Monitoring diseases with empirical and model-generated histories

Research output: Contribution to journalArticleResearchpeer-review

Abstract

Diagnostic monitoring systems track disease hypotheses over time, symbolically interpreting the time-varying patient data produced by medical instrumentation. The need to track multiple interacting diseases recommends a hypothesize, test and refine reasoning architecture which incorporates a robust knowledge representation. Rule-based systems are inadequate, and deep or model-based representations capable of first principles reasoning are currently favoured. However, the model-based approach may be too low level for many monitoring tasks. While disease interactions may present novel patterns to a monitor, usually the diseases themselves will be familiar. It is proposed that disease histories generated from pathophysiological models are at an appropriate level of abstraction for many monitoring tasks. Histories lie between disease models and rules in depth. Using the QSIM representation, results are presented for model-generated histories that define some limits of their utility in reasoning systems. In particular, if the underlying system is non-linear then restrictions exist on the predictions possible with histories alone. These results are extended to poorly modelled domains which may be tractable to reasoning with empirically derived histories. As a consequence, we can also specify when a monitoring system must switch from history to model-based representations.

LanguageEnglish
Pages135-147
Number of pages13
JournalArtificial Intelligence in Medicine
Volume2
Issue number3
DOIs
Publication statusPublished - 1990
Externally publishedYes

Fingerprint

Monitoring
Knowledge representation
Knowledge based systems
History
Switches

Cite this

@article{7368c2fc1ca44c11ad35ddf2198fdf9d,
title = "Monitoring diseases with empirical and model-generated histories",
abstract = "Diagnostic monitoring systems track disease hypotheses over time, symbolically interpreting the time-varying patient data produced by medical instrumentation. The need to track multiple interacting diseases recommends a hypothesize, test and refine reasoning architecture which incorporates a robust knowledge representation. Rule-based systems are inadequate, and deep or model-based representations capable of first principles reasoning are currently favoured. However, the model-based approach may be too low level for many monitoring tasks. While disease interactions may present novel patterns to a monitor, usually the diseases themselves will be familiar. It is proposed that disease histories generated from pathophysiological models are at an appropriate level of abstraction for many monitoring tasks. Histories lie between disease models and rules in depth. Using the QSIM representation, results are presented for model-generated histories that define some limits of their utility in reasoning systems. In particular, if the underlying system is non-linear then restrictions exist on the predictions possible with histories alone. These results are extended to poorly modelled domains which may be tractable to reasoning with empirically derived histories. As a consequence, we can also specify when a monitoring system must switch from history to model-based representations.",
author = "Coiera, {Enrico W.}",
year = "1990",
doi = "10.1016/0933-3657(90)90044-R",
language = "English",
volume = "2",
pages = "135--147",
journal = "Artificial Intelligence in Medicine",
issn = "0933-3657",
publisher = "Elsevier",
number = "3",

}

Monitoring diseases with empirical and model-generated histories. / Coiera, Enrico W.

In: Artificial Intelligence in Medicine, Vol. 2, No. 3, 1990, p. 135-147.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Monitoring diseases with empirical and model-generated histories

AU - Coiera, Enrico W.

PY - 1990

Y1 - 1990

N2 - Diagnostic monitoring systems track disease hypotheses over time, symbolically interpreting the time-varying patient data produced by medical instrumentation. The need to track multiple interacting diseases recommends a hypothesize, test and refine reasoning architecture which incorporates a robust knowledge representation. Rule-based systems are inadequate, and deep or model-based representations capable of first principles reasoning are currently favoured. However, the model-based approach may be too low level for many monitoring tasks. While disease interactions may present novel patterns to a monitor, usually the diseases themselves will be familiar. It is proposed that disease histories generated from pathophysiological models are at an appropriate level of abstraction for many monitoring tasks. Histories lie between disease models and rules in depth. Using the QSIM representation, results are presented for model-generated histories that define some limits of their utility in reasoning systems. In particular, if the underlying system is non-linear then restrictions exist on the predictions possible with histories alone. These results are extended to poorly modelled domains which may be tractable to reasoning with empirically derived histories. As a consequence, we can also specify when a monitoring system must switch from history to model-based representations.

AB - Diagnostic monitoring systems track disease hypotheses over time, symbolically interpreting the time-varying patient data produced by medical instrumentation. The need to track multiple interacting diseases recommends a hypothesize, test and refine reasoning architecture which incorporates a robust knowledge representation. Rule-based systems are inadequate, and deep or model-based representations capable of first principles reasoning are currently favoured. However, the model-based approach may be too low level for many monitoring tasks. While disease interactions may present novel patterns to a monitor, usually the diseases themselves will be familiar. It is proposed that disease histories generated from pathophysiological models are at an appropriate level of abstraction for many monitoring tasks. Histories lie between disease models and rules in depth. Using the QSIM representation, results are presented for model-generated histories that define some limits of their utility in reasoning systems. In particular, if the underlying system is non-linear then restrictions exist on the predictions possible with histories alone. These results are extended to poorly modelled domains which may be tractable to reasoning with empirically derived histories. As a consequence, we can also specify when a monitoring system must switch from history to model-based representations.

UR - http://www.scopus.com/inward/record.url?scp=0000923768&partnerID=8YFLogxK

U2 - 10.1016/0933-3657(90)90044-R

DO - 10.1016/0933-3657(90)90044-R

M3 - Article

VL - 2

SP - 135

EP - 147

JO - Artificial Intelligence in Medicine

T2 - Artificial Intelligence in Medicine

JF - Artificial Intelligence in Medicine

SN - 0933-3657

IS - 3

ER -