44
Distributed, Knowledge- Based Temporal-Abstraction Mediation Yuval Shahar, M.D., Ph.D. Medical Informatics Research Center Department of Information Systems Engineering Ben Gurion University, Beer Sheva, Israel

Distributed, Knowledge-Based Temporal-Abstraction Mediation Yuval Shahar, M.D., Ph.D. Medical Informatics Research Center Department of Information Systems

Embed Size (px)

Citation preview

Page 1: Distributed, Knowledge-Based Temporal-Abstraction Mediation Yuval Shahar, M.D., Ph.D. Medical Informatics Research Center Department of Information Systems

Distributed, Knowledge-Based Temporal-Abstraction

Mediation

Yuval Shahar, M.D., Ph.D.

Medical Informatics Research CenterDepartment of Information Systems Engineering

Ben Gurion University, Beer Sheva,

Israel

Page 2: Distributed, Knowledge-Based Temporal-Abstraction Mediation Yuval Shahar, M.D., Ph.D. Medical Informatics Research Center Department of Information Systems

The Need for Intelligent Integration of Multiple Time-Oriented Clinical Data

• Many medical tasks, especially those involving chronic patients, require extraction of clinically meaningful concepts from multiple sources of raw, longitudinal, time-oriented data– Example: “Modify the standard dose of the drug, if during treatment,

the patient experiences a second episode of liver toxicity (Grade II or more) that has persisted for at least two weeks”

• Examples of clinical tasks:– Diagnosis

• Searching for “a gradual increase of fasting blood-glucose level”– Therapy

• Following a treatment plan based on a clinical guideline– Quality assessment

• Comparing observed treatments with those recommended by a guideline– Research

• Detection of hidden dependencies over time between clinical parameters

Page 3: Distributed, Knowledge-Based Temporal-Abstraction Mediation Yuval Shahar, M.D., Ph.D. Medical Informatics Research Center Department of Information Systems

The Need for Intelligent Mediation:The Gap Between Raw Clinical Data and Clinically Meaningful Concepts

• Clinical databases store raw, time-stamped data• Care providers and decision-support applications

reason about patients in terms of abstract, clinically meaningful concepts, typically over significant time periods

• A system that automatically answers queries or detects patterns regarding either raw clinical data or concepts derivable from them over time, is crucial for effectively supporting multiple clinical tasks

Page 4: Distributed, Knowledge-Based Temporal-Abstraction Mediation Yuval Shahar, M.D., Ph.D. Medical Informatics Research Center Department of Information Systems

The Temporal-Abstraction Task

• Input: time-stamped clinical data and relevant events (interventions)

• Output: interval-based abstractions

• Identifies past and present trends and states

• Supports decisions based on temporal patterns, such as: “modify therapy if the patient has a second episode of Grade II bone-marrow toxicity lasting more than 3 weeks”

• Focuses on interpretation, rather than on forecasting

Page 5: Distributed, Knowledge-Based Temporal-Abstraction Mediation Yuval Shahar, M.D., Ph.D. Medical Informatics Research Center Department of Information Systems

A Clinical Temporal-Abstraction Example:The Bone-Marrow Transplantation

Domain

.

0 40020010050

1000

2000( )

100K

150K

( )

•••

• • • ••

• •

•••

Granu-locytecounts

• • •

Time (days)

Plateletcounts

PAZ protocol

M[0] M[1] M[2] M[3] M[1] M[0]

BMT

Expected CGVHD

Page 6: Distributed, Knowledge-Based Temporal-Abstraction Mediation Yuval Shahar, M.D., Ph.D. Medical Informatics Research Center Department of Information Systems

The Bone-Marrow Transplantation Example, Revisited

Page 7: Distributed, Knowledge-Based Temporal-Abstraction Mediation Yuval Shahar, M.D., Ph.D. Medical Informatics Research Center Department of Information Systems

Uses of Temporal Abstractions:

