Temporal diagnostic reasoning based on time-objects

doi:10.1016/0933-3657(95)00035-6

Artificial Intelligence in Medicine

Volume 8, Issue 3, July 1996, Pages 235-265

https://doi.org/10.1016/0933-3657(95)00035-6 Get rights and content

Abstract

Time is essential in diagnostic problem-solving. However, as with other commonsense tasks, time representation and reasoning is not a trivial undertaking. This probably explains why time has either been ignored or implicitly represented and used in the majority of diagnostic systems, medical or otherwise. Durations, temporal uncertainty and multiple temporal granularities are necessary requirements for medical problem-solving. Most general theories of time proposed in the literature do not address all these requirements, and some do not address any. The paper discusses time representation and reasoning in medical diagnostic problem-solving, building from a generic temporal ontology which covers the above temporal requirements. Much of what is discussed, however, is applicable to non-medical domains as well. It is argued that the diagnostic concepts (patient data, disorders, therapeutic-actions) are naturally modelled as time-objects. The resulting representation treats time as an integral dimension to these concepts, with special status. Time-object-based representations for generic hypotheses (disorders, actions) are discussed and illustrated; in the case of disorders the representation covers both an associational model and a causal-associational model. A central function of diagnostic problem-solving is deciding the compatibility of hypotheses with regard to a patient model. In this respect the paper discusses temporal and contextual screening of triggered hypotheses as well as accountings and conflicts between time-objects.

References (61)

J.F. Allen
Towards a general theory of action and time
Artif. Intell
(1984)
P. Barahona
A causal and temporal reasoning model and its use in drug therapy applications
Artif. Intell. Med.
(1994)
W.J. Clancey
Heuristic classification
Artif. Intell.
(1985)
L. Console et al.
On the co-operation between abductive and temporal reasoning in medical diagnosis
Artif. Intell. Med.
(1991)
T.L. Dean et al.
Temporal data base management
Artif. Intell.
(1987)
I.J. Haimowitz et al.
Clinical monitoring using regression-based trend templates
Artif. Intell. Med.
(1995)
I.J. Haimowitz et al.
Managing temporal worlds for medical trend diagnosis
Artif. Intell. Med.
(1996)
S. Hanks et al.
Modeling a dynamic and uncertain world I: symbolic and probabilistic reasoning about change
Artif. Intell.
(1994)
E.T. Keravnou et al.
Modelling diagnostic skills in the domain of skeletal dysplasias
Comput. Methods Progr. Biomed.
(1994)
E.T. Keravnou et al.
Deep and shallow models in medical expert systems
Artif. Intell. Med.
(1989)

E.T. Keravnou et al.

A temporal reasoning framework used in the domain of skeletal dysplasias

Artif. Intell Med.

(1990)

E.T. Keravnou et al.

Explicit data-modelling for second-generation diagnostic expert systems

W. Long

Temporal reasoning for diagnosis in a causal probabilistic knowledge base

Artif. Intell. Med.

(1996)

R. Maiocchi et al.

Temporal data management: a comparative view

IEEE Trans. Knowledge Data Eng.

(1991)

L.E. McKenzie et al.

Evaluation of relational algebras incorporating the time dimension in databases

ACM Comput. Surveys

(1991)

N.L. Sarda

Extensions to SQL for historical databases

IEEE Trans. Knowledge Data Eng.

(1990)

Y. Shahar et al.

A problem-solving architecture for managing temporal data and their abstractions

D.A. Tong et al.

Model-based interpretation of the ECG: A methodology for temporal and spatial reasoning

Comput. Biomed. Res.

(1993)

P. Torasso et al.

L. Vila

A Survey on temporal reasoning in artificial intelligence

AICOM

(1994)

J.F. Allen

Maintaining knowledge about temporal intervals

CACM

(1983)

C. Combi et al.

TIME-NESIS: a data model in managing time granularity of natural-language clinical information

L. Console et al.

Fuzzy temporal reasoning on causal models

L. Console et al.

An approach to diagnosis on causal-temporal models

T. Dean et al.

Probabilistic temporal reasoning

G. Friedrich

Model-based diagnosis and repair

AICOM

(1993)

G. Friedrich et al.

Diagnosing temporal misbehavior

A. Galton

Reified temporal theories and how to unreify them

E. Groβ et al.

On clipping persistence (or whatever must be clipped) in time maps

S. Hanks

Representing and computing temporally scoped beliefs

Cited by (23)

