Evaluation of rule interestingness measures in medical knowledge discovery in databases

Miho Ohsaki, Hidenao Abe, Shusaku Tsumoto, Hideto Yokoi, Takahira Yamaguchi

Research output: Contribution to journalArticle

46 Citations (Scopus)

Abstract

Objective: We discuss the usefulness of rule interestingness measures for medical KDD through experiments using clinical datasets, and, based on the outcomes of these experiments, also consider how to utilize these measures in postprocessing. Methods and materials: We first conducted an experiment to compare the evaluation results derived from a total of 40 various interestingness measures with those supplied by a medical expert for rules discovered in a clinical dataset on meningitis. We calculated and compared the performance of each interestingness measure to estimate a medical expert's interest using f-measure and correlation coefficient. We then conducted a similar experiment for hepatitis. Results and conclusion: The comprehensive results of experiments on meningitis and hepatitis indicate that the interestingness measures, accuracy, chi-square measure for one quadrant, relative risk, uncovered negative, and peculiarity, have a stable, reasonable performance in estimating real human interest in the medical domain. The results also indicate that the performance of interestingness measures is influenced by the certainty of a hypothesis made by the medical expert, and that the combinational use of interestingness measures will contribute to support medical experts to generate and confirm their hypotheses through human-system interaction.

Original languageEnglish
Pages (from-to)177-196
Number of pages20
JournalArtificial Intelligence in Medicine
Volume41
Issue number3
DOIs
Publication statusPublished - 2007 Nov

Fingerprint

Meningitis
Hepatitis
Data mining
Databases
Experiments
Datasets

Keywords

  • 68T30
  • 68U35
  • Clinical data
  • Data mining
  • Interestingness
  • Knowledge discovery in databases
  • Postprocessing

ASJC Scopus subject areas

  • Artificial Intelligence
  • Medicine(all)

Cite this

Evaluation of rule interestingness measures in medical knowledge discovery in databases. / Ohsaki, Miho; Abe, Hidenao; Tsumoto, Shusaku; Yokoi, Hideto; Yamaguchi, Takahira.

In: Artificial Intelligence in Medicine, Vol. 41, No. 3, 11.2007, p. 177-196.

Research output: Contribution to journalArticle

Ohsaki, Miho ; Abe, Hidenao ; Tsumoto, Shusaku ; Yokoi, Hideto ; Yamaguchi, Takahira. / Evaluation of rule interestingness measures in medical knowledge discovery in databases. In: Artificial Intelligence in Medicine. 2007 ; Vol. 41, No. 3. pp. 177-196.
@article{bbdabed308a54117aa6735bc56b6209d,
title = "Evaluation of rule interestingness measures in medical knowledge discovery in databases",
abstract = "Objective: We discuss the usefulness of rule interestingness measures for medical KDD through experiments using clinical datasets, and, based on the outcomes of these experiments, also consider how to utilize these measures in postprocessing. Methods and materials: We first conducted an experiment to compare the evaluation results derived from a total of 40 various interestingness measures with those supplied by a medical expert for rules discovered in a clinical dataset on meningitis. We calculated and compared the performance of each interestingness measure to estimate a medical expert's interest using f-measure and correlation coefficient. We then conducted a similar experiment for hepatitis. Results and conclusion: The comprehensive results of experiments on meningitis and hepatitis indicate that the interestingness measures, accuracy, chi-square measure for one quadrant, relative risk, uncovered negative, and peculiarity, have a stable, reasonable performance in estimating real human interest in the medical domain. The results also indicate that the performance of interestingness measures is influenced by the certainty of a hypothesis made by the medical expert, and that the combinational use of interestingness measures will contribute to support medical experts to generate and confirm their hypotheses through human-system interaction.",
keywords = "68T30, 68U35, Clinical data, Data mining, Interestingness, Knowledge discovery in databases, Postprocessing",
author = "Miho Ohsaki and Hidenao Abe and Shusaku Tsumoto and Hideto Yokoi and Takahira Yamaguchi",
year = "2007",
month = "11",
doi = "10.1016/j.artmed.2007.07.005",
language = "English",
volume = "41",
pages = "177--196",
journal = "Artificial Intelligence in Medicine",
issn = "0933-3657",
publisher = "Elsevier",
number = "3",

}

TY - JOUR

T1 - Evaluation of rule interestingness measures in medical knowledge discovery in databases

AU - Ohsaki, Miho

AU - Abe, Hidenao

AU - Tsumoto, Shusaku

AU - Yokoi, Hideto

AU - Yamaguchi, Takahira

PY - 2007/11

Y1 - 2007/11

N2 - Objective: We discuss the usefulness of rule interestingness measures for medical KDD through experiments using clinical datasets, and, based on the outcomes of these experiments, also consider how to utilize these measures in postprocessing. Methods and materials: We first conducted an experiment to compare the evaluation results derived from a total of 40 various interestingness measures with those supplied by a medical expert for rules discovered in a clinical dataset on meningitis. We calculated and compared the performance of each interestingness measure to estimate a medical expert's interest using f-measure and correlation coefficient. We then conducted a similar experiment for hepatitis. Results and conclusion: The comprehensive results of experiments on meningitis and hepatitis indicate that the interestingness measures, accuracy, chi-square measure for one quadrant, relative risk, uncovered negative, and peculiarity, have a stable, reasonable performance in estimating real human interest in the medical domain. The results also indicate that the performance of interestingness measures is influenced by the certainty of a hypothesis made by the medical expert, and that the combinational use of interestingness measures will contribute to support medical experts to generate and confirm their hypotheses through human-system interaction.

AB - Objective: We discuss the usefulness of rule interestingness measures for medical KDD through experiments using clinical datasets, and, based on the outcomes of these experiments, also consider how to utilize these measures in postprocessing. Methods and materials: We first conducted an experiment to compare the evaluation results derived from a total of 40 various interestingness measures with those supplied by a medical expert for rules discovered in a clinical dataset on meningitis. We calculated and compared the performance of each interestingness measure to estimate a medical expert's interest using f-measure and correlation coefficient. We then conducted a similar experiment for hepatitis. Results and conclusion: The comprehensive results of experiments on meningitis and hepatitis indicate that the interestingness measures, accuracy, chi-square measure for one quadrant, relative risk, uncovered negative, and peculiarity, have a stable, reasonable performance in estimating real human interest in the medical domain. The results also indicate that the performance of interestingness measures is influenced by the certainty of a hypothesis made by the medical expert, and that the combinational use of interestingness measures will contribute to support medical experts to generate and confirm their hypotheses through human-system interaction.

KW - 68T30

KW - 68U35

KW - Clinical data

KW - Data mining

KW - Interestingness

KW - Knowledge discovery in databases

KW - Postprocessing

UR - http://www.scopus.com/inward/record.url?scp=35648950495&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=35648950495&partnerID=8YFLogxK

U2 - 10.1016/j.artmed.2007.07.005

DO - 10.1016/j.artmed.2007.07.005

M3 - Article

C2 - 17851054

AN - SCOPUS:35648950495

VL - 41

SP - 177

EP - 196

JO - Artificial Intelligence in Medicine

JF - Artificial Intelligence in Medicine

SN - 0933-3657

IS - 3

ER -