Examples in BioMedical Domains• Therapy planning and patient monitoring; E.g., the EON and DeGel projects (modular architectures to support guideline-based care)

• Creating high-level summaries of time-oriented medical records

• Supporting explanation modules for a medical DSS

• Representing goals of therapy guidelines for quality assurance at runtime and quality assessment retrospectively; E.g., the Asgaard project: Guideline intentions regarding both process and outcomes are captured as temporal patterns to be achieved or avoided

• Recent use in Italy for detecting patterns in gene expression levels

• Visualization of time-oriented clinical data: the KNAVE project

Page 8: Distributed, Knowledge-Based Temporal-Abstraction Mediation Yuval Shahar, M.D., Ph.D. Medical Informatics Research Center Department of Information Systems

Knowledge-Based Temporal Abstraction (KBTA)

Structuralknowledge

Classificationknowledge

Temporal-semanticknowledge

Temporal-dynamicknowledge

Contextformation

Temporalinference

Temporalinterpolation

Temporal-patternmatching

Contempo-raneousabstraction

The knowledge-basedtemporal-abstractionmethod

The temporal-abstraction task

Temporal-contextrestriction

Verticaltemporalinference

Horizontaltemporalinference

Temporalinterpo-lation

Temporal-patternmatching

Page 9: Distributed, Knowledge-Based Temporal-Abstraction Mediation Yuval Shahar, M.D., Ph.D. Medical Informatics Research Center Department of Information Systems

The KBTA Ontology• Events (interventions) (e.g., insulin therapy) - part-of, is-a relations

• Parameters (measured raw data and derived concepts) (e.g., hemoglobin values; anemia levels) - abstracted-into, is-a relations

• Patterns (e.g., crescendo angina; quiescent-onset GVHD) - component-of, is-a relations

• Abstraction goals (user views)(e.g., therapy of diabetes) - is-a relations

• Interpretation contexts (effect of regular insulin) - subcontext, is-a relations

• Interpretation contexts are induced by all other entities

Page 10: Distributed, Knowledge-Based Temporal-Abstraction Mediation Yuval Shahar, M.D., Ph.D. Medical Informatics Research Center Department of Information Systems

Temporal-Abstraction Output Types

• State abstractions (LOW, HIGH)• Gradient abstractions (INC, DEC)• Rate Abstractions (SLOW, FAST) • Pattern Abstractions (CRESCENDO)

- Linear patterns- Periodic patterns

Page 11: Distributed, Knowledge-Based Temporal-Abstraction Mediation Yuval Shahar, M.D., Ph.D. Medical Informatics Research Center Department of Information Systems

Temporal-Abstraction Knowledge Types

• Structural (e.g., part-of, is-a relations) - mainly declarative/relational

• Classification (e.g., value ranges; patterns) - mainly functional

• Temporal-semantic (e.g., “concatenable” property) - mainly logical • Temporal-dynamic (e.g., interpolation functions) - mainly probabilistic

Page 12: Distributed, Knowledge-Based Temporal-Abstraction Mediation Yuval Shahar, M.D., Ph.D. Medical Informatics Research Center Department of Information Systems

Dynamic Induction of Contexts:Temporal Constraints Between Inducing Proposition and Induced

Context(Shahar, AMAI 1998)

+2W+4W

AZT-toxicity interpretation context

AZT administration

ss

ee

sees

Page 13: Distributed, Knowledge-Based Temporal-Abstraction Mediation Yuval Shahar, M.D., Ph.D. Medical Informatics Research Center Department of Information Systems

Induction of Interpretation Contexts

+2W+4W

CCTG-522_AZT-toxicity interpretation context

AZT-administration event

(a)

+4W+-6W

-2W

Hepatitis B

HB prodrome Chronic active hepatitis

(b)

CCTG-522 protocol

Page 14: Distributed, Knowledge-Based Temporal-Abstraction Mediation Yuval Shahar, M.D., Ph.D. Medical Informatics Research Center Department of Information Systems

