260 likes | 388 Views
Clinical Element Models (CEMs). SHARP F2F Meeting Mayo Clinic June 21, 2010 Stanley M Huff, MD. A Simple Model. Use of detailed clinical models in SHARP. Guide for data normalization widgets Target for structured output from NLP Logical structure for data payload in NHIN Connect services
E N D
Clinical Element Models (CEMs) SHARP F2F Meeting Mayo Clinic June 21, 2010 Stanley M Huff, MD
Use of detailed clinical models in SHARP • Guide for data normalization widgets • Target for structured output from NLP • Logical structure for data payload in NHIN Connect services • Reference for data that participates in the phenotype logic and queries
Patient, Employee, Provider, Organization, ContactParty, PatientContact (visit), ServiceDeliveryLocation, AdmitDiagnosis HealthIssue (Problem), Allergy, Intolerance, Document Order OrderLab, OrderLabMicro, OrderBloodProduct OrderMedAmb, OrderMedCont, OrderMedInt, OrderMedPCA, OrderMedReg OrderNutrition, OrderRadiology, OrderNursing, OrderRepiratory, OrderTherapies LabObs, MicroLabObs, Assert, Eval, Meas, Proc Qualifiers, Modifiers (Subject), Attributions, Panels Model Classes Created
Number of models created - 4384 Laboratory models – 2933 Evaluations – 210 Measurements – 353 Assertions – 143 Procedures – 87 Qualifiers, Modifiers, and Components Statuses – 26 Date/times – 27 Others – 400+ Panels – 79 Model Subtypes Created
Send me an email and I will send you a zip file stan.huff@imail.org Web browser www.clinicalelement.com Works best with Mozilla Firefox browser Access to the models
Dry Wet Ideal What if there is no model? Site #1 70 70 kg Dry Weight: Site #2 70 70 kg Weight:
Patient Identifier Patient Identifier Date and Time Date and Time Observation Type Observation Type Weight type Observation Value Observation Value Units Units 123456789 123456789 7/4/2005 7/4/2005 Weight Dry Weight Dry 70 70 kg kg 123456789 123456789 7/19/2005 7/19/2005 Weight Current Weight Current 73 73 kg kg Relational database implications How would you calculate the desired weight loss during the hospital stay?
SNOMED ICD-10 RxNorm FDB LOINC CPT SNOMED LOINC FDB RxNorm CPT ICD-10 Context Specific Mapping Tables Internal Terminology (ECIDS) Mayo Thesaurus ECIS Thesaurus IH Thesaurus Models Models and Concepts LexGrid Terminology Server Model Centered Data Representation
We assume that the model is used in association with a terminology server.
Model and Terminology Instance data Model MedicationOrder { drug PenVK, dose 250, route Oral, frequency Q6H, startTime 09/01/95 10:01, endTime 09/11/95 23:59, orderedBy Don Jones, M.D., orderNumber A234567 } MedicationOrder ::= SET { drug Drug, dose Decimal, route DrugRoute, frequency DrugFrequency, startTime DateTime, endTime DateTime, orderedBy Clinician, orderNumber OrderNumber} If the medicationOrder.drug is_a “antibiotic” then notify the infection control officer.
