Comparison between objective interestingness measures and real human interest in medical data mining

Miho Ohsaki, Yoshinori Sato, Shinya Kitaguchi, Hideto Yokoi, Takahira Yamaguchi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

10 Citations (Scopus)

Abstract

This research empirically investigates the performance of conventional rule interestingness measures and discusses their availability to supporting KDD through system-human interaction in medical domain. We compared the evaluation results by a medical expert and that by selected measures for the rules discovered from a dataset on hepatitis. Recall and 2 Measure 1 demon-strated the highest performance, and all measures showed different trends under our experimental conditions. These results indicated that some measures can predict really interesting rules at a certain level and that their combinational use in system-human interaction will be useful.

Original languageEnglish
Title of host publicationLecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)
EditorsB. Orchard, C. Yang, M. Ali
Pages1072-1081
Number of pages10
Volume3029
Publication statusPublished - 2004
Externally publishedYes
Event17th International Conference on Industrial and Engineering Applications of Artificial Intelligence and Expert Systems, IEA/AIE 2004 - Ottowa, Ont., Canada
Duration: 2004 May 172004 May 20

Other

Other17th International Conference on Industrial and Engineering Applications of Artificial Intelligence and Expert Systems, IEA/AIE 2004
CountryCanada
CityOttowa, Ont.
Period04/5/1704/5/20

Fingerprint

Data mining
Availability

ASJC Scopus subject areas

  • Hardware and Architecture

Cite this

Ohsaki, M., Sato, Y., Kitaguchi, S., Yokoi, H., & Yamaguchi, T. (2004). Comparison between objective interestingness measures and real human interest in medical data mining. In B. Orchard, C. Yang, & M. Ali (Eds.), Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science) (Vol. 3029, pp. 1072-1081)

Comparison between objective interestingness measures and real human interest in medical data mining. / Ohsaki, Miho; Sato, Yoshinori; Kitaguchi, Shinya; Yokoi, Hideto; Yamaguchi, Takahira.

Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science). ed. / B. Orchard; C. Yang; M. Ali. Vol. 3029 2004. p. 1072-1081.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ohsaki, M, Sato, Y, Kitaguchi, S, Yokoi, H & Yamaguchi, T 2004, Comparison between objective interestingness measures and real human interest in medical data mining. in B Orchard, C Yang & M Ali (eds), Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science). vol. 3029, pp. 1072-1081, 17th International Conference on Industrial and Engineering Applications of Artificial Intelligence and Expert Systems, IEA/AIE 2004, Ottowa, Ont., Canada, 04/5/17.
Ohsaki M, Sato Y, Kitaguchi S, Yokoi H, Yamaguchi T. Comparison between objective interestingness measures and real human interest in medical data mining. In Orchard B, Yang C, Ali M, editors, Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science). Vol. 3029. 2004. p. 1072-1081
Ohsaki, Miho ; Sato, Yoshinori ; Kitaguchi, Shinya ; Yokoi, Hideto ; Yamaguchi, Takahira. / Comparison between objective interestingness measures and real human interest in medical data mining. Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science). editor / B. Orchard ; C. Yang ; M. Ali. Vol. 3029 2004. pp. 1072-1081
@inproceedings{e46565a24b2b4cd59dfd755204d42131,
title = "Comparison between objective interestingness measures and real human interest in medical data mining",
abstract = "This research empirically investigates the performance of conventional rule interestingness measures and discusses their availability to supporting KDD through system-human interaction in medical domain. We compared the evaluation results by a medical expert and that by selected measures for the rules discovered from a dataset on hepatitis. Recall and 2 Measure 1 demon-strated the highest performance, and all measures showed different trends under our experimental conditions. These results indicated that some measures can predict really interesting rules at a certain level and that their combinational use in system-human interaction will be useful.",
author = "Miho Ohsaki and Yoshinori Sato and Shinya Kitaguchi and Hideto Yokoi and Takahira Yamaguchi",
year = "2004",
language = "English",
volume = "3029",
pages = "1072--1081",
editor = "B. Orchard and C. Yang and M. Ali",
booktitle = "Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)",

}

TY - GEN

T1 - Comparison between objective interestingness measures and real human interest in medical data mining

AU - Ohsaki, Miho

AU - Sato, Yoshinori

AU - Kitaguchi, Shinya

AU - Yokoi, Hideto

AU - Yamaguchi, Takahira

PY - 2004

Y1 - 2004

N2 - This research empirically investigates the performance of conventional rule interestingness measures and discusses their availability to supporting KDD through system-human interaction in medical domain. We compared the evaluation results by a medical expert and that by selected measures for the rules discovered from a dataset on hepatitis. Recall and 2 Measure 1 demon-strated the highest performance, and all measures showed different trends under our experimental conditions. These results indicated that some measures can predict really interesting rules at a certain level and that their combinational use in system-human interaction will be useful.

AB - This research empirically investigates the performance of conventional rule interestingness measures and discusses their availability to supporting KDD through system-human interaction in medical domain. We compared the evaluation results by a medical expert and that by selected measures for the rules discovered from a dataset on hepatitis. Recall and 2 Measure 1 demon-strated the highest performance, and all measures showed different trends under our experimental conditions. These results indicated that some measures can predict really interesting rules at a certain level and that their combinational use in system-human interaction will be useful.

UR - http://www.scopus.com/inward/record.url?scp=9444268735&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=9444268735&partnerID=8YFLogxK

M3 - Conference contribution

VL - 3029

SP - 1072

EP - 1081

BT - Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)

A2 - Orchard, B.

A2 - Yang, C.

A2 - Ali, M.

ER -