The Meaning of Interpretation Contexts

• Context intervals serve as a frame of reference for interpretation: Abstractions are meaningful only in a context (e.g., “anemia in a pregnant woman”)

• Context intervals focus and limit the computations to only those relevant to a particular context (thus, knowledge is brought to bear only when relevant)

• Contexts enable the use of context-specific knowledge, thus increasing accuracy of resultant abstractions

Page 15: Distributed, Knowledge-Based Temporal-Abstraction Mediation Yuval Shahar, M.D., Ph.D. Medical Informatics Research Center Department of Information Systems

Advantages of Explicit Contexts•Any temporal relation (e.g., overlaps) can hold between a

context and its inducing proposition; contexts can be induced before and after the inducing proposition (thus enabling a certain type of hindsight and foresight)+ Note: Forming contexts is a finite process

• The same context-forming proposition can induce multiple context intervals

• The same interpretation context might be induced by different propositions

• Explicit contexts support maintenance of several concurrent views (or interpretations) of the data, in which the same parameter has different values at the same time, each within a different context+ Note: No contradiction--values are in different contexts

Page 16: Distributed, Knowledge-Based Temporal-Abstraction Mediation Yuval Shahar, M.D., Ph.D. Medical Informatics Research Center Department of Information Systems

Local and Global Persistence Functions:Exponential-Decay Local Belief Functions

(Shahar, JETAI 1999)

1

0

I1 I2

t

1 2

th

Time

Bel()

Page 17: Distributed, Knowledge-Based Temporal-Abstraction Mediation Yuval Shahar, M.D., Ph.D. Medical Informatics Research Center Department of Information Systems

Temperature

Hemoglobin Level

Linear Component

Week 2 Week 3Week 1

Anemia

Fever Fever

Anemia Anemia

FeverFever

Anemia

Fever

Linear ComponentLinear Component Linear Component

Periodic Pattern

Abstraction of Periodic Patterns

Page 18: Distributed, Knowledge-Based Temporal-Abstraction Mediation Yuval Shahar, M.D., Ph.D. Medical Informatics Research Center Department of Information Systems

The RÉSUMÉ System Architecture

Temporal-abstraction mechanisms

Temporal fact baseE v e n t s

C o n t e x t s

A b s t r a c t e d i n t e r v a l s

P r i m i t i v e d a t a •

Domain TA knowledge base

Event ontology

Parameter ontology

Primitive data

Events

••

Context ontology

External patient database

+ +

+

•+

Page 19: Distributed, Knowledge-Based Temporal-Abstraction Mediation Yuval Shahar, M.D., Ph.D. Medical Informatics Research Center Department of Information Systems

Application Domains for the KBTA Method(Shahar & Musen, 1993, 1996; Shahar & Molina 1999;

Boaz and Shahar 2005; Shabtai, Shahar, and Elovic, 2006)

• Medical domains:– Guideline-based care

• AIDS therapy

• Oncology

– Monitoring of children’s growth

– Therapy of insulin-dependent diabetes patients

• Non-medical domains:– Evaluation of traffic-controllers actions

– summarization of meteorological data

– Integration of intelligence data over time

– Monitoring electronic security threats in computers and communication networks

Page 20: Distributed, Knowledge-Based Temporal-Abstraction Mediation Yuval Shahar, M.D., Ph.D. Medical Informatics Research Center Department of Information Systems

Monitoring of Children’s growth:The Parameter Ontology

Parameters

Abstract Primit ive

Abstractions

State

abstractions

Gradient

abstractions

Rate

abstractions

Physical Radiology

Tanner

HTSDS

Height Boneage

Maturation

HTSDS_state

HTSDS_STATE_STATE

(alarm states)

HTSDS_gradient HTSDS_rate

Constant

Population distribution

Tanner_state (Tanner SD)

