A technique for identifying three diagnostic findings using association analysis

Tomoaki Imamura, Shinya Matsumoto, Yoshiyuki Kanagawa, Bunichi Tajima, Shiro Matsuya, Masutaka Furue, Hiroshi Oyama

Research output: Contribution to journalArticle

16 Citations (Scopus)

Abstract

In diagnosing diseases in clinical practice, a combination of three clinical findings is often used to represent each disease. This is largely because it is often difficult or impractical to assess for all possible combinations of symptoms and abnormal exam findings that occur in any particular disease. For most diseases, diagnostic triads are based on empirical observations. In this study, we determined diagnostic triads for chronic diseases using data mining procedures. We also verified the combinations' validity as well as our procedure for determining them. We used symptoms and examination findings from 477 patients with chronic diseases, collected as part of a 35-year longitudinal study begun in 1968. For each patient there were 295 items from examinations in internal medicine, dermatology, ophthalmology, dentistry and blood tests. We judged each item to be either normal or abnormal, and restricted the analysis to the abnormal findings. To analyze such an exhaustive assortment, we used the data mining technique of association analysis. The analysis generated three clinical findings for each disease. Diseases were defined based on blood tests. Searching through all 295 items to find the three most useful clinical findings would be impractical on a commodity PC. However, by excluding normal items, we were able to sufficiently reduce the total number of combinations so as to make combinatorial analysis on a PC feasible. In addition to more accurate diagnoses, we believe our technique can identify those diagnostic data that are more cost effective in terms of time and other resources required for their collection.

Original languageEnglish
Pages (from-to)51-59
Number of pages9
JournalMedical and Biological Engineering and Computing
Volume45
Issue number1
DOIs
Publication statusPublished - Jan 1 2007

Fingerprint

Data mining
Blood
Dermatology
Ophthalmology
Dentistry
Costs
Internal Medicine

All Science Journal Classification (ASJC) codes

  • Biomedical Engineering
  • Computer Science Applications

Cite this

A technique for identifying three diagnostic findings using association analysis. / Imamura, Tomoaki; Matsumoto, Shinya; Kanagawa, Yoshiyuki; Tajima, Bunichi; Matsuya, Shiro; Furue, Masutaka; Oyama, Hiroshi.

In: Medical and Biological Engineering and Computing, Vol. 45, No. 1, 01.01.2007, p. 51-59.

Research output: Contribution to journalArticle

Imamura, Tomoaki ; Matsumoto, Shinya ; Kanagawa, Yoshiyuki ; Tajima, Bunichi ; Matsuya, Shiro ; Furue, Masutaka ; Oyama, Hiroshi. / A technique for identifying three diagnostic findings using association analysis. In: Medical and Biological Engineering and Computing. 2007 ; Vol. 45, No. 1. pp. 51-59.
@article{c404d68687894817bed1aac25d6213bd,
title = "A technique for identifying three diagnostic findings using association analysis",
abstract = "In diagnosing diseases in clinical practice, a combination of three clinical findings is often used to represent each disease. This is largely because it is often difficult or impractical to assess for all possible combinations of symptoms and abnormal exam findings that occur in any particular disease. For most diseases, diagnostic triads are based on empirical observations. In this study, we determined diagnostic triads for chronic diseases using data mining procedures. We also verified the combinations' validity as well as our procedure for determining them. We used symptoms and examination findings from 477 patients with chronic diseases, collected as part of a 35-year longitudinal study begun in 1968. For each patient there were 295 items from examinations in internal medicine, dermatology, ophthalmology, dentistry and blood tests. We judged each item to be either normal or abnormal, and restricted the analysis to the abnormal findings. To analyze such an exhaustive assortment, we used the data mining technique of association analysis. The analysis generated three clinical findings for each disease. Diseases were defined based on blood tests. Searching through all 295 items to find the three most useful clinical findings would be impractical on a commodity PC. However, by excluding normal items, we were able to sufficiently reduce the total number of combinations so as to make combinatorial analysis on a PC feasible. In addition to more accurate diagnoses, we believe our technique can identify those diagnostic data that are more cost effective in terms of time and other resources required for their collection.",
author = "Tomoaki Imamura and Shinya Matsumoto and Yoshiyuki Kanagawa and Bunichi Tajima and Shiro Matsuya and Masutaka Furue and Hiroshi Oyama",
year = "2007",
month = "1",
day = "1",
doi = "10.1007/s11517-006-0121-6",
language = "English",
volume = "45",
pages = "51--59",
journal = "Medical and Biological Engineering and Computing",
issn = "0140-0118",
publisher = "Springer Verlag",
number = "1",

