female (%) Anti-CCP(%) 63N/A RF (%) Erosions (%) MTX (%) Anti-TNF (%) Clinical features of patients CCP has an OR = 1.5 for predicting erosions

4 million patients 31,171 patients ICD9 RA and/or CCP checked (goal = high sensitivity) 3,585 RA patients Classification algorithm (goal = high PPV) Discarded blood for DNA

Linking the Datamart-Crimson NLP data Codified data

OR similar in EMR cohort 1,500 RA multi-ethnic RA cases and 1,500 matched controls

Genetic risk score also similar

4 million patients 31,171 patients ICD9 RA and/or CCP checked (goal = high sensitivity) 3,585 RA patients Classification algorithm (goal = high PPV) Clinical subsets Discarded blood for DNA

Response to therapy

Non-responder to anti-TNF therapy NLP+codified data, together with statistical modeling, to define treatment response

Responder to anti-TNF therapy NLP+codified data, together with statistical modeling, to define treatment response

Responder to anti-TNF therapy 5-year NIH grant as part of the PharmacoGenomics Research Network (PGRN)

Conclusions

Options for clinical + DNA designClinical data DNASample size cost clinical trial +++ +$$$ registry $$ claims data +n/a+++$ EMR $ Conclusion: NLP + codified data, together with appropriate statistical modeling, can yield accurate clinical data.

Options for clinical + DNA designClinical data DNASample size cost clinical trial +++ +$$$ registry $$ claims data +n/a+++$ EMR $ Conclusion: Genetic studies in our EMR cohort yield effect sizes similar to traditional cohorts.

Options for clinical + DNA designClinical data DNASample size cost clinical trial +++ +$$$ registry $$ claims data +n/a+++$ EMR $ Conclusion: It should be possible to extend this same framework to classify response vs non-response to drugs used to treat RA.