Presentation HealthCom 2012

KNOWLEDGE ENGINEERING OF HEALTHCARE

APPLICATIONS BASED ON MINIMALIST MULTILEVEL

MODELS

EXPANDING THE SCOPE OF EHEALTH: FROM ELECTRONIC HEALTH RECORDS

TO BIOMEDICAL APPLICATIONS

Luciana Tricai CavaliniDepartment of Health Information TechnologyMedical Sciences CollegeRio de Janeiro State University

Timothy Wayne CookMLHIM Associated LaboratoryNational Institute of Science and Technology –Medicine Assisted by Scientific Computing

Healthcare systems are much more

complex than any other sector of human society,

regarding 3 dimensions:

Space

Time

Ontology

DYNAMICS AND COMPLEXITY IN HEALTHCARE

Healthcare is the only economic sector that deals with biological production processes (which are created by nature)

All other economic sectors deal with industrial production processes (which are created by the man)

Production processes that are created by the man are much simpler than the biological processes, because:

WHY HEALTHCARE IS SO COMPLEX?

See Dawkins R. The greatest show on earth, pp. 204-5, and Marx K. Complete works.

Evolution had millions of years to reach to that complexity

Civilization starts just dozens of thousands of years ago

Industrial systems are as simple as possible to maximize

profit

Biological systems are as complex as necessary to

guarantee the survival of the species

The greatest medical

terminology (SNOMED-CT) has more than 310,000 terms, connected by

more than 1,000,000 links

Thus, in medicine, there

are roughly 310,000

concepts, connected to each other by

millions of different ways

In practical terms; building a

“megalithic system” that all

healthcare settings could

use would require a great

amount of tables with

310,000 fields and millions of relationships

THE ONTOLOGICAL COMPLEXITY

Cavalini-Cook Conjecture: The probability of consensus between 2 or more experts from the same field regarding which would be the “maximum data model” for any given

healthcare concept tends to zero

This complexity turns a computer science problem that does not exist (or at least it is not critical) in any other sector of human society into a very important issue in healthcare.

This problem is:

THE CONSEQUENCES OF HEALTHCARE COMPLEXITY (1)

SEMANTICINTEROPERABILITY

- Cough- For 3

months- Low fever

Chest X-Ray:- Nodule in

right apex

BAL:- TB

Chest X-Ray:- Nodule in

right apex

BAL:- TB

- Cough- For 3

months- Low fever

- Cough- For 3

months- Low fever

Chest X-Ray:- Nodule in

right apex

Semantic interoperability in healthcare is not perceived as a problem by the vast majority of health

informaticians because:Apparently, it only concerns national governments, and

no country nowadays has the

required combination of

technical capability, political

will and transparency to

run a semantically interoperable

national ehealth project

Most software companies are

satisfied with their customer portfolio or still dream the old monopolistic dream of taking over the whole

global market for themselves

Academic projects are usually

focused on a very specific subject, and recording their data in

isolated silos is not seen as a

problem, because they do not regard their data as part of the patient’s

Life Health Record

A UNDERESTIMATED PROBLEM

Semantic interoperability is critical, but healthcare complexity brings another intractable issue even for self-contained systems: maintenanceIn healthcare, you define your data model today and it does not last 6 months, because healthcare concepts evolve fast and new concepts come along every dayIt is virtually impossible to make a customer satisfied with a default application; the requisites are completely different, even for the simpler cases (e.g. two NHS GPs)In real life, the average time for a medical software to be abandoned is 2 years and the abandon rate is 70% (source: CHAOS Report)

THE CONSEQUENCES OF HEALTHCARE COMPLEXITY (2)

MULTILEVEL MODELING APPROACHES

openEHR MLHIM 13606Models

Maximalist Minimalist ReductionistApproach

Maximum Any size MaximumData model

EMR Any applicationOnly message

exchangePossible implementation

Intense Minimal IntermediateRM residual context

KNOWLEDGE MODELING APPROACHES

openEHR MLHIM 13606Models

ArchetypeConcept

Constraint Definition (CCD)

ArchetypeStructure

One Any number One# of structures / concept

Top-down, consensus

Bottom-up,merit

Top-down, consensus

Governance model

ADL XML Schema ADLLanguage

THE MLHIM SPECIFICATIONS IMPLEMENTATION

The MLHIM Reference Model XML Schema Graphical representation

Examples of CCDs ICD-10 4-digit codes for Respiratory Tuberculosis (A15.-) Demography NCI Standard Template

The Data Model Converter to CCD

The CCD Repository Uploader

Code available at:www.mlhim.org or https://launchpad.net/mlhim

THANK YOU!

[email protected]

[email protected]

谢谢 !

OBRIGADA!