}

TY - JOUR

T1 - A technique for identifying three diagnostic findings using association analysis

AU - Imamura, Tomoaki

AU - Matsumoto, Shinya

AU - Kanagawa, Yoshiyuki

AU - Tajima, Bunichi

AU - Matsuya, Shiro

AU - Furue, Masutaka

AU - Oyama, Hiroshi

PY - 2007/1/1

Y1 - 2007/1/1

N2 - In diagnosing diseases in clinical practice, a combination of three clinical findings is often used to represent each disease. This is largely because it is often difficult or impractical to assess for all possible combinations of symptoms and abnormal exam findings that occur in any particular disease. For most diseases, diagnostic triads are based on empirical observations. In this study, we determined diagnostic triads for chronic diseases using data mining procedures. We also verified the combinations' validity as well as our procedure for determining them. We used symptoms and examination findings from 477 patients with chronic diseases, collected as part of a 35-year longitudinal study begun in 1968. For each patient there were 295 items from examinations in internal medicine, dermatology, ophthalmology, dentistry and blood tests. We judged each item to be either normal or abnormal, and restricted the analysis to the abnormal findings. To analyze such an exhaustive assortment, we used the data mining technique of association analysis. The analysis generated three clinical findings for each disease. Diseases were defined based on blood tests. Searching through all 295 items to find the three most useful clinical findings would be impractical on a commodity PC. However, by excluding normal items, we were able to sufficiently reduce the total number of combinations so as to make combinatorial analysis on a PC feasible. In addition to more accurate diagnoses, we believe our technique can identify those diagnostic data that are more cost effective in terms of time and other resources required for their collection.

AB - In diagnosing diseases in clinical practice, a combination of three clinical findings is often used to represent each disease. This is largely because it is often difficult or impractical to assess for all possible combinations of symptoms and abnormal exam findings that occur in any particular disease. For most diseases, diagnostic triads are based on empirical observations. In this study, we determined diagnostic triads for chronic diseases using data mining procedures. We also verified the combinations' validity as well as our procedure for determining them. We used symptoms and examination findings from 477 patients with chronic diseases, collected as part of a 35-year longitudinal study begun in 1968. For each patient there were 295 items from examinations in internal medicine, dermatology, ophthalmology, dentistry and blood tests. We judged each item to be either normal or abnormal, and restricted the analysis to the abnormal findings. To analyze such an exhaustive assortment, we used the data mining technique of association analysis. The analysis generated three clinical findings for each disease. Diseases were defined based on blood tests. Searching through all 295 items to find the three most useful clinical findings would be impractical on a commodity PC. However, by excluding normal items, we were able to sufficiently reduce the total number of combinations so as to make combinatorial analysis on a PC feasible. In addition to more accurate diagnoses, we believe our technique can identify those diagnostic data that are more cost effective in terms of time and other resources required for their collection.

UR - http://www.scopus.com/inward/record.url?scp=33846415798&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33846415798&partnerID=8YFLogxK

U2 - 10.1007/s11517-006-0121-6

DO - 10.1007/s11517-006-0121-6

M3 - Article

C2 - 17171389

AN - SCOPUS:33846415798

VL - 45

SP - 51

EP - 59

JO - Medical and Biological Engineering and Computing

JF - Medical and Biological Engineering and Computing

SN - 0140-0118

IS - 1

ER -