Hybrid knowledge-based systems for therapy planning

Silvana Quaglini, R. Bellazzi, C. Berzuini, M. Stefanelli, G. Barosi

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

The design and development of a knowledge-based system (KBS) for therapy planning may benefit from an epistemological analysis of this generic medical task. We specialized a previously formulated epistemological model of medical reasoning toward therapy planning by defining an appropriate ontology and an inference model. We propose a computational framework for the implementation of such epistemological model. Then, we discuss how to choose the formalisms for knowledge representation. It will become evident that a KBS for therapy planning usually requires more than one formalism. We experimented the combined use of production rules, frames, and probabilistic models, such as influence diagrams. From the computational point of view, the system is based on a blackboard control architecture, where control knowledge and domain knowledge are represented explicitly and separately. The medical domain where the system has been experimented is hematology, more specifically the therapy of anemic patients. Clinical examples from this field provide empirical evidence supporting our claims.

Original languageEnglish
Pages (from-to)207-226
Number of pages20
JournalArtificial Intelligence in Medicine
Volume4
Issue number3
DOIs
Publication statusPublished - 1992

Fingerprint

Knowledge based systems
Planning
Knowledge representation
Ontology
Statistical Models
Hematology
Therapeutics

Keywords

  • blackboard control architecture
  • epistemological model
  • influence diagrams
  • knowledge-based systems
  • Therapy planning

ASJC Scopus subject areas

  • Artificial Intelligence
  • Medicine(all)

Cite this

Hybrid knowledge-based systems for therapy planning. / Quaglini, Silvana; Bellazzi, R.; Berzuini, C.; Stefanelli, M.; Barosi, G.

In: Artificial Intelligence in Medicine, Vol. 4, No. 3, 1992, p. 207-226.

Research output: Contribution to journalArticle

Quaglini, Silvana ; Bellazzi, R. ; Berzuini, C. ; Stefanelli, M. ; Barosi, G. / Hybrid knowledge-based systems for therapy planning. In: Artificial Intelligence in Medicine. 1992 ; Vol. 4, No. 3. pp. 207-226.
@article{7fd4ab0820f24242a2df081c50aa5ebe,
title = "Hybrid knowledge-based systems for therapy planning",
abstract = "The design and development of a knowledge-based system (KBS) for therapy planning may benefit from an epistemological analysis of this generic medical task. We specialized a previously formulated epistemological model of medical reasoning toward therapy planning by defining an appropriate ontology and an inference model. We propose a computational framework for the implementation of such epistemological model. Then, we discuss how to choose the formalisms for knowledge representation. It will become evident that a KBS for therapy planning usually requires more than one formalism. We experimented the combined use of production rules, frames, and probabilistic models, such as influence diagrams. From the computational point of view, the system is based on a blackboard control architecture, where control knowledge and domain knowledge are represented explicitly and separately. The medical domain where the system has been experimented is hematology, more specifically the therapy of anemic patients. Clinical examples from this field provide empirical evidence supporting our claims.",
keywords = "blackboard control architecture, epistemological model, influence diagrams, knowledge-based systems, Therapy planning",
author = "Silvana Quaglini and R. Bellazzi and C. Berzuini and M. Stefanelli and G. Barosi",
year = "1992",
doi = "10.1016/0933-3657(92)90028-N",
language = "English",
volume = "4",
pages = "207--226",
journal = "Artificial Intelligence in Medicine",
issn = "0933-3657",
publisher = "Elsevier",
number = "3",

}

TY - JOUR

T1 - Hybrid knowledge-based systems for therapy planning

AU - Quaglini, Silvana

AU - Bellazzi, R.

AU - Berzuini, C.

AU - Stefanelli, M.

AU - Barosi, G.

PY - 1992

Y1 - 1992

N2 - The design and development of a knowledge-based system (KBS) for therapy planning may benefit from an epistemological analysis of this generic medical task. We specialized a previously formulated epistemological model of medical reasoning toward therapy planning by defining an appropriate ontology and an inference model. We propose a computational framework for the implementation of such epistemological model. Then, we discuss how to choose the formalisms for knowledge representation. It will become evident that a KBS for therapy planning usually requires more than one formalism. We experimented the combined use of production rules, frames, and probabilistic models, such as influence diagrams. From the computational point of view, the system is based on a blackboard control architecture, where control knowledge and domain knowledge are represented explicitly and separately. The medical domain where the system has been experimented is hematology, more specifically the therapy of anemic patients. Clinical examples from this field provide empirical evidence supporting our claims.

AB - The design and development of a knowledge-based system (KBS) for therapy planning may benefit from an epistemological analysis of this generic medical task. We specialized a previously formulated epistemological model of medical reasoning toward therapy planning by defining an appropriate ontology and an inference model. We propose a computational framework for the implementation of such epistemological model. Then, we discuss how to choose the formalisms for knowledge representation. It will become evident that a KBS for therapy planning usually requires more than one formalism. We experimented the combined use of production rules, frames, and probabilistic models, such as influence diagrams. From the computational point of view, the system is based on a blackboard control architecture, where control knowledge and domain knowledge are represented explicitly and separately. The medical domain where the system has been experimented is hematology, more specifically the therapy of anemic patients. Clinical examples from this field provide empirical evidence supporting our claims.

KW - blackboard control architecture

KW - epistemological model

KW - influence diagrams

KW - knowledge-based systems

KW - Therapy planning

UR - http://www.scopus.com/inward/record.url?scp=0026868147&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0026868147&partnerID=8YFLogxK

U2 - 10.1016/0933-3657(92)90028-N

DO - 10.1016/0933-3657(92)90028-N

M3 - Article

VL - 4

SP - 207

EP - 226

JO - Artificial Intelligence in Medicine

JF - Artificial Intelligence in Medicine

SN - 0933-3657

IS - 3

ER -