Boneage_state (boneage SD)

Page 21: Distributed, Knowledge-Based Temporal-Abstraction Mediation Yuval Shahar, M.D., Ph.D. Medical Informatics Research Center Department of Information Systems

Monitoring of Children’s growth: Temporal Abstraction of the

Height Standard Deviation Score (HTSDS)

HTSDS

0

2.0

4.0

6.0

-2.0

-4.0

ContextsFEMALE

Abstracted intervals

4 5 6 7 8 9 10

Age (years)

••

HTSDS_SS

HTSDS_G

HTSDS_R

MILD_ALARM SEVERE_ALARM

SAME INCREASING DECREASING

STATIC FAST STATIC FAST

Page 22: Distributed, Knowledge-Based Temporal-Abstraction Mediation Yuval Shahar, M.D., Ph.D. Medical Informatics Research Center Department of Information Systems

The Diabetes Parameter Ontology

= PROPERTY-OF relation; = IS-A relation; = ABSTRACTED_INTO relation

Parameters

Abstract Laboratory

State abstractions Glucose

Glucose_state

Glucose_state_DM

Glucose_state_DM_preprandial

Glucose_state_DM_prebreakfast

Maximal-gapfunctions

Temporal-semanticproperties

Horizontal-classificationtables

Vertical-classificationtables

Page 23: Distributed, Knowledge-Based Temporal-Abstraction Mediation Yuval Shahar, M.D., Ph.D. Medical Informatics Research Center Department of Information Systems

The Diabetes Event Ontology

= PART-OF relation; = IS-A relation

Events

Medications

Insulin

Regular_insulin NPH_insulin UL_insulin

Physical exerciseMeals

Warm-up Main-effort

Breakfast Lunch Supper Snack

Page 24: Distributed, Knowledge-Based Temporal-Abstraction Mediation Yuval Shahar, M.D., Ph.D. Medical Informatics Research Center Department of Information Systems

The Diabetes Context Ontology

= SUB-CONTEXT relation; = IS-A relation

Contexts

Insulin_action

Regular_insulinaction

DM

Preprandial PostprandialPost_PE

Prebreakfast

Post_PE

Prelunch Presupper

Page 25: Distributed, Knowledge-Based Temporal-Abstraction Mediation Yuval Shahar, M.D., Ph.D. Medical Informatics Research Center Department of Information Systems

Forming Contexts in Diabetes

+0.5 hrs+10 hrs

Regular_insulin_action

Regular_insulin administration event

Diabetes mellitus (DM) treatment

DM_regular_insulin_action interpretation context

Postprandial contextPreprandial context

+1 hrs

Meal

0 hrs

-1 hrs0 hrs

DM_Postprandial contextDM_preprandial context

Page 26: Distributed, Knowledge-Based Temporal-Abstraction Mediation Yuval Shahar, M.D., Ph.D. Medical Informatics Research Center Department of Information Systems

Acquisition of Temporal-Abstraction Knowledge

(Shahar et al., JAMIA, 1999)

Page 27: Distributed, Knowledge-Based Temporal-Abstraction Mediation Yuval Shahar, M.D., Ph.D. Medical Informatics Research Center Department of Information Systems

Evaluation of Automated Knowledge Entry

• Formal evaluation performed, using– 3 experts, 3 knowledge engineers, 3 clinical domains

– a gold standard of data, knowledge and output abstractions

• Domains: – monitoring of children’s growth

– care of diabetes patients

– protocol-based care in oncology and AIDS

• The study evaluated the usability of the KA tool solely for entry of previously elicited knowledge

Page 28: Distributed, Knowledge-Based Temporal-Abstraction Mediation Yuval Shahar, M.D., Ph.D. Medical Informatics Research Center Department of Information Systems

KA Tool Evaluation: Results

• Understanding RÉSUMÉ required 6 to 20 hours (median: 15 to 20 hours)

