Download as PDF, PPTX
![Ontology-driven data organization allows simplistic data
models that paste together
i2b2 DB
[ Enterprise Project 1
Shared
Data ]
i2b2 DB
Shared data Ontology
Project 2
of Project 1
Consent/Tracking
of Project 2 Security
i2b2 DB
Project 3
of Project 3](https://image.slidesharecdn.com/murphyi2b2-indivo6-18-2012-120622103304-phpapp02/75/Secondary-Use-of-Healthcare-Data-for-Translational-Research-22-2048.jpg)
Uploaded byChildren's Hospital Informatics Program
Secondary Use of Healthcare Data for Translational Research
The document discusses the use of healthcare data for translational research, focusing on high throughput methods for patient selection and phenotype exploration using the i2b2 tool. It highlights collaborations across institutions and the integration of patient data for clinical trials, emphasizing the importance of engaging patients in research. Additionally, it describes the framework and benefits of utilizing i2b2 in organizing clinical data for improved research outcomes.
More Related Content
Similar to Secondary Use of Healthcare Data for Translational Research
Secondary Use of Healthcare Data for Translational Research
- 1. Secondary Use ofHealthcare Data for Translational Research Shawn Murphy MD, Ph.D. Indivo Conference June 18, 2012
- 2. Example: PPARγ Pro12Alaand Diabetes Oh et al. Deeb et al. Mancini et al. Clement et al. Hegele et al. Sample size Hasstedt et al. Lei et al. Ringel et al. Hara et al. Meirhaeghe et al. Overall P value = 2 x 10-7 Douglas et al. Altshuler et al. Mori et al. Odds ratio = 0.79 (0.72-0.86) All studies Estimated risk 0.2 0.4 0.6 0.8 1 1.2 1.4 1.6 1.8 2.0 (Ala allele) 0.1 0.3 0.5 0.7 0.9 1.1 1.3 1.5 1.7 1.9 Ala is protective Courtesy J. Hirschhorn
- 3. High Throughput Methodsfor supporting Translational Research Setof patients is selected from medical record data in a high throughput fashion Investigatorsexplore phenotypes of these patients using i2b2 tools and a translational team developed to work specifically with medical record data Distributed networks cross institutional boundaries for phenotype selection, public health, and hypothesis testing Working with Indivo for advancement of patient participation in Translational Research
- 4. High Throughput Methodsfor supporting Translational Research Setof patients is selected from medical record data in a high throughput fashion Investigatorsexplore phenotypes of these patients using i2b2 tools and a translational team developed to work specifically with medical record data Distributed networks cross institutional boundaries for phenotype selection, public health, and hypothesis testing Working with Indivo for advancement of patient participation in Translational Research
- 5. Research Patient DataRegistry exists at Partners Healthcare to find patient cohorts for clinical research Query construction in web tool 1) Queries for aggregate patient numbers - Warehouse of in & outpatient clinical data De- - 6.0 million Partners Healthcare patients identified - 1.5 billion diagnoses, medications, procedures, laboratories, & physical findings Data coupled to demographic & visit data Warehouse - Authorized use by faculty status - Clinicians can construct complex queries Z731984X Z74902XX - Queries cannot identify individuals, internally ... can produce identifiers for (2) ... Encrypted identifiers 2) Returns identified patient data OR 0000004 2185793 - Start with list of specific patients, usually from (1) ... 0000004 2185793 - Authorized use by IRB Protocol ... ... - Returns contact and PCP information, demographics, ... providers, visits, diagnoses, medications, procedures, Real identifiers laboratories, microbiology, reports (discharge, LMR, operative, radiology, pathology, cardiology, pulmonary, endoscopy), and images into a Microsoft Access database and text files.
