An Evaluation of Explanations of Probabilistic Inference

From Tetherless World Wiki

Jump to: navigation, search

Citation: Henri Jacques Suermondt and Gregory F. Cooper. (1992) An Evaluation of Explanations of Probabilistic Inference. In KSL-92-16, 1992.

Publication techreport ( Edit )
type Technical Report
bibtype techreport
Bibtex basics
author Henri Jacques Suermondt and Gregory F. Cooper
title An Evaluation of Explanations of Probabilistic Inference
number KSL-92-16
institution Knowledge Systems, AI Laboratory
address Washington, D.C.
year 1992
Bibtex more
Access Paper
abstract Providing explanations of the conclusions of decision-support systems can be viewed as presenting inference results in a manner that enhances the user's insight into how these results were obtained. The ability to explain inferences has been demonstrated to be an important factor in making medical decision-support systems acceptable for clinical use. Although many researchers in artificial intelligence have explored the automatic generation of explanations for decision-support systems based on symbolic reasoning, research in automated explanation of probabilistic results has been limited.We present the results of an evaluation study of INSITE, a program that explains the reasoning of decision-support systems based on Bayesian belief networks. In the domain of anesthesia, we compared subjects who had access to a belief network with explanations of the inference results, to control subjects who used the same belief network without explanations. We show that, compared to control subjects, the explanation subjects demonstrated greater diagnostic accuracy, were more confident about their conclusions, were more critical of the belief network, and found the presentation of the inference results more clear.

KSL Technical Report ID: KSL-92-16
Facts about An Evaluation of Explanations of Probabilistic InferenceRDF feed
Abstract Providing explanations of the conclusions … Providing explanations of the conclusions of decision-support systems can be viewed as presenting inference results in a manner that enhances the user's insight into how these results were obtained. The ability to explain inferences has been demonstrated to be an important factor in making medical decision-support systems acceptable for clinical use. Although many researchers in artificial intelligence have explored the automatic generation of explanations for decision-support systems based on symbolic reasoning, research in automated explanation of probabilistic results has been limited.We present the results of an evaluation study of INSITE, a program that explains the reasoning of decision-support systems based on Bayesian belief networks. In the domain of anesthesia, we compared subjects who had access to a belief network with explanations of the inference results, to control subjects who used the same belief network without explanations. We show that, compared to control subjects, the explanation subjects demonstrated greater diagnostic accuracy, were more confident about their conclusions, were more critical of the belief network, and found the presentation of the inference results more clear. ation of the inference results more clear.
Address Washington, D.C.  +
Author Henri Jacques Suermondt and Gregory F. Cooper  +
Bibtype techreport  +
Has author Henri Jacques Suermondt and Gregory F. Cooper  +
Has identifier KSL-92-16  +
Has publishing details 1992  +
Has title An Evaluation of Explanations of Probabilistic Inference  +
Has where published KSL-92-16  +
Has year 1992  +
Institution Knowledge Systems, AI Laboratory  +
Ksl tr id KSL-92-16  +
Number KSL-92-16  +
Process note YES  +
Title An Evaluation of Explanations of Probabilistic Inference  +
Year 1992  +
Retrieved from "http://tw.rpi.edu/wiki/An_Evaluation_of_Explanations_of_Probabilistic_Inference"
Personal tools