For Group Health HSRC to Complete:
Proposal Number: HS______
Date Received: ______
FDA Y N

RESEARCH AND HUMAN SUBJECTS REVIEW APPLICATION: RECORDDATA ONLY

(USE ONLY FOR STUDIES OF EXISTING DATA, NOT SPECIMENS)

PROJECT TITLE

SHARP Area 4: Secondary Use of EHR Data
INVESTIGATOR NAME, TITLE,POSITION (Responsible for conduct of research at Group Health)
David S. Carrell, PhD, Multi-Institutional Research Consultant
INVESTIGATOR ADDRESS, PHONE, EMAIL
Group Health Research Institute
1730 Minor Ave, Suite 1600
Seattle, WA 98101-1448
Phone: 206.287.2705
E-mail: / APPLICANT ORGANIZATION
Group Health Research Institute
1730 Minor Ave, Suite 1600
Seattle, WA 98101-1448
GHRI CONTACT INVESTIGATOR/PROJECT MANAGER (if different from above) NAME, ADDRESS, PHONE, EMAIL
Gabrielle Gundersen
E-mail:
PROJECT PERIOD / GROUP HEALTH INVOLVEMENT PERIOD
FROM:
TO: / 04/01/2010
03/31/2014 / FROM:
TO: / 04/01/2010
03/31/2014
FUNDING STATUS / FUNDED UNDER REVIEW NOT TO BE FUNDED
TOTAL DIRECT COSTS AT GROUP HEALTH / $ 431,065
CERTIFICATION
INVESTIGATOR ASSURANCE: I acknowledge that I am the Investigator responsible for the conduct of this research at Group Health. I certify that the statements herein are true, complete and accurate to the best of my knowledge. I confirm that I will report any serious or unanticipated adverse effects, problems, or protocol deviations. I acknowledge that no changes will be put into effect without prior approval from the HSRC. I will renew this application with the HSRC as directed by the HSRC but no less than annually. I will conduct the research project in compliance with the HSRC conditions of approval. I understand that procedures described in the original grant application will only be implemented if they are also described in this application and approved by the IRB. I acknowledge that this research project will not be put into effect and no confidential records, data or specimens will be used until the research receives final approval from the HSRC.
Signature of Investigator / Date

Need help, instructions, or copies of documents from the GHRI Intranet? Email .

All HSRC correspondence will be sent to the investigator with a copy to the project manager, if known.

TABLE OF CONTENTS

Please complete this form and include all necessary materials in the order listed below. After you have assembled all of these materials, paginate them consecutively and type and/or handwrite the page numbers in the right hand column of the Table of Contents.Data collection instruments may be paginated separately.

Please indicate which of the items listed below are relevant to and included with this application, using the following annotations, in the left hand column below:

A = attached

F = will be submitted for future review

N/A = not applicable to this particular study

PAGE #

ACompleted Research/Human Subjects Review Application...... 3

Supplement C – Research Use of the Internet and E-mail......

N/ASupplement D – HIPAA Checklist......

AInvestigator biographical sketch(es) (please limit to 4 investigators*, 4 pages per biosketch)......

ABudget for work to be done at Group Health (you may black out individual salaries)......

ABudget justification (indicate N/A if not required for the proposal)......

Letters of Support from Group Health sponsor or collaborator (if available) ......

N/ARecruitment flow chart ......

N/AWritten consent form(s)......

N/AHIPAA Authorization Form for use and release of health information......

Data collection instruments including:

N/AMedical record abstraction form......

Other

Other (Describe):

N/A1 copy of complete grant application (including appendices) if project is federally funded ANDif Group Health

is prime recipient of grant funds or if the HSRC is the only IRB reviewing the study

*If Group Health is the IRB of record for other sites, please also include a biosketch for each lead investigator at those sites.

FUNDING INFORMATION

Please list all funding, current and pending, for this research application. Use additional sheets as necessary.

