Clinical Element Models

1 /ECIS Title or job number /

04/22/23

Clinical Element Models

W3C Semantic WebHealthcare and Life Sciences Interest Group

November 8, 2007

Tom Oniki, PhDSr. Medical Informaticist

Intermountain HealthcareSalt Lake City, UT


04/22/23

Acknowledgements

Stan Huff, Joey Coyle, Craig Parker, Yan Heras, and many others


04/22/23

Intermountain HealthcareHealth Delivery Network, not-for-profit

Serving Utah and Southern Idaho

21 Hospitals/ 2105 beds/150 Clinics

Medical Group of 550 employed physicians

Insurance plan of 500,000 covered lives

$85M/year charitable care exclusive of bad debt

27,000 employees

Partner in the Utah Health Information Network


04/22/23

The essentials of the propositionThe need for the clinical models is dictated by what we want to accomplish as providers of health care

The best clinical care requires the use of computerized clinical decision support and automated data analysis

Clinical decision support and automated data analysis can only function against standard structured coded data

Detailed clinical models provide the standard structure and terminology needed for clinical decision support and automated data analysis

One important clinical decision support and automated data analysis use case is clinical trials recruitment


04/22/23

The Clinical Element ModelIntermountain Healthcare’s design for detailed clinical models

Evolution and refinement of The Clinical Event Model which Intermountain has been using for the past 12 years.• ~200 million instances of clinical data stored

in our repository.


04/22/23

What do we model using Clinical Element Models (CEMs)?

All data in the patient’s EMR, including:• Allergies• Problem lists• Laboratory results• Medication and diagnostic orders• Medication administration• Physical exam and clinical measurements• Signs, symptoms, diagnoses• Clinical documents• Procedures• Family history, medical history and review of symptoms


04/22/23

How will Clinical Element models be used?• Interfaces• Core services• Decision logic• Data entry screens, flow sheets, reports, ad hoc

queries

Does NOT dictate physical storage strategy


04/22/23

<cetype name="SystolicBloodPressureMeas"><key code="SystolicBloodPressureMeas_KEY_ECID"/><qual name="bodyPosition" card="0-1"/><constraint path="qual.bodyPosition.data.cwe.domain"

value="BloodPressureBodyPosition_DOMAIN_ECID"/><constraint path="data.pq.unit.domain"

value="PressureUnitOfMeasure_DOMAIN_ECID"/><constraint path="data.pq.unit.preferred" value="mmHg_ECID"/>

</cetype>

The Systolic Blood Pressure Example in CEML


04/22/23

The Clinical Element Model

Type - The name of a particular model

Key - Real world concept. Links model to an external coded terminology.

Value Choice - Possible ways to convey the model’s value.


04/22/23

Value Choice

Data - Value conveyed as an HL7 version 3 data type

Items - Value conveyed by multiple Clinical Elements collectively


04/22/23

Clinical Element

type

key

SystolicBloodPressureMeas (concept thatrepresents “our model for capturingsystolic blood pressure measurements”)

SystolicBloodPressure (“real world” concept;may be mapped to SNOMED code)

data 120 mm Hg

A Simple Observation


04/22/23

SystolicBloodPressureMeas

key SystolicBloodPressure (“real world” concept;may be mapped to SNOMED code)

data 120 mm Hg

A Simple Observation (shorthand)


04/22/23

BloodPressurePanel

key BloodPressure

items

A panel containing two observations


key SystolicBloodPressure

data 120 mmHg

DiastolicBloodPressureMeas

key DiastolicBloodPressure

data 80 mmHg


04/22/23

Qualifiers of the Value Choice

Qualifiers – CEM’s which give more information about the Value Choice.


04/22/23



data 120 mmHg

The use of Qualifiers


04/22/23



data 120 mmHg


quals

data Sitting

key BodyPosition

BodyPosition


04/22/23



data 120 mmHg


quals

data Sitting

key BodyPosition

BodyPosition

Controlled Terminology Codes!