• Learning to use the KA tool required 2 to 6 hours (median: 3 to 4 hours)

• Acquisition times for physicians varied by domain: 2 to 20 hours for growth monitoring (median: 3 hours), 6 and 12 hours for diabetes care, and 5 to 60 hours for protocol-based care (median: 10 hours)

• A speedup of up to 25 times (median: 3 times) was demonstrated for all participants when the KA process was repeated

• On their first attempt at using the tool to enter the knowledge, the knowledge engineers recorded entry times similar to those of the second attempt of the expert physicians entering the same knowledge

• In all cases, RÉSUMÉ, using knowledge entered via the KA tool, generated abstractions that were almost identical to those generated using the same knowledge, when entered manually

Page 29: Distributed, Knowledge-Based Temporal-Abstraction Mediation Yuval Shahar, M.D., Ph.D. Medical Informatics Research Center Department of Information Systems

Editing The KBTA Ontology in Protégé 2000

Page 30: Distributed, Knowledge-Based Temporal-Abstraction Mediation Yuval Shahar, M.D., Ph.D. Medical Informatics Research Center Department of Information Systems

Temporal Reasoning and Temporal Maintenance

• Temporal reasoning supports inference tasks involving time-oriented data; often connected with artificial-intelligence methods

• Temporal data maintenance deals with storage and retrieval of data that has multiple temporal dimensions; often connected with database systems

• Both require temporal data modelling

Clinicaldecision-supportapplication

TM TR DB

Page 31: Distributed, Knowledge-Based Temporal-Abstraction Mediation Yuval Shahar, M.D., Ph.D. Medical Informatics Research Center Department of Information Systems

Examples of Temporal-Maintenance

Systems

• TSQL2, a bitemporal-database query language (Snodgrass et al., Arizona)

• TNET and the TQuery language (Kahn, Stanford/UCSF)

• The Chronus/Chronus2 projects (Stanford)

Page 32: Distributed, Knowledge-Based Temporal-Abstraction Mediation Yuval Shahar, M.D., Ph.D. Medical Informatics Research Center Department of Information Systems

Examples of Temporal-Reasoning

Systems

• RÉSUMÉ

• M-HTP

• TOPAZ

• TrenDx

Page 33: Distributed, Knowledge-Based Temporal-Abstraction Mediation Yuval Shahar, M.D., Ph.D. Medical Informatics Research Center Department of Information Systems

Temporal Data Manager

• Performs– - Temporal abstraction of time-oriented data

– - Temporal maintenance

• Used for tasks such as finding in a patient database which patients fulfils the guideline eligibility conditions (expressed as temporal patterns), assessing the quality of care by comparison to predefined time-oriented goals, or visualization of temporal patterns in the patient’s record

Page 34: Distributed, Knowledge-Based Temporal-Abstraction Mediation Yuval Shahar, M.D., Ph.D. Medical Informatics Research Center Department of Information Systems

1) Extend the DBMS 2) Extend the Application

Two Possible Implementation Strategies

Database

Application

Temporal Data Management

Database

Application

Temporal Data Management

Page 35: Distributed, Knowledge-Based Temporal-Abstraction Mediation Yuval Shahar, M.D., Ph.D. Medical Informatics Research Center Department of Information Systems

Problems in Extending The DBMS

Temporal data management methods implemented in a DBMS: are limited to producing very

simple abstractions are often database-specific

Database

Application

Temporal Data Management

Page 36: Distributed, Knowledge-Based Temporal-Abstraction Mediation Yuval Shahar, M.D., Ph.D. Medical Informatics Research Center Department of Information Systems

Problems in Extending the Application

Temporal data management methods implemented in applications: duplicate some of the

functions of the DBMS are application-specific

Database

Application

Temporal Data Management

Page 37: Distributed, Knowledge-Based Temporal-Abstraction Mediation Yuval Shahar, M.D., Ph.D. Medical Informatics Research Center Department of Information Systems