Funding Type:

Research Grant Fellowship Training Grant Contract Other, specify:

Funding Agency:The Office of the National Coordinator for Health Information Technology (ONC)

Principal Investigator (on proposal): Christopher Chute

Grant Number:

Proposal Title:

Status: NewStart Date: 04/1/2010End Date: 03/31/2014Funded: Yes No

Competing continuation

Non-competing continuation

Is the source of this funding federal? Yes No

What institution is the prime recipient of these funds?Mayo Clinic Research

If Group Health is the prime recipient, please list all institutions that will be sub-recipients of funds on this award:

N/A – GHRI is not prime.

Funding Type:

Research Grant Fellowship Training Grant Contract Other, specify:

Funding Agency:

Principal Investigator (on proposal):

Grant Number:

Proposal Title:

Status: NewStart Date:End Date:Funded: Yes No

Competing continuation

Non-competing continuation

Is the source of this funding federal? Yes No

What institution is the prime recipient of these funds?

If Group Health is the prime recipient, please list all institutions that will be sub-recipients of funds on this award:

0.0INVOLVED ORGANIZATIONS, INVESTIGATORS AND IRBS

If this application describes multiple study phases or subprojects, please answer the following questions separately for each phase or subproject. Please use additional sheets as necessary. Note: Sometimes cooperative arrangements are possible when multiple IRBs are reviewing the same study. Contact the Human Subjects Office if this seems relevant to your study.

  1. List all institutions that are performance sites (i.e., places where data are collected or subjects are recruited/enrolled) and identify which IRB will be reviewing for each site.

Childrens Hospital Boston (local IRB)

Mayo Clinic (local IRB)

University of PittsburghMedicalCenter (local IRB)

University of Utah/Intermountain Health Care(local IRB)

Seattle Group Health (local IRB)

2.List all Group Health investigators involved in this study.

David Carrell, PhD

3.List all non-Group Health investigators involved in this study. Also, list their institutional affiliation as related to this study.

Investigator / Institution
Chris Chute, MD, DrPH / Principal Investigator, Mayo Clinic
Guergana Savova, PhD / Co-investigator, ChildrensHospitalBoston, HarvardMedicalSchool
Jim Martin, PhD / Co-investigator, University of Colorado
Martha Palmer, PhD / Co-investigator, University of Colorado
Wayne Ward, PhD / Co-investigator, University of Colorado
Wendy Chapman, PhD / Co-investigator, University of California, San Diego
Peter Haug, PhD / Co-investigator, University of Utah
Peter Szolovits, PhD / Co-investigator, MIT
Ozlem Uzuner, PhD / Co-investigator, State University of New York, Albany

4.List any other consultants and/orinstitutions involved in this study not mentioned above.

NA

5.Is Group Health/Group Health Research Institute the prime grant/contract recipient or the coordinating center for the activities described in this application?

YES NO

If YESand if federally funded, attach the grant applicationOR if the grant application was already reviewed by the HSRC as part of another application, list the HS# here.

1.0FINANCIAL INFORMATION AND STUDY IMPACT ON GROUP HEALTH

Conflict of Interest

1.1Does any member of the research team, or their immediate family, have significant financial interest* in the research or its products that could be affected by the outcome of the research (e.g., consulting fees, honoraria, patents, copyrights, and royalties from those rights)?

YES NO

1.2Does any member of the research team, or their immediate family, have a financial interest in the sponsor of the research (e.g., equity interest, speakers’ bureau, financial compensation for services)?

YES NO

1.3Does any member of the research team, or their immediate family, have any other financial interests that could possibly affect, or be perceived to affect, the results of the research or other activities funded or proposed for funding?

YES NO

If YES to any item above, submit a description of the financial interest (this can be a copy of the disclosure statement to institutional officials) as an attachment to the end of this proposal. Provide documentation that institutional officials have cleared conflict of interest issues. If there are significant financial interests that require management by the institution, describe the institutional plans for managing the conflict of interest.

1.4Is it possible that a commercial product or patent could derive from the research or use of research participants’ data?

YES NO

If YES, explain the possible commercial applications of research. Explain if there are any plans to compensate research participants if research results lead to commercialization of research.

