Temporal diagnostic reasoning based on time-objects

Keravnou, Elpida

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

Cited by 25 publications

(16 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In this section we explain how abductive diagnostic theories (failure models and background knowledge of normality) and case histories can be uniformly represented in terms of time-objects (Keravnou 1995a(Keravnou , 1996d. A specific diagnostic activity operates within a (possibly moving) window of real time that at any instant of time gives the past and future period of interest.…”

Section: Modeling Failures Faults Normality and Actions As Time-obmentioning

confidence: 99%

Abductive Diagnosis Using Time‐Objects: Criteria for the Evaluation of Solutions

Keravnou

Washbrook

2001

Computational Intelligence

View full text Add to dashboard Cite

Diagnostic problem solving aims to account for, or explain, a malfunction of a system (human or other). Any plausible potential diagnostic solution must satisfy some minimum criteria relevant to the application. Often there will be several plausible solutions, and further criteria will be required to select the "best" explanation. Expert diagnosticians may employ different, complex criteria at different stages of their reasoning. These criteria may be combinations of some more primitive criteria, which therefore should be represented separately and explicitly to permit their flexible and transparent combined usage.In diagnostic reasoning there is a tight coupling between the formation of potential solutions and their evaluation. This is the essence of abductive reasoning. This article presents an abductive framework for diagnostic problem solving. Time-objects, an association of a property and an existence, are used as the representation formalism and a number of primitive, general evaluation criteria into which time has been integrated are defined. Each criterion provides an intuitive yardstick for evaluating the space of potential solutions. The criteria can be combined as appropriate for particular applications to define plausible and best explanations.The central principle is that when time is diagnostically significant, it should be modeled explicitly to enable a more accurate formulation and evaluation of diagnostic solutions. The integration of time and primitive evaluation criteria is illustrated through the Skeletal Dysplasias Diagnostician (SDD) system, a diagnostic expert system for a real-life medical domain. SDD's notions of plausible and best explanation are reviewed so as to show the difficulties in formalizing such notions. Although we illustrate our work by medical problems, it has been motivated by consideration of problems in a number of other domains (fermentation monitoring, air and ground traffic control, power distribution) and is intended to be of wide applicability.

show abstract

Section: Modeling Failures Faults Normality and Actions As Time-obmentioning

confidence: 99%

Abductive Diagnosis Using Time‐Objects: Criteria for the Evaluation of Solutions

Keravnou

Washbrook

2001

Computational Intelligence

View full text Add to dashboard Cite

show abstract

“…Recently, several research efforts have been devoted to define ontologies and mechanisms for medical temporal reasoning and abstraction independently of a specific medical application [Do96a,Ke96,La95,Mi95,Sh94]. From this point of view, the Event Calculus (EC), the well-known general theory of time and change proposed by [Ko86], appears to be an interesting framework.…”

Section: The Temporal Dimensionmentioning

confidence: 99%

“…From this point of view, the Event Calculus (EC), the well-known general theory of time and change proposed by [Ko86], appears to be an interesting framework. In particular, EC (i) is a general and thus likely to be reusable approach, (ii) is well-founded and has been thoroughly formally studied (some works dealing with formal aspects of the EC are [Ce95,Sa95,Sr95,Va95], just to mention the most recent ones), and (iii) adheres to a model with events, states and cause-effect relationships, which seems well adapted for temporal reasoning in medical domains [Do96a,Ke96,La93].…”

Section: The Temporal Dimensionmentioning

confidence: 99%

“…One possibility is not to differentiate (essentially for reasons of simplicity) between them. For example, this perspective is taken in [Ke96], where a formal ontology based on the notion of time-objects (which are both time-points and time-intervals) and atemporal properties associated with time-objects is introduced. The other possibility is to distinguish between active and passive temporal entities.…”

Section: Modeling Of Eventsmentioning

confidence: 99%

“…A significant improvement of the proposed formalism would thus consist in the introduction of facilities to represent temporal abstractions that could be automatically compiled into lower level initiates_at and terminates_at axioms. Furthermore, a limitation of the EC temporal ontology which has been already pointed out in the literature [Ke96] is that EC does not allow multiple granularities (and the resulting vagueness in the occurrence of events). While this was not a problem in our specific application, it could be a major impediment to the exploitation of EC in other medical applications.…”

Section: Temporal Abstractionsmentioning

confidence: 99%

See 2 more Smart Citations

Using a general theory of time and change in patient monitoring: Experiment and evaluation

Chittaro

Dojat

1997

Computers in Biology and Medicine

View full text Add to dashboard Cite

Explicit representation of time and change is an essential feature for building medical decision support systems. In this paper, we propose to use one of the well-known general theories of time and change, namely the Event Calculus [Ko86], to represent temporal aspects in intelligent medical monitoring systems. In particular, we explore the application of CEC [Ch96a] (an efficient implementation of the Event Calculus) to the management of mechanical ventilation, using it to interpret change in data over time, assess patient status and its evolution, and choose the proper respiratory therapy. First, we present the prototype we have built, which has been extensively tested on patient's data reflecting several real clinical situations. Then, we provide a thorough evaluation of the obtained results, pointing out both strengths and weaknesses of adopting the Event Calculus as a temporal reasoning formalism in patient monitoring. We also identify a number of extensions which can be extremely useful in order to ease the scaling up of the possible medical applications of the approach.

show abstract

Temporal Abductive Diagnosis

Keravnou

Washbrook

1999

Progress in Artificial Intelligence

View full text Add to dashboard Cite

Temporal diagnostic reasoning based on time-objects

Cited by 25 publications

References 34 publications

Abductive Diagnosis Using Time‐Objects: Criteria for the Evaluation of Solutions

Abductive Diagnosis Using Time‐Objects: Criteria for the Evaluation of Solutions

Using a general theory of time and change in patient monitoring: Experiment and evaluation

Temporal Abductive Diagnosis

Contact Info

Product

Resources

About