Analysis Normal Form A Standard Model for Aggregating Clinical Data - PowerPoint PPT Presentation

Analysis Normal Form A Standard Model for Aggregating Clinical Data for Analysis Keith E. Campbell, MD, PhD 1 , Tim Williams, BS 2 , Raja A. Cholan, MS 2 (1) Veterans Health Administration (2) Deloitte Consulting LLP

The Current Health IT Landscape A major contributing factor to high medical errors is inaccuracy in patient health care data in electronic health records (EHRs) due in part to a variety of clinical data models that exist. This inaccuracy in health care data has led to erroneous clinical decisions and patient safety issues. More than 250,000 deaths in the US are attributed to medical errors every year. There is an urgent need for widespread standard and consistent quality of health care. Source: Debourgh & Prion and HealthIT.gov

What is a Clinical Statement?  A definite and clear representation of a clinically-significant fact or situation that was observed to exist or happened, or that a particular procedure was requested  Expressed as a narrative that provides a written account that can be naturally read by humans, as well as a normal form which is a machine- processable representation

Example of Variation in Current Clinical Data Models

Variation in FHIR Observation Resources FHIR Observation Resource (EHR 1) FHIR Observation Resource (EHR 2) Patient identifier: [Identifier] Patient identifier: [Identifier] ... ... category: CodeableConcept category: CodeableConcept code: CodeableConcept <<Brachial artery code: CodeableConcept << Brachial Code Code - left Systolic blood pressure LOINC artery Systolic Blood Pressure LOINC [8546-4] >> [8508-4] >> ... ... value: Type[] << Quantity | value: Type[] << Quantity | Value Value CodeableConcept| 140 >> CodeableConcept| 140 >> interpretation: CodeableConcept << interpretation: CodeableConcept << ObservationInterpretationCodes+ >> ObservationInterpretationCodes+ >> ... ... bodySite: CodeableConcept << SNOMED CT bodySite: CodeableConcept << SNOMED CT Body Site Body Site brachial artery: laterality = left >> left brachial artery >> ... ... method: CodeableConcept << SNOMED CT method: CodeableConcept << SNOMED CT Method Method Vital Signs Monitor>> Vital Signs Monitor>> ... ... Device: Reference[] Device | Device: Reference[] Device | Device Device DeviceMetric DeviceMetric There are currently many ways to represent the same clinical statement

Analysis Normal Form (ANF) Design Principles  Simplicity: Simplicity of the entire system instead of just one area of the system  Consistency: Consistent representation of information that is commonly shared across models  Reusability: Architectural patterns should encourage class reusability where possible. Reusability may further refine encapsulation when composition is considered  Reducing Variability: Minimize arbitrary classification rules to eliminate ambiguities to allow a single representation of clinical data ANF’s Design Principles help standardize statement representation so that it is understandable, reproducible, and useful

Analysis Normal Form (ANF)  Applies a clean separation between statement and terminology concerns  Helps structure clinical information so that it is consistently represented when exchanged among systems  Normalizes a variety of clinical statements to a common normal form  HL7 ANF Informative Ballot was successfully published in 2019

Major Components of an ANF Statement  Topic  Defines the action (being performed or requested) or the result of that action  Needs to be able to exist on its own and still retain original intent and clarity of meaning  Each clinical statement may only have one topic (but the topic is a comprehensive expression)  Circumstance  HOW , WHY, WHEN, and with WHAT “result” a requested or performed action will be or was carried out  ANF promotes a normalized representation of observation or intervention results where all results are represented to a " measure "

ANF Statement as a FHIR Observation Extension FHIR Observation Resource (ANF)  Data elements for ‘body site’, Patient identifier: [Identifier] ... ‘method’, and ‘device’ may no longer category: CodeableConcept code: CodeableConcept <<[Observation be required Code procedure] – (Method) [Examination – action]- (Has focus)[Sitting systolic  Using ANF’s Topic component, this blood pressure]- [Procedure site – Direct] [Structure of left brachial artery]- (Using device) [Blood pressure contextual information can be cuff, adult size] >> ... modeled in FHIR’s ‘code’ data value: Type[] << Quantity | Value CodeableConcept| 140 >> element interpretation: CodeableConcept << ObservationInterpretationCodes+ >> ANF may reduce the variability of clinical statement representations , by shifting the complexity to terminology expressions

What Can ANF Be Used For?  Clinical Decision Support  Provide a standards-based, normalized representation of clinical statements  Use an objective measure to help evaluate the result, presence, and magnitude of a specific finding, request or observation  Classify the topic of a statement using standard terminology expressions  Data Analytics / Mining  Create normalized data natively  Transform representations of clinical statements to normal form (e.g. transform C-CDA templates, FHIR profiles to ANF) The ability to measure and improve outcomes relies on consistent, high-quality data that is aggregated from a variety of systems

Next Steps  Make ANF accessible so that statements can be represented as new FHIR extensions to existing resources for clinical decision support

Thank you  Read a copy of the HL7 ANF Informative Ballot Specification here: http://solor.io/anf  Contact Information  rajkumar.cholan@va.gov  keith.campbell@va.gov  http://solor.io/