Knowledge-Based Temporal Abstraction in Clinical Domains

From Tetherless World Wiki

Jump to: navigation, search

Citation: Yuval Shahar and Mark A. Musen. (1995) Knowledge-Based Temporal Abstraction in Clinical Domains. In KSL-95-23, February,1995.

Publication techreport ( Edit )
type Technical Report
bibtype techreport
Bibtex basics
author Yuval Shahar and Mark A. Musen
title Knowledge-Based Temporal Abstraction in Clinical Domains
number KSL-95-23
institution Knowledge Systems, AI Laboratory
year 1995
month February
Bibtex more
note Medical Computer Science
Access Paper
abstract We have defined a knowledge-based framework for solving the task of creating abstract, interval-based concepts from time-stamped clinical data_the knowledge-based temporal-abstraction (KBTA) method. The KBTA method decomposes the temporal-abstraction task into five tasks; a formal mechanism is proposed for solving each subtask. The KBTA framework emphasizes the explicit representation of the knowledge required for abstraction of time-oriented clinical data, and facilitates its acquisition, maintenance, reuse, and sharing. The RESUME system implements the KBTA method. We tested RESUME in several clinical domains in which the task of monitoring patients is prominent. In particular, we tested the KBTA framework in the domain of monitoring patients who have insulin-dependent diabetes. We acquired from adiabetes-therapy expert a diabetes-therapy temporal-abstraction knowledge base. Two diabetes-therapy experts (including the first one) created temporal abstractions relevant to the therapy-monitoring task from about 800 points of data from cases of diabetic patients. The RESUME system generated about 80% of the abstractions agreed by both experts; about 97% of the overall generated abstractions were valid. We discuss the advantages and limitations of the current architecture.

KSL Technical Report ID: KSL-95-23
Facts about Knowledge-Based Temporal Abstraction in Clinical DomainsRDF feed
Abstract We have defined a knowledge-based framewor … We have defined a knowledge-based framework for solving the task of creating abstract, interval-based concepts from time-stamped clinical data_the knowledge-based temporal-abstraction (KBTA) method. The KBTA method decomposes the temporal-abstraction task into five tasks; a formal mechanism is proposed for solving each subtask. The KBTA framework emphasizes the explicit representation of the knowledge required for abstraction of time-oriented clinical data, and facilitates its acquisition, maintenance, reuse, and sharing. The RESUME system implements the KBTA method. We tested RESUME in several clinical domains in which the task of monitoring patients is prominent. In particular, we tested the KBTA framework in the domain of monitoring patients who have insulin-dependent diabetes. We acquired from adiabetes-therapy expert a diabetes-therapy temporal-abstraction knowledge base. Two diabetes-therapy experts (including the first one) created temporal abstractions relevant to the therapy-monitoring task from about 800 points of data from cases of diabetic patients. The RESUME system generated about 80% of the abstractions agreed by both experts; about 97% of the overall generated abstractions were valid. We discuss the advantages and limitations of the current architecture. d limitations of the current architecture.
Author Yuval Shahar and Mark A. Musen  +
Bibtype techreport  +
Has author Yuval Shahar and Mark A. Musen  +
Has identifier KSL-95-23  +
Has publishing details February,1995  +
Has title Knowledge-Based Temporal Abstraction in Clinical Domains  +
Has where published KSL-95-23  +
Has year 1995  +
Institution Knowledge Systems, AI Laboratory  +
Ksl tr id KSL-95-23  +
Month February  +
Note Medical Computer Science
Number KSL-95-23  +
Process note NO  +
Title Knowledge-Based Temporal Abstraction in Clinical Domains  +
Year 1995  +
Retrieved from "http://tw.rpi.edu/wiki/Knowledge-Based_Temporal_Abstraction_in_Clinical_Domains"
Personal tools