- 6. Organizing data inthe Clinical Data Warehouse Star schema Binary Concept DIMENSION Patient DIMENSION concept_key concept_text search_hierarchy patient_key patient_id (encrypted) sex Tree Patient-Concept FACTS age patient_key birth_date concept_key race start_date deceased end_date ZIP Encounter DIMENSION practitioner_key encounter_key encounter_key value_type encounter_date numeric_value hospital_of_service textual_value abnormal_flag Pract . DIMENSION practitioner_key start name search service .16 6.0 150 .06 1500 million
- 7. FINDING PATIENTS Query items Person who is using tool Query construction Results - broken down by number distinct of patients
- 9. High Throughput Methodsfor supporting Translational Research Setof patients is selected from medical record data in a high throughput fashion Investigatorsexplore phenotypes of these patients using i2b2 tools and a translational team developed to work specifically with medical record data Distributed networks cross institutional boundaries for phenotype selection, public health, and hypothesis testing Working with Indivo for advancement of patient participation in Translational Research
- 10. The National Centerfor Biomedical Computing entitled Informatics for Integrating Biology and the Bedside (i2b2), what is it? Software for explicitly organizing and transforming person- oriented clinical data to a way that is optimized for clinical genomics research Allows integration of clinical data, trials data, and genotypic data A portable and extensible application framework Software is built in a modular pattern that allows additions without disturbing core parts Available as open source at https://www.i2b2.org
- 11. i2b2 Cell: TheCanonical Software Module Business Logic i2b2 Data Access Data Objects HTTP XML (minimum: RESTful)
- 12. An i2b2 Environment(the Hive) is built from i2b2 Cells “Hive” of software services provided by i2b2 cells B patient_dimension PK Patient_Num 1 observation_fact 1 PK visit_dimension Encounter_Num A patient_dimension PK Patient_Num Birth_Date Death_Date Vital_Status_CD 1 PK PK observation_fact Patient_Num ∞ PK Encounter_Num Concept_CD ∞ 1 PK visit_dimension Encounter_Num Start_Date End_Date Active_Status_CD Location_CD* Start_Date PK Observer_CD ∞ PK Patient_Num End_Date Age_Num* ∞ PK Start_Date Birth_Date ∞ PK Encounter_Num Gender_CD* ∞ ∞ observer_dimension Death_Date PK Concept_CD ∞ Active_Status_CD Race_CD* PK Modifier_CD Vital_Status_CD Location_CD* PK Instance_Num PK Observer_CD ∞ Ethnicity_CD* PK Observer_Path Age_Num* ∞ PK Start_Date End_Date Gender_CD* Race_CD* PK Modifier_CD ∞ ∞ observer_dimension ValType_CD Observer_CD PK Instance_Num TVal_Char Name_Char Ethnicity_CD* PK Observer_Path NVal_Num concept_dimension End_Date ValueFlag_CD ∞ ValType_CD Observer_CD Observation_Blob modifier_dimension PK Concept_Path C TVal_Char Name_Char NVal_Num ∞ PK Modifier_Path concept_dimension Concept_CD ValueFlag_CD ∞ Name_Char Observation_Blob modifier_dimension Modifier_CD PK Concept_Path Name_Char ∞ PK Modifier_Path visit_dimension Concept_CD patient_dimension Name_Char Modifier_CD PK Encounter_Num PK Patient_Num 1 observation_fact 1 Name_Char Start_Date PK Patient_Num End_Date Birth_Date ∞ PK Encounter_Num Death_Date PK Concept_CD ∞ Active_Status_CD Vital_Status_CD Location_CD* PK Observer_CD ∞ Age_Num* ∞ PK Start_Date Gender_CD* Race_CD* PK