High-Throughput Phenotyping from EHRs The SHARPn “phenotyping funnel” ©2012 MFMER | slide-1 Phenotype specific patient cohorts DRLs QDMs CEMs Intermountain EHR data Mayo Clinic EHR data [Welch et al., JBI 2012; 45(4):763-71]
High-Throughput Phenotyping from EHRs
The SHARPn “phenotyping funnel”
©2012 MFMER | slide-1
Phenotype specific patient cohorts
DRLs
QDMs CEMs
Intermountain EHR data
Mayo Clinic EHR data
[Welch et al., JBI 2012; 45(4):763-71]
High-Throughput Phenotyping from EHRs
Data Transform Transform
Algorithm Development Process - Modified
Phenotype Algorithm
Visualization
Evaluation
NLP, SQL
Rules
Mappings
Semi-Automatic Execution
©2012 MFMER | slide-2
• Standardized representation of clinical data
• Create new and re-use existing clinical element models (CEMs)
• Standardized and structured representation of phenotype definition criteria
• Use the NQF Quality Data Model (QDM)
• Conversion of structured phenotype criteria into executable queries
• Use JBoss® Drools (DRLs)
[Welch et al., JBI 2012; 45(4):763-71]
High-Throughput Phenotyping from EHRs
Clinical Element Models Higher-Order Structured Representations
©2012 MFMER | slide-3
[Stan Huff, IHC]
High-Throughput Phenotyping from EHRs
[Stan Huff, IHC]
CEMs available for patient demographics, medications, lab measurements, procedures etc.
©2012 MFMER | slide-6
SHARPn data normalization pipeline - II
CEM MySQL database with standardized and normalized patient data
[Welch et al., JBI 2012; 45(4):763-71]
High-Throughput Phenotyping from EHRs
Data Transform Transform
Algorithm Development Process - Modified
Phenotype Algorithm
Visualization
Evaluation
NLP, SQL
Rules
Mappings
Semi-Automatic Execution
©2012 MFMER | slide-7
• Standardized representation of clinical data
• Create new and re-use existing clinical element models (CEMs)
• Standardized and structured representation of phenotype definition criteria
• Use the NQF Quality Data Model (QDM)
[Welch et al., JBI 2012; 45(4):763-71]
High-Throughput Phenotyping from EHRs
NQF Quality Data Model (QDM) • Standard of the National Quality Forum (NQF)
• A structure and grammar to represent quality measures and phenotype definitions in a standardized format
• Groups of codes in a code set (ICD-9, etc.) • "Diagnosis, Active: steroid induced diabetes" using
"steroid induced diabetes Value Set GROUPING (2.16.840.1.113883.3.464.0001.113)”
• Supports temporality & sequences • AND: "Procedure, Performed: eye exam" > 1 year(s)
starts before or during "Measurement end date"
• Implemented as a set of XML schemas • Links to standardized terminologies (ICD-9, ICD-10,
SNOMED-CT, CPT-4, LOINC, RxNorm etc.)
©2012 MFMER | slide-9
High-Throughput Phenotyping from EHRs
Example: Diabetes & Lipid Mgmt. - II
©2012 MFMER | slide-11
Human readable HTML
High-Throughput Phenotyping from EHRs
Example: Diabetes & Lipid Mgmt. - V
©2012 MFMER | slide-14
Computer readable XML (based on HL7 RIM semantics)
High-Throughput Phenotyping from EHRs
Data Transform Transform
Algorithm Development Process - Modified
Phenotype Algorithm
Visualization
Evaluation
NLP, SQL
Rules
Mappings
Semi-Automatic Execution
©2012 MFMER | slide-15
• Standardized representation of clinical data
• Create new and re-use existing clinical element models (CEMs)
• Standardized and structured representation of phenotype definition criteria
• Use the NQF Quality Data Model (QDM)
• Conversion of structured phenotype criteria into executable queries
• Use JBoss® Drools (DRLs)
[Welch et al., JBI 2012; 45(4):763-71]
High-Throughput Phenotyping from EHRs
JBoss® Drools rules management system
©2012 MFMER | slide-16
• Represents knowledge with declarative production rules • Origins in artificial intelligence
expert systems • Simple when <pattern> then
<action> rules specified in text files
• Separation of data and logic into separate components
• Forward chaining inference model (Rete algorithm)
• Domain specific languages (DSL)
High-Throughput Phenotyping from EHRs
Example Drools rule
©2012 MFMER | slide-17
rule “Glucose <= 40, Insulin On” when $msg : GlucoseMsg(glucoseFinding <= 40, currentInsulinDrip > 0 ) then glucoseProtocolResult.setInstruction(GlucoseInstructionsGLUCOSE_LESS_THAN_40_INSULIN_ON_MSG); end
{binding} {Java Class} {Class Getter Method}
Parameter {Java Class}
{Class Setter Method}
{Rule Name}
High-Throughput Phenotyping from EHRs ©2012 MFMER | slide-18
[Li et al., AMIA 2012; (Epub ahead of print)]
The “executable” Drools workflow
©2012 MFMER | slide-19
[Li et al., AMIA 2012; (Epub ahead of print)]
http://phenotypeportal.org [Endle et al., AMIA 2012; (Epub ahead of print)]
1. Converts QDM to Drools
2. Rule execution by querying the CEM database
3. Generate summary reports