User friendly decision support techniques in a case-based reasoning system

Authors:
Monica H. Ou;Geoff A. W. West;Mihai Lazarescu;Chris Clay
Affiliations:
Department of Computing, Curtin University of Technology, Perth, Western Australia, Australia;Department of Computing, Curtin University of Technology, Perth, Western Australia, Australia;Department of Computing, Curtin University of Technology, Perth, Western Australia, Australia;Royal Perth Hospital, Perth, Western Australia, Australia
Venue:
AI'04 Proceedings of the 17th Australian joint conference on Advances in Artificial Intelligence
Year:
2004

Citing 5
Cited 1

C4.5: programs for machine learning

C4.5: programs for machine learning
Applying case-based reasoning: techniques for enterprise systems

Applying case-based reasoning: techniques for enterprise systems
Data mining: practical machine learning tools and techniques with Java implementations

Data mining: practical machine learning tools and techniques with Java implementations
Formal Concept Analysis: Mathematical Foundations

Formal Concept Analysis: Mathematical Foundations
Computing with Conceptual Structures

ICCS '00 Proceedings of the Linguistic on Conceptual Structures: Logical Linguistic, and Computational Issues

Dynamic knowledge validation and verification for CBR teledermatology system

Artificial Intelligence in Medicine

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper describes methods to enable efficient use and administration of a CBR system for teledermatology in which the users are assumed to be non-computer literate In particular, a user-friendly interface to enable a general practitioner to decide a diagnosis with the minimum number of questions asked is proposed Specifically, we propose a technique to improve the usefulness of a decision tree approach in terms of general rather than specific questions Additionally, we describe a new technique to minimise the number of questions presented to the user in the query process for training the CBR system Importantly we apply FCA technique to enable the consultant dermatologist to validate new knowledge and supervised the incremental learning of the CBR system.