Modifier_CD ∞ ∞ observer_dimension PK Instance_Num Ethnicity_CD* PK Observer_Path End_Date ValType_CD Observer_CD TVal_Char Name_Char NVal_Num concept_dimension ValueFlag_CD ∞ PK Concept_Path Observation_Blob modifier_dimension ∞ local PK Modifier_Path Concept_CD Name_Char Modifier_CD Name_Char visit_dimension patient_dimension PK Encounter_Num PK Patient_Num 1 observation_fact 1 Start_Date PK Patient_Num End_Date Birth_Date ∞ PK Encounter_Num Death_Date PK Concept_CD ∞ Active_Status_CD Vital_Status_CD Location_CD* PK Observer_CD ∞ Age_Num* ∞ PK Start_Date Gender_CD* Race_CD* PK Modifier_CD ∞ ∞ observer_dimension PK Instance_Num Ethnicity_CD* Data PK Observer_Path End_Date ValType_CD Observer_CD TVal_Char Name_Char NVal_Num concept_dimension ValueFlag_CD ∞ PK Concept_Path Observation_Blob modifier_dimension ∞ Model PK Modifier_Path Concept_CD Name_Char Modifier_CD Name_Char remote Data Repository Cell
- 13. I2b2 Software componentsare distributed as open source
- 14. Set of patientsis selected through Enterprise Repository and data is gathered into a data mart Selected patients Project Data directly Data from other Data imported Specific EDR from EDR sources specifically for Phenotypic project Data Automated Queries search for Patients and add Data
- 15. Interogation can occurthrough i2b2 web client
- 16. Data is availablethrough the i2b2 Workbench
- 17. Team support forProjects Local sources Ex: BICS RPDR RPDR Local EDC Mart Clinical Final Project DB Analyst Biostatistician Programmer Project Manager Local data extract analyst RPDR Support Programmers
- 18. Natural Language Processing SOCIAL HISTORY: The patient is married with four grown daughters, Smoker uses tobacco, has wine with dinner. SOCIAL HISTORY: The patient is a nonsmoker. No alcohol. Non-Smoker SOCIAL HISTORY: Negative for tobacco, alcohol, and IV drug abuse. BRIEF RESUME OF HOSPITAL COURSE: Past Smoker 63 yo woman with COPD, 50 pack-yr tobacco (quit 3 wks ago), spinal stenosis, ... SOCIAL HISTORY: The patient lives in rehab, married. Unclear smoking history from the admission note… ??? HOSPITAL COURSE: ... It was recommended that she receive …We also added Lactinax, oral form of Lactobacillus acidophilus to attempt a repopulation of her gut. Hard to pick SH: widow,lives alone,2 children,no tob/alcohol. Hard to pick
- 19. NLP Workflow I2b2 Project Investigators NLP Specialists
- 20. Research Investigator Workflowenabled by mi2b2 Query is done Derive new To find patients data from images Use i2b2 Request Study Images with Images Accession #’s BIRN/XNAT mi2b2 Images Retrieved from Clinical PACS
- 21. Builds complex “CustomStudy” displays
- 22. Ontology-driven data organizationallows simplistic data models that paste together i2b2 DB [ Enterprise Project 1 Shared Data ] i2b2 DB Shared data Ontology Project 2 of Project 1 Consent/Tracking of Project 2 Security i2b2 DB Project 3 of Project 3
- 23. Custom views supportsclinical trials in i2b2 A Patient-Centered View is welcomed by clinical researchers when they review patients for clinical trials The Patient-Centered View can be focused to support specific needs of each clinical trial review New Apps can be written to assist eligibility determination during the viewing of a patient
- 24. SMART Addition toi2b2 1. SMART Connect 2. REST SMART
- 25. A “Patient-Centered View”enabled by SMART
- 26.