04/22/23

Modeling Issues


04/22/23

Let’s see, I want to analyze numbness symptoms in neurological patients . . .

More than just groups of codes


04/22/23



Fortunately, we store SNOMED CT codes. I see this patient had:

– Numbness (44077006)– Right (24028007)– Arm (40983000)– Left (7771000)– Leg (30021000)


04/22/23



Fortunately, we store SNOMED CT codes. I see this patient had:

– Numbness (44077006)– Right (24028007)– Arm (40983000)– Left (7771000)– Leg (30021000)

But does this mean:•Numbness of right arm and left leg?•Numbness of left arm and right leg? •Numbness of both arms and legs?


04/22/23

What if Dry Weight is stored/accessed as:• A single name/code and value

– Dry Weight = 70 kg

Different ways to model

If Dry Weight > 70 kg, then . . .


04/22/23

What if Dry Weight is stored/accessed as:• A single name/code and value

– Dry Weight = 70 kg

• The combination of two names/codes and values

– Weight = 70 kg– Weight type = “dry”




04/22/23


If Dry Weight > 70 kg, then . . .IF(Dry Weight > 70 kgOR (Weight > 70 kg AND Weight type = “dry”)THEN . . .


04/22/23

IF(Dry Weight > 70 kgOR (Weight > 70 kg AND Weight type = “dry”)OR . . .are there any other ways??)THEN . . .




04/22/23

IF(Dry Weight > 70 kgOR (Weight > 70 kg AND Weight type = “dry”)OR . . .are there any other ways??)THEN . . .



We want to store only one way!


04/22/23

Stored/accessed as:• A single name/code and value

– Right Arm Cuff Systolic Blood Pressure = 120 mm Hg

• The combination of multiple names/codes and values

– Systolic Blood Pressure = 120 mm Hg– Body Location = “arm”

– Body Location Laterality = “right”– Device = “cuff”


Another example: “Systolic Blood Pressure Taken from the Right Arm with

a Cuff”


04/22/23

Even if we store it this way:– Systolic Blood Pressure = 120 mm Hg

– Body Location = “arm”– Body Location Laterality = “right”

– Device = “cuff”

A UI will want to present it this way:– Systolic Blood Pressure = 120 mm Hg

– Body Location = “right arm”– Device = “cuff”

We need a conversion mechanism – just like we need for converting to Clinical Trials

models!


Another example: “Systolic Blood Pressure Taken from the Right Arm with

a Cuff”


04/22/23



data 120 mm Hg


SystolicBloodPressureAssert

key Assertion

data “SystolicBloodPressure = 120 mm Hg”


04/22/23



data 120 mm Hg


SystolicBloodPressureAssert

key Assertion

data “SystolicBloodPressure = 120 mm Hg”


04/22/23

AsthmaAssert

key Assertion

data Asthma



04/22/23

HairColorMeas

key HairColor

data Blonde


HairColorAssert

key Assertion

data Blonde Hair Color


04/22/23

Common Processing

• Heart Rates and Blood Pressures both have body locations.• They aren’t the same body locations, but an

application may want to process them similarly, e.g., display them in the same column

• Do we create a parent “things with body locations”?

• Vision changes and Weight changes don’t have much in common.• But an application may want to display/capture

“things that have changed” since the last visit.• Do we create a parent “things that can change”?


04/22/23

Things we seek:• Explicit models for data elements – including

standardized coded terminology• A single way (or at least a very few well-

defined ways) to store/access a data element• A standard or “interlingua” for models that

make them shareable between institutions• Extensibility• Applications that address data generically


04/22/23

Status

• We’re in the process of creating models as part of our partnership with GE• We have very few of the items on the functional

requirements xls• We do not have any data stored against our

models yet• We can discuss creating the needed models

Questions?

Documents

Clinical Element Models