*“Significant financial interest”is defined as any interest valued at greater than $10,000 and, irrespective of value, any equity or ownership interest of more than five percent in any single entity held in aggregate by an Investigator and the Investigator’s spouse or dependent children.

Contract Information

1.5Will this project be conducted under a contractual agreement with Group Health (e.g., federal or foundation grant, federal or business contract, subcontract to another institution, etc.)?

YES NON/A Internally funded

If NO, please submit a “Confidentiality and Security Agreement” signed by each person who will have access to Group Health data and is not a Group Health employee.

Study Impact on Group Health

1.6 Will this study involve Group Health resources or facilities beyond Group Health Research Institute (GHRI)?

YES NO

If YES, please list.

1.7List any Group Health staff persons (outside ofGHRI) who are collaborating on this project (i.e., clinic staff, pharmacy staff, laboratory staff, etc.)

N/A

1.8Will this study have an impact on the delivery of health care at Group Health or on health care providers at Group Health?

YES NO

If YES, please respond to the following questions:

a.Briefly describe impact on Group Health delivery system providers and/or other staff.

b.What steps have you taken or will you take to minimize impact of the study on the care delivery system (i.e., consultations with relevant staff RE study procedures, departmental sign-off, etc.)?

  1. If relevant, what steps will you take to facilitate coordination of care, so the patient’s (study participant’s) health care is not negatively affected? (i.e., communications with physicians/staff, putting limited study information, such as vaccinations, in medical record, etc.)
  1. Group Health has a policy on coverage for experimental or investigational treatments (See Policy C-01-008) and there are limits on Medicare coverage of clinical trials. Therefore, please provide assurance that you will get approval of the study consent form by Group Health’s Legal Department prior to implementing the study if it is an investigational drug or device trial.

1.9Is there anything about the nature of this study which, if revealed to the public, could put Group Health at risk or competitive disadvantage? (Examples: publishing rates of medical errors, cost of particular services or procedures, or proprietary information. Think front page of the newspaper.)

YES NO

If YES, please briefly describe the risk(s) and how this will be mitigated (i.e., Group Health leaders are involved in project design, GHRI Director or other GH leadership will sign off prior to publication, etc.)

This study will use de-identified clinical text such as physician chart notes on Group Health patients. Revealing this fact to the public presents no risk or disadvantage to Group Health. There is no plan to reveal the de-identified clinical text to the public, and even if it were mistakenly revealed, as de-identified clinical text it would not cause harm/disadvantage. However, if there is a possibility, though very small, that a combination of mistakes could result in harm or disadvantage to Group Health. This would be the case if both of the following events took place:

  1. A de-identification failure occurred prior to sharing documents with other sites. A “failure” is a mistake in the de-identification process that results in one or more patient identifiers being mistakenly left in a clinical document that was intended to be de-identified.
  2. An unintended disclosureoccurred whereby one or more documents with de-identification failures was revealed to one or more persons not involved in the project.

1.10Does this study involve any high risk methods or clinical procedures (such as investigational drugs, devices, or procedures; radiation safety concerns; novel interventions with patients, etc.) that could increase liability risks for Group Health?

YES NO

If YES,please describe the risk(s) and how this will be managed.

1.11Please briefly describe why you believe it is appropriate to conduct this study at Group Health (given Group Health’s mission and business purpose).

This is a methods development project. The methods developed include various automated technologies used to extract data from electronic medical records—including clinical text—useful for conducting research and improving patient care. These aims are consistent with and may make positive contributions to Group Health’s interests in self-improvement as a “learning health care system.”

2.0TRAINING IN THE PROTECTION OF HUMAN SUBJECTS

Investigators and all key personnel are required to complete training on the protection of human subjects. Individuals working on research projects at Group Health, even if they are employees of another institution, may complete this training on the web at by signing in under Group Health Cooperative. (More detailed information on training is available here.)

Please check one or both of the following:

Below (or attached) is a list including the names of each investigator and key personnel responsible for the design and conduct of the study; the title of the education program completed by each named personnel; and the date he/she completed the training. Please do not send actual certificates of training for each person.

