Building a medical decision support system for colon polyp screening by using fuzzy classification trees

I-Jen Chiang, Ming Jium Shieh, Jane Yung Jen Hsu, Jau Min Wong

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

To deal with highly uncertain and noisy data, for example, biochemical laboratory examinations, a classifier is required to be able to classify an instance into all possible classes and each class is associated with a degree which shows how possible an instance is in that class. According to these degrees, we can discriminate the more possible classes from the less possible classes. The classifier or an expert can pick the most possible one to be the instance class. However, if their discrimination is not distinguishable, it is better that the classifier should not make any prediction, especially when there is incomplete or inadequate data. A fuzzy classifier is proposed to classify the data with noise and uncertainties. Instead of determining a single class for a given instance, fuzzy classification predicts the degree of possibility for every class. Adenomatous polyps are widely accepted to be precancerous lesions and will degenerate into cancers ultimately. Therefore, it is important to generate a predictive method that can identify the patients who have obtained polyps and remove the lesions of them. Considering the uncertainties and noise in the biochemical laboratory examination data, fuzzy classification trees, which integrate decision tree techniques and fuzzy classifications, provide the efficient way to classify the data in order to generate the model for polyp screening.

Original languageEnglish
Pages (from-to)61-75
Number of pages15
JournalApplied Intelligence
Volume22
Issue number1
DOIs
Publication statusPublished - Jan 2005

Fingerprint

Decision support systems
Screening
Classifiers
Decision trees
Uncertainty

Keywords

  • Fuzzy classification trees
  • Fuzzy classifications
  • Fuzzy entropy
  • Polyp screening

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Artificial Intelligence

Cite this

Building a medical decision support system for colon polyp screening by using fuzzy classification trees. / Chiang, I-Jen; Shieh, Ming Jium; Hsu, Jane Yung Jen; Wong, Jau Min.

In: Applied Intelligence, Vol. 22, No. 1, 01.2005, p. 61-75.

Research output: Contribution to journalArticle

Chiang, I-Jen ; Shieh, Ming Jium ; Hsu, Jane Yung Jen ; Wong, Jau Min. / Building a medical decision support system for colon polyp screening by using fuzzy classification trees. In: Applied Intelligence. 2005 ; Vol. 22, No. 1. pp. 61-75.
@article{cd8d54203f264a40a83effc68ea5cda6,
title = "Building a medical decision support system for colon polyp screening by using fuzzy classification trees",
abstract = "To deal with highly uncertain and noisy data, for example, biochemical laboratory examinations, a classifier is required to be able to classify an instance into all possible classes and each class is associated with a degree which shows how possible an instance is in that class. According to these degrees, we can discriminate the more possible classes from the less possible classes. The classifier or an expert can pick the most possible one to be the instance class. However, if their discrimination is not distinguishable, it is better that the classifier should not make any prediction, especially when there is incomplete or inadequate data. A fuzzy classifier is proposed to classify the data with noise and uncertainties. Instead of determining a single class for a given instance, fuzzy classification predicts the degree of possibility for every class. Adenomatous polyps are widely accepted to be precancerous lesions and will degenerate into cancers ultimately. Therefore, it is important to generate a predictive method that can identify the patients who have obtained polyps and remove the lesions of them. Considering the uncertainties and noise in the biochemical laboratory examination data, fuzzy classification trees, which integrate decision tree techniques and fuzzy classifications, provide the efficient way to classify the data in order to generate the model for polyp screening.",
keywords = "Fuzzy classification trees, Fuzzy classifications, Fuzzy entropy, Polyp screening",
author = "I-Jen Chiang and Shieh, {Ming Jium} and Hsu, {Jane Yung Jen} and Wong, {Jau Min}",
year = "2005",
month = "1",
doi = "10.1023/B:APIN.0000047384.85823.f6",
language = "English",
volume = "22",
pages = "61--75",
journal = "Applied Intelligence",
issn = "0924-669X",
publisher = "Springer Netherlands",
number = "1",

}

TY - JOUR

T1 - Building a medical decision support system for colon polyp screening by using fuzzy classification trees

AU - Chiang, I-Jen

AU - Shieh, Ming Jium

AU - Hsu, Jane Yung Jen

AU - Wong, Jau Min

PY - 2005/1

Y1 - 2005/1

N2 - To deal with highly uncertain and noisy data, for example, biochemical laboratory examinations, a classifier is required to be able to classify an instance into all possible classes and each class is associated with a degree which shows how possible an instance is in that class. According to these degrees, we can discriminate the more possible classes from the less possible classes. The classifier or an expert can pick the most possible one to be the instance class. However, if their discrimination is not distinguishable, it is better that the classifier should not make any prediction, especially when there is incomplete or inadequate data. A fuzzy classifier is proposed to classify the data with noise and uncertainties. Instead of determining a single class for a given instance, fuzzy classification predicts the degree of possibility for every class. Adenomatous polyps are widely accepted to be precancerous lesions and will degenerate into cancers ultimately. Therefore, it is important to generate a predictive method that can identify the patients who have obtained polyps and remove the lesions of them. Considering the uncertainties and noise in the biochemical laboratory examination data, fuzzy classification trees, which integrate decision tree techniques and fuzzy classifications, provide the efficient way to classify the data in order to generate the model for polyp screening.

AB - To deal with highly uncertain and noisy data, for example, biochemical laboratory examinations, a classifier is required to be able to classify an instance into all possible classes and each class is associated with a degree which shows how possible an instance is in that class. According to these degrees, we can discriminate the more possible classes from the less possible classes. The classifier or an expert can pick the most possible one to be the instance class. However, if their discrimination is not distinguishable, it is better that the classifier should not make any prediction, especially when there is incomplete or inadequate data. A fuzzy classifier is proposed to classify the data with noise and uncertainties. Instead of determining a single class for a given instance, fuzzy classification predicts the degree of possibility for every class. Adenomatous polyps are widely accepted to be precancerous lesions and will degenerate into cancers ultimately. Therefore, it is important to generate a predictive method that can identify the patients who have obtained polyps and remove the lesions of them. Considering the uncertainties and noise in the biochemical laboratory examination data, fuzzy classification trees, which integrate decision tree techniques and fuzzy classifications, provide the efficient way to classify the data in order to generate the model for polyp screening.

KW - Fuzzy classification trees

KW - Fuzzy classifications

KW - Fuzzy entropy

KW - Polyp screening

UR - http://www.scopus.com/inward/record.url?scp=9144267072&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=9144267072&partnerID=8YFLogxK

U2 - 10.1023/B:APIN.0000047384.85823.f6

DO - 10.1023/B:APIN.0000047384.85823.f6

M3 - Article

VL - 22

SP - 61

EP - 75

JO - Applied Intelligence

JF - Applied Intelligence

SN - 0924-669X

IS - 1

ER -