Concept Semantic Network Drugs Cardiovascular Analgesics Antibiotics Aminoglycosides Penicillins Cephalosporins Pen VK Amoxicillin Nafcillin
Denormalized Semantic Network Drugs has-child Antibiotics Drugs has-child Analgesics Drugs has-child Cardiovascular Antibiotics has-child Penicillins Antibiotics has-child Cephalosporins Antibiotics has-child Aminoglycosides Penicillins has-child Pen VK Penicillins has-child Amoxicillin Penicillins has-child Nafcillin Drugs has-member Antibiotics Drugs has-member Penicillins Drugs has-member Pen VK Drugs has-member Amoxicillin Drugs has-member Nafcillin
Mods - Component CE’s which change the meaning of the Value Choice. Quals - Component CE’s which give more information about the Value Choice. Mods and Quals of the Value Choice
<cetype name="BloodPressurePanel" kind="panel"> <key code="BloodPressurePanel_KEY_ECID" /> <item name="systolicBloodPressureMeas" type="SystolicBloodPressureMeas" card="0-1" /> <item name="diastolicBloodPressureMeas" type="DiastolicBloodPressureMeas" card="0-1" /> <item name="meanArterialPressureMeas" type="MeanArterialPressureMeas" card="0-1" /> <qual name="methodDevice" type="MethodDevice" card="0-1" /> <qual name="bodyLocationPrecoord" type="BodyLocationPrecoord" card="0-1" /> <qual name="bodyPosition" type="BodyPosition" card="0-1" /> <qual name="relativeTemporalContext" type="RelativeTemporalContext" card="0-M" /> <qual name="patientPrecondition" type="PatientPrecondition" card="0-M" /> <mod name="subject" type="Subject" card="0-1" /> <att name="observed" type="Observed" card="0-1" /> <att name="reportedReceived" type="ReportedReceived" card="0-1" /> <att name="verified" type="Verified" card="0-1" /> … </cetype> XML Model with Term Binding The name of this model Binding to a single “observable” concept
<constraint path="qual.methodDevice.data.cwe.domain" value="BloodPressureMeasurementDevice_DOMAIN_ECID" /> <constraint path="qual.bodyLocationPrecoord.data.cwe.domain" value="BloodPressureBodyLocationPrecoord_DOMAIN_ECID" /> Binding to a “domain” (value set) Path to the coded element The name of the terminology “domain” that the element is “bound” to
HTML Compiler XML Template Java Class “In Memory” Form CEML Source File CE Translator UML? openEHR Archetype? HL7 RIM Static Models? OWL?
Decomposition Mapping Precoordinated Model (User Interface Model) SystolicBPRightArmSitting SystolicBPRightArmSittingObs 138 mmHg data Post coordinated Model (Storage Model) SystolicBP SystolicBPObs 138 mmHg data quals BodyLocation BodyLocation Right Arm data PatientPosition PatientPosition Sitting data
“Chest pain made worse by exercise” Two events, but very close association Normally would go into a single finding “Ate a meal at a restaurant and 30 minutes later he felt nauseated, and then an hour later he began vomiting blood.” Discrete events with known time and potential causal relationships May need to be represented by multiple associated findings Semantic links are used to represent relationships between distinct event instances How much data in a single record?
InstanceId 1RelationshipInstanceId 2 (123) Nausea followed-by (987) Vomiting Representation of Semantic Links • Semantic links can also have certainty and attribution • Certainty • Attribution (who or what asserted the relationship, when, and why?)
Terminology Services (including CEMs) Using NHIN for transmitting data Detailed Model And the Internet for managing Content Patient Patient EMR 1b EMR 1a Billing Billing Imaging Imaging Facility a Internet Providr Providr EMR 2b EMR 2a Claims Claims Sched Sched Facility Facility Lab Lab Rx Rx …. …. Terminology, Models, Logic, NLP Semantics, etc. Normalized Data Instances Canonical EMR+ NHIN EDW Staging ETL ETL + Rules Normalization Widgets Normalization Widgets NLP Widgets NLP Widgets Analytic Health Repository Normalized Data Instances Normalized Data Instances Decision Support CER HTA QI CDS Facility b
Discussion • Evaluation projects • Sharing data through NHIN Connect and/or NHIN Direct • What, who, when, where? • Comparison of data processed through SHARP to data in existing Mayo and Intermountain data trust, EDW, AHR • What, who, when, where? • Others? • Evaluation of NLP outputs and value? Focus on a specific domain: X-rays, operative notes, progress notes, sleep studies? • Questions • What is the target set of normalization widgets that we want to build? • Can we do the evaluations on de-identified data? • Do we need patient consent to do the evaluations? • Others?