A Supervised Learning Approach to Predicting Coronary Heart Disease Complications in Type 2 Diabetes Mellitus Patients

M Giardina, FJ Azuaje, PJ McCullagh, R Harper

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

11 Citations (Scopus)

Abstract

A supervised machine learning approach that incorporates Genetic Algorithms (GA) and Weighted k-Nearest Neighbours (WkNN) was applied to classify type 2 diabetes mellitus (T2DM) patients according to the presence or absence of Coronary Heart Disease (CHD) complications. The investigation was carried out by analyzing potential risk factors recorded at the Ulster Hospital in Northern Ireland. A GA initialization technique that integrates medical expert knowledge was compared with traditional data-driven GA initialization techniques. The results indicate that the incorporation of expert knowledge provides only a small improvement of CHD classification performance compared with models based on data-driven initialization techniques. This may be due to data incompleteness and noise or due to the beneficial effects of treatment, which masks the complication of CHD in the dataset. Further incorporation of expert knowledge at different levels of the GA need to be addressed to improve decision support in this domain.
LanguageEnglish
Title of host publicationUnknown Host Publication
Pages325- 331
Number of pages7
Publication statusPublished - Oct 2006
EventIEEE 6th Symposium on Bioinformatics & Bioengineering - Washington,USA
Duration: 1 Oct 2006 → …

Conference

ConferenceIEEE 6th Symposium on Bioinformatics & Bioengineering
Period1/10/06 → …

Fingerprint

Type 2 Diabetes Mellitus
Coronary Disease
Learning
Northern Ireland
Masks
Noise
Therapeutics

Cite this

Giardina, M., Azuaje, FJ., McCullagh, PJ., & Harper, R. (2006). A Supervised Learning Approach to Predicting Coronary Heart Disease Complications in Type 2 Diabetes Mellitus Patients. In Unknown Host Publication (pp. 325- 331)
@inproceedings{bfad05005b6047e982ea1cf6bc253d62,
title = "A Supervised Learning Approach to Predicting Coronary Heart Disease Complications in Type 2 Diabetes Mellitus Patients",
abstract = "A supervised machine learning approach that incorporates Genetic Algorithms (GA) and Weighted k-Nearest Neighbours (WkNN) was applied to classify type 2 diabetes mellitus (T2DM) patients according to the presence or absence of Coronary Heart Disease (CHD) complications. The investigation was carried out by analyzing potential risk factors recorded at the Ulster Hospital in Northern Ireland. A GA initialization technique that integrates medical expert knowledge was compared with traditional data-driven GA initialization techniques. The results indicate that the incorporation of expert knowledge provides only a small improvement of CHD classification performance compared with models based on data-driven initialization techniques. This may be due to data incompleteness and noise or due to the beneficial effects of treatment, which masks the complication of CHD in the dataset. Further incorporation of expert knowledge at different levels of the GA need to be addressed to improve decision support in this domain.",
author = "M Giardina and FJ Azuaje and PJ McCullagh and R Harper",
year = "2006",
month = "10",
language = "English",
pages = "325-- 331",
booktitle = "Unknown Host Publication",

}

Giardina, M, Azuaje, FJ, McCullagh, PJ & Harper, R 2006, A Supervised Learning Approach to Predicting Coronary Heart Disease Complications in Type 2 Diabetes Mellitus Patients. in Unknown Host Publication. pp. 325- 331, IEEE 6th Symposium on Bioinformatics & Bioengineering, 1/10/06.

A Supervised Learning Approach to Predicting Coronary Heart Disease Complications in Type 2 Diabetes Mellitus Patients. / Giardina, M; Azuaje, FJ; McCullagh, PJ; Harper, R.

Unknown Host Publication. 2006. p. 325- 331.

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

TY - GEN

T1 - A Supervised Learning Approach to Predicting Coronary Heart Disease Complications in Type 2 Diabetes Mellitus Patients

AU - Giardina, M

AU - Azuaje, FJ

AU - McCullagh, PJ

AU - Harper, R

PY - 2006/10

Y1 - 2006/10

N2 - A supervised machine learning approach that incorporates Genetic Algorithms (GA) and Weighted k-Nearest Neighbours (WkNN) was applied to classify type 2 diabetes mellitus (T2DM) patients according to the presence or absence of Coronary Heart Disease (CHD) complications. The investigation was carried out by analyzing potential risk factors recorded at the Ulster Hospital in Northern Ireland. A GA initialization technique that integrates medical expert knowledge was compared with traditional data-driven GA initialization techniques. The results indicate that the incorporation of expert knowledge provides only a small improvement of CHD classification performance compared with models based on data-driven initialization techniques. This may be due to data incompleteness and noise or due to the beneficial effects of treatment, which masks the complication of CHD in the dataset. Further incorporation of expert knowledge at different levels of the GA need to be addressed to improve decision support in this domain.

AB - A supervised machine learning approach that incorporates Genetic Algorithms (GA) and Weighted k-Nearest Neighbours (WkNN) was applied to classify type 2 diabetes mellitus (T2DM) patients according to the presence or absence of Coronary Heart Disease (CHD) complications. The investigation was carried out by analyzing potential risk factors recorded at the Ulster Hospital in Northern Ireland. A GA initialization technique that integrates medical expert knowledge was compared with traditional data-driven GA initialization techniques. The results indicate that the incorporation of expert knowledge provides only a small improvement of CHD classification performance compared with models based on data-driven initialization techniques. This may be due to data incompleteness and noise or due to the beneficial effects of treatment, which masks the complication of CHD in the dataset. Further incorporation of expert knowledge at different levels of the GA need to be addressed to improve decision support in this domain.

M3 - Conference contribution

SP - 325

EP - 331

BT - Unknown Host Publication

ER -