Extending the event calculus for tracking epidemic spread
2006, Artificial Intelligence in Medicine
The email reporting system has been recognized as a key tool for early warning of disease outbreaks and surveillance of emerging diseases. The aim of the work reported here was to develop a formal language for building an event-centered representation of outbreak histories, described by outbreak reports, which could be used for tracking the spread of epidemics.
The SpatioTemporal Extended Event Language (STEEL) we have built is an extension of the Event Calculus that is based on joint spatial and temporal location of event occurrences and structured conglomeration of events. This language allows us to represent and build aggregates of events, according to their spatiotemporal location.
In a proof of concept study, this language was implemented in Prolog. A trial corpus of 35 outbreak reports from a PROMED-Mail diffusion list was hand coded in an experimental implementation of STEEL. The performances of this language were compared with three human experts during a question and answer task on this corpus. The experiment showed agreement between responses of the experts and the system.
STEEL ensures the spatial and temporal location of event occurrence. The resulting representation is very close to the narrative. Further work must be made to develop a system capable of automatically modeling outbreak reports.
Chapter 20 Time in qualitative simulation
2005, Foundations of Artificial Intelligence
A generalized time quantifier approach to approximate reasoning
2004, Fuzzy Sets and Systems
In this paper, a rather expressive fuzzy temporal logic for linear time is introduced. First, this logic is a multivalued generalization (Lukasiewicz style) of a two-valued linear-time temporal logic based on, e.g., the “until” operator. Second, it is obtained by introducing a generalized time quantifier (a generalization of the partition operator investigated by Shen) applied to fuzzy time sets.
In this fuzzy temporal logic, generalized compositional rules of inference, suitable for approximate reasoning in a temporal setting, are presented as valid formulas.
Some medical examples illustrate our approach.
Multiple representations and multi-modal reasoning in medical diagnostic systems
2001, Artificial Intelligence in Medicine
Citation Excerpt :
Although an explicit representation of time is useful for many tasks such as data interpretation, data abstraction, monitoring, etc., in the following I will concentrate on temporal reasoning in connection to diagnosis. As pointed out in [28] and [33], the requirements of time representation and reasoning posed by diagnostic problem solving in medical domains are quite demanding. It is not surprising that a large number of approaches have been proposed for taking into account the variety of temporal phenomena to be dealt with in diagnostic problem solving and that some approaches try to reduce the complexity of the problem by making assumptions on the characteristics of the system to be diagnosed.
The paper examines the motivations for developing medical diagnostic systems exploiting multiple representations and multi-modal reasoning. The analysis is carried on by revisiting the architectural choices of the CHECK system (developed in late 1980s) which combined heuristic and causal knowledge. The results in the theory of diagnosis and in model-based reasoning (MBR) obtained in early 1990s are used for providing a formal characterization of the notion of diagnosis and of the reasoning mechanisms used in CHECK.
The paper addresses also the problem of replacing heuristic knowledge provided by human experts with operational knowledge automatically derived from the deep model. In particular, the pros and cons of knowledge compilation and of the integration of case-based reasoning (CBR) with MBR are discussed by summarizing the experience gained in developing AID and ADAPtER.
The problem of using an explicit representation of time in diagnostic systems is analyzed and recent work on the different characterizations of diagnosis arising when the temporal dimension is considered is reported.
Finally, the implications of the results obtained in MBR and in temporal reasoning on the future of medical diagnostic systems are briefly discussed.
Knowledge discovery and knowledge validation in intensive care
2000, Artificial Intelligence in Medicine
Operational protocols are a valuable means for quality control. However, developing operational protocols is a highly complex and costly task. We present an integrated approach involving both intelligent data analysis and knowledge acquisition from experts that support the development of operational protocols. The aim is to ensure high quality standards for the protocol through empirical validation during the development, as well as lower development cost through the use of machine learning and statistical techniques. We demonstrate our approach of integrating expert knowledge with data driven techniques based on our effort to develop an operational protocol for the hemodynamic system.
How knowledge drives understanding - Matching medical ontologies with the needs of medical language processing
1999, Artificial Intelligence in Medicine
In this article, we introduce a knowledge-based approach to medical text understanding. From an in-depth consideration of deep sentence and text understanding we distill basic requirements for an adequate knowledge representation framework. These requirements are then matched with currently available medical ontologies (thesauri, terminologies, etc.). A fundamental trade-off is recognized between large-scale conceptual coverage on the one hand, and formal mechanisms for integrity preservation and conceptual expressiveness on the other hand. We discuss various shortcomings of the most wide-spread ontologies to capture medical knowledge in-the-large. As a result, we argue for the need of a formally sound and expressive model along the lines of KL-ONE-style terminological representation systems in the format of description logics. These provide an adequate methodology for designing more sophisticated, flexible medical ontologies serving the needs of ‘deep’ knowledge applications which are by no means restricted to medical language processing.

View all citing articles on Scopus

View full text

PaperTemporal diagnostic reasoning based on time-objects

Abstract

Artif. Intell

Artif. Intell. Med.

Artif. Intell.

Artif. Intell. Med.

Artif. Intell.

Artif. Intell. Med.

Artif. Intell. Med.

Artif. Intell.

Comput. Methods Progr. Biomed.

Artif. Intell. Med.

Artif. Intell Med.

Artif. Intell. Med.

IEEE Trans. Knowledge Data Eng.

ACM Comput. Surveys

IEEE Trans. Knowledge Data Eng.

Comput. Biomed. Res.

AICOM

Maintaining knowledge about temporal intervals

CACM

TIME-NESIS: a data model in managing time granularity of natural-language clinical information

Fuzzy temporal reasoning on causal models

An approach to diagnosis on causal-temporal models

Probabilistic temporal reasoning

Model-based diagnosis and repair

AICOM

Diagnosing temporal misbehavior

Reified temporal theories and how to unreify them

On clipping persistence (or whatever must be clipped) in time maps

Representing and computing temporally scoped beliefs

Paper
Temporal diagnostic reasoning based on time-objects