Research Focus Area: 4. Secondary Use of EHR Data - Project Charter
Project Title/Name: / Data Normalization and Evaluation
Project Leads: / Dr. Christopher Chute, Dr. Stan Huff
Project Manager / Lacey Hart
Date: / July 20, 2010 – December 2010
To be completed during Project Approval Process
Portfolio:
Mayo Clinic Research - BSI PMO / Program:
SHARP Area 4 / Project Number:
Projects 1 & 6
Brief Project Background & Description: (What will this project do?) (255 characters):
- Data liquidity requires transformation of non-standard patient data into comparable consistent formats
- In practice, clinical data and provider information is unstructured and non-standard
- Overall Aim: Develop an open-source, dynamically configurable services framework to transform health information into standards-conforming, comparable, and consistent data
Objectives: (Problem or Opportunity Statement / Background of Project Need)
- Build generalizable data normalization pipeline
- Semantic normalization annotators involving LexEVS
- Establish a globally available resource for health terminologies and value sets
- Establish and expand modular library of normalization algorithms
- Consistent and standardized common model to support large-scale vocabulary use and adoption
- Support mapping into canonical value sets
- Normalize the data against CEMs.
- Normalize retrospective data from the EMRs and compare it to normalized data that already exists in our data warehouses (Mayo Enterprise Data Trust, Intermountain).
- Iteratively test normalization pipelines, including NLP where appropriate, against normalized forms, and tabulate discordance.
- Use cohort identification algorithms in both EMR data and EDW data.
- Sharing data through NHIN Connect and/or NHIN Direct
- Comparison of data processed through SHARP to data in existing Mayo and Intermountain data trust, EDW, AHR
- Evaluation of NLP outputs and value? Focus on a specific domain: X-rays, operative notes, progress notes, sleep studies?
Project Scope:
IN Scope / OUT of ScopeList items/functionality to be accomplished here / List all exclusions (out of scope) here
Use case evaluation for data element extraction / Scientific use case validation
Data class identification/prioritization / New information models
Generalizable data normalization pipeline / Disease specific widgets?
Normalization annotators
standardized common model & mapping
Iteratively test normalization pipeline
NHIN connection
Preliminary Timeline: (Enter any applicable milestone or deliverable dates)
Milestone or Deliverable / Target Completion DateCharter Approved / 7/27/2010
Identify Use Cases / 7/27/2010
Seek Common data elements and classes of data / 8/11/2010
Prioritize list of classes & desired widgets / 8/18/2010
Evaluate normalization tools & models (i.e. Regenstrief) / 9/1/2010
Define normalization templates (invoke CEMs, etc) / 9/1/2010
PAD& T2D Widgets for HTP Team / 10/2010
PE & PNA Widgets for HTP Team / 12/2010
Define infrastructure information model framework / TBD
Define role of normalized data in NHIN connect / TBD
Roles and Responsibilities: (Enter the estimated resources needed to initiate the project)
Team Roles / Resource Skill Set Needed / Name / FTE neededLead / Christopher Chute / 5%
Lead / Stan Huff / 5%
PM / Lacey Hart / 5%
IT Arch / Tom Johnson / 5%
Phenotyping / Jyoti Pathak
Cui Tao
Agilex / Kyle Marchant
Agilex / Les Westberg
MN HIE / Mike Ubl
Peter Haug
Tom Oniki
Dependencies/Assumptions/Risks/Constraints: (Enter any known or anticipated points to communicate)
- High dependency on NLP, HTP and Infrastructure project resources.
- Dependent upon IRB approval at both Utah and Mayo
Terms:
•AHR: Analytic Health Repository
•CEM: Clinical Element Model
•Decision Support Related:
–CER: Comparative Effectiveness Research (cost excluded)
–HTA: Health Technology Assessment (cost benefit/effectiveness)
–QI: Quality Improvement (health care operations)
–CDS: Clinical Decision Support (bedside)
•ETL: Extract Transform Load
•NHIN: Nationwide Health Information Network
Endorsement:
Endorsed Not Endorsed Deferred until ______
Comments (Enter endorsement mechanism and any other comments)
Title / Signature / DateProject Owner(s): / ______/ ______
Project Manager: / ______/ ______
Version 1.0Page 1 of 310/6/2018