PersonnelRoleEd ProgramDate Completed

David CarrellPICITI9/14/2009

Below (or attached) is the plan, including a timeline, for completion of a training program by any project investigator or key personnel who has not yet received training.

3.0 RESEARCH DESCRIPTION (This section should not exceed 7 pages.)

Study Abstract

Strategic Health IT Advanced Research Projects (SHARP) Research Focus Area: 4. Secondary Use of EHR Data

We propose research that will generate a framework of open-source services that can be dynamically configured to transform EHR data into standards-conforming, comparable information suitable for large-scale analyses, inferencing, and integration of disparate health data. We will apply these services to phenotype recognition (disease, risk factor, eligibility, or adverse event) in medical centers and population-based settings. Finally, we will examine data quality and repair strategies with real-world evaluations of their behavior in Clinical and Translational Science Awards (CTSAs), health information exchanges (HIEs), and National Health Information Network (NHIN) connections.

We have assembled a federated informatics research community committed to open-source resources that can industrially scale to address barriers to the broad-based, facile, and ethical use of EHR data for secondary purposes. We will collaborate to create, evaluate, and refine informatics artifacts that advance the capacity to efficiently leverage EHR data to improve care, generate new knowledge, and address population needs. Our goal is to make these artifacts available to the community of secondary EHR data users, manifest as open-source tools, services, and scalable software. In addition, we have partnered with industry developers who can make these resources available with commercial deployment. We propose to assemble modular services and agents from existing open-source software to improve the utilization of EHR data for a spectrum of use-cases and focus on three themes: Normalization, Phenotypes, and Data Quality/Evaluation. Our six projects span one or more of these themes, though together constitute a coherent ensemble of related research and development. Finally, these services will have open-source deployments as well as commercially supported implementations.

There are six strongly intertwined, mutually dependent projects, including: 1) Semantic and Syntactic Normalization; 2) Natural Language Processing (NLP); 3) Phenotype Applications; 4) Performance Optimization; 5) Data Quality Metrics; and 6) Evaluation Frameworks. The first two projects align with our Data Normalization theme, while Phenotype Applications and Performance Optimization span themes 1 and 2 (Normalization and Phenotyping); while the last two projects correspond to our third theme.

Specific Aims

3.1Describe the short- and long-term objectives of this research.

The project that Group Health is involved in is described in the abstract (see section 3.0 above) as “Natural Language Processing (NLP).” NLP is the use of automated computing technologies to gather useful information from text that mimics a human process, such as when trained chart abstractors read charts to manually abstract research information. The overall aim is to create tools and methods to support the secondary use of clinical information contained in EMRs support health

The short-term objective(Aim 1, years 1 and 2) is to discover the relevant mentions in clinical text of “named entities” that refer to particular medical conditions or health care events. The long-term objective (Aim 2, years 3 and 4) is to use these named entities to discover the relations between them, which is necessary for identifying the clinically relevant information to be extracted.

The specific aims stated in the project proposal, are:

Specific Aims. Specific Aim 1: Clinical event discovery from the clinical narrative consisting of (1) defining a set of clinical events and a set of attributes to be discovered, (2) identifying standards to serve as templates for attribute/value pairs, (3) creating a "gold standard" through the development of annotation schema, guidelines, and annotation flow, and evaluating the quality of the gold standard, (4) identifying relevant controlled vocabularies and ontologies for broad clinical event coverage, (5) developing and evaluating a methodology for clinical event discovery and template population, (6) extending Mayo Clinic's clinical Text Analysis and Knowledge Extraction System (cTAKES) information model13, and implementing best-practice solutions for clinical event discovery.

Specific Aim 2: Relation discovery among the clinical events discovered in Aim 1 consisting of (1) defining a set of relevant relations, (2) identifying standards-based information models for templated normalization, (3) creating a gold standard through the development of an annotation schema, guidelines, and annotation flow, and evaluating the quality of the gold standard, (4) developing and evaluating methods for relation discovery and template population, (5) implementing high-throughput scalable phenotype extraction solutions as annotators in cTAKES and UIMA-AS, either within an institution’s local network or as a cloud-based deployment integrated with the institution’s virtual private network.