Our Strategy

• Separates data management methods from the application and the database

• Decomposes temporal data management into two general tasks:– temporal abstraction– temporal maintenance

Database

Application

Temporal AbstractionTemporal Querying

Page 38: Distributed, Knowledge-Based Temporal-Abstraction Mediation Yuval Shahar, M.D., Ph.D. Medical Informatics Research Center Department of Information Systems

The Tzolkin Temporal-Mediator Architecture

[Nguyen, Shahar et al., 1999]

Database

Application

Temporal-QueryingModule

TemporalAbstraction

Module

KnowledgeBase

Tzolkin

ResultsQuery

AbstractionKnowledge

Page 39: Distributed, Knowledge-Based Temporal-Abstraction Mediation Yuval Shahar, M.D., Ph.D. Medical Informatics Research Center Department of Information Systems

The IDAN Temporal-Abstraction Mediator(Boaz and Shahar, 2003, 2005)

Temporal-Abstraction

Controller

Knowledge- acquisition tool

Standard Medical Vocabularies Service KNAVE-II

Knowledge Service

Temporal-Abstraction

Service (ALMA)

Data Access Service

Medical Expert

Clinical User

Page 40: Distributed, Knowledge-Based Temporal-Abstraction Mediation Yuval Shahar, M.D., Ph.D. Medical Informatics Research Center Department of Information Systems

Adding a New Clinical Database to The IDAN Mediator Architecture

• Due to local variations in terminology and data structure, linking to a new clinical database requires creation of– A schema-mapping table– A term-mapping table– A unit-mapping table

• The mapping tools use a vocabulary-server search engine that organizes and searches within several standard controlled medical vocabularies (ICD-9-CM , LOINC, CPT, SNOMED, NDF)

• Clinical databases are mapped into the standard terms and structure that are used by the clinical knowledge base, thus making the knowledge base(s) highly generic and reusable

• The overall mapping methodology has been implemented within the Medical Database Adaptor (MEIDA) system [German, 2006]

Page 41: Distributed, Knowledge-Based Temporal-Abstraction Mediation Yuval Shahar, M.D., Ph.D. Medical Informatics Research Center Department of Information Systems

The LOINC Server Search Engine

Page 42: Distributed, Knowledge-Based Temporal-Abstraction Mediation Yuval Shahar, M.D., Ph.D. Medical Informatics Research Center Department of Information Systems

LOINC Search Results

Page 43: Distributed, Knowledge-Based Temporal-Abstraction Mediation Yuval Shahar, M.D., Ph.D. Medical Informatics Research Center Department of Information Systems

Accessing Local Data Sources

Unknown

schema

Virtual

schema

adaptorData

access

module

(DAM)

Term mapping table

Local data source site

4: Data request( Patient, LocalTerm )

3: LocalTerm, LocalUnit

5: Data

2: get local term and unit

(StdTerm )

?

6: get transformation

function( LocalUnit, OutUnit )

1: Data request ( Patient,

StdTerm, OutUnit )

7: TransFunc

8: Result = transform

(Data, TransFunc )

9: Result

Transformation

functions library

Page 44: Distributed, Knowledge-Based Temporal-Abstraction Mediation Yuval Shahar, M.D., Ph.D. Medical Informatics Research Center Department of Information Systems

Summary:Knowledge-Based Abstraction

of Time-Oriented Data• Temporal abstraction of time-oriented data can employ reusable domain-

independent computational mechanisms that access a domain-specific temporal-abstraction ontology

• Temporal abstraction is useful for monitoring, therapy planning, data summarization and visualization, explanation, and quality assessment

• The IDAN distributed temporal mediator mediates and coordinates queries to the knowledge base and to the database

• Current and future work: – Continuous temporal abstraction - The Momentum architecture [Spokoiny and Shahar, 2004,

in press]– Probabilistic temporal abstraction (PTA) [Ramati and Shahar, 2005]