- 27. Patient-Centered View canbe edited by user
- 28. High Throughput Methodsfor supporting Translational Research Setof patients is selected from medical record data in a high throughput fashion Investigatorsexplore phenotypes of these patients using i2b2 tools and a translational team developed to work specifically with medical record data Distributed networks cross institutional boundaries for phenotype selection, public health, and hypothesis testing Working with Indivo for advancement of patient participation in Translational Research
- 29. Community United States International Arizona State University Georges Pompidous Hospital, Paris, France Beth Israel Deaconness Hospital, Boston, MA Institute for Data Technology and Informatics (IDI), NTNU, Norway Boston University School of Medicine, Boston, MA Karolinska Institute, Sweden Brigham and Women's Hospital, Boston, MA University of Erlangen-Nuremberg, Germany Case Western Reserve Hospital University of Goettingen, Goettingen, Germany Children's Hospital, Boston, MA University of Leicester and Hospitals, England (Biomed. Res. Informatics Ctr. for (Denver) Children's Hospital, Denver, CO Clin. Sci) Children's Hospital of Philadelphia, PA University of Pavia, Pavia, Italy Childrens's National Medical Center (GWU) University of Seoul, Seoul, Korea Cincinnati Children's Hospital, Cincinnati, OH Cleveland Clinic, Cleveland, OH (Weil Medical College of) Cornell, NYC, NY Duke Medical College Group Health Cooperative Harvard Pilgrim Healthcare Harvard Medical School, Boston, MA Health Sciences South Carolina Kaiser Permanente Health Kimmel Cancer Center (Thomas Jefferson University) Massachusetts General Hospital, Boston, MA Maine Medical Center, Portland, ME Marshfield Clinic, Wisconsin Morehouse School of Medicine, Atlanta, GA Ohio State University Medical Center, Columbus, OH Oregon Health & Science University, Portland, OR Renaissance Computing Institute, Chapel Hill, NC South Carolina Clinical and Translational Research Institute Tufts Medical Center, Boston, MA University of Alabama University of Arkansas Medical School University of California Davis, Davis, CA University of California San Francisco, SF, CA University of Chicago University of Massachusetts Medical School, Worcester, MA University of Michigan Medical Center, Ann Arbor, MI University of Pennsylvania School of Medicine, Philadelphia, PA University of Rochester Medical Center, Rochester, NY University of Texas Health Sciences Center at Houston, Houston, TX University of Texas Health Sciences Center at San Antonio, SA, TX University of Texas Health Sciences Center Southwestern, Dallas, TX Utah Health Science Center, Salt Lake City, UT University of Washington, Seattle, WA University of Wisconsin Madison Veterans Administration Boston and Utah
- 30. Aggregating across 4hospitals, 3 i2b2 instances SHRINE (Shared Research Informatics Network) = Distributed Queries
- 31. Clinical data inSHRINE 10 years (2001-2011) 4 hospitals 6 million total patients >1 billion medical observations Demographics Diagnoses (ICD9-CM) Medications (RxNorm) Labs (LOINC)
- 32.
- 34. Query Health =I2b2 queries distributed to hospitals that may or may not be hosting i2b2
- 35. High Throughput Methodsfor supporting Translational Research Setof patients is selected from medical record data in a high throughput fashion Investigatorsexplore phenotypes of these patients using i2b2 tools and a translational team developed to work specifically with medical record data Distributed networks cross institutional boundaries for phenotype selection, public health, and hypothesis testing Working with Indivo for advancement of patient participation in Translational Research
- 36. Integration of i2b2and Indivo INDIVO PATIENT PUBLISH DATA FILTER PATIENT MATCH
- 37. Key new components PATIENT Allows patients permission to be attached MATCH to their records in i2b2 DATA Allows only specified parts of the i2b2 FILTER record on the patient to be viewed by the patient PATIENT Allows patients to publish their outcomes PUBLISH to i2b2 = WRITE BACK TO i2b2
- 38. Advantages for Patients Able to see data on themselves from medical record Important to learn lessons form Beth Israel – Microsoft Healthvault venture Integration can span across several institutions May be able to take advantage of SHRINE infrastructure SMART will allow integrated view to focus on patient’s illnesses and concerns Indivo may provide a way to return research results to patients
- 39. Advantages for Research Indivo makes it possible to collect Patient Reported Outcomes Can allow engagement of patient for recruitment for Clinical Trials
- 40. Collaborators RPDR Medical Imaging (mi2b2) Eugene Braunwald Christopher Herrick John Glaser David Wang Diane Keogh Bill Wang Henry Chueh i2b2 Driving Biology Projects I2b2 and SMART Vivian Gainer Isaac Kohane Victor Castro Susanne Churchill Raul Guzman Griffin Weber Robert Plenge Michael Mendis Scott Weiss Nich Wattanasin Stan Shaw Vivian Gainer John Brownstein Lori Phillips Qing Zeng Rajesh Kuttan Guergana Savova Wensong Pan Janice Donahue Query Health William Simons (SHRINE) Jeff Klann Andy McMurry (SHRINE) Doug McFadden (SHRINE) Ken Mandl (SMART) Josh Mandel (SMART)