Coronary heart disease prognosis using machine-learning techniques on patients with type 2 diabetes mellitus

Ângela Pimentel, Hugo Filipe Silveira Gamboa, Isa Maria Almeida, Pedro Matos, Rogério Tavares Ribeiro, João F. Raposo

Research output: Chapter in Book/Report/Conference proceedingChapterpeer-review

1 Citation (Scopus)

Abstract

Heart diseases and stroke are the number one cause of death and disability among people with type 2 diabetes (T2D). Clinicians and health authorities for many years have expressed interest in identifying individuals at increased risk of coronary heart disease (CHD). Our main objective is to develop a prognostic workflow of CHD in T2D patients using a Holter dataset. This workflow development will be based on machine learning techniques by testing a variety of classifiers and subsequent selection of the best performing system. It will also assess the impact of feature selection and bootstrapping techniques over these systems. Among a variety of classifiers such as Naive Bayes (NB), Random Forest (RF), Support Vector Machine (SVM), Alternating Decision Tree (ADT), Random Tree (RT) and K-Nearest Neighbour (KNN), the best performing classifier is NB. We achieved an area under receiver operating characteristics curve (AUC) of 68,06% and 74,33% for a prognosis of 3 and 4 years, respectively.

Original languageEnglish
Title of host publicationChronic Illness and Long-Term Care: Breakthroughs in Research and Practice
PublisherIGI Global
Pages198-217
Number of pages20
Volume1
ISBN (Electronic)9781522571230
ISBN (Print)1522571221, 9781522571223
DOIs
Publication statusPublished - 1 Jan 2018

Fingerprint

Dive into the research topics of 'Coronary heart disease prognosis using machine-learning techniques on patients with type 2 diabetes mellitus'. Together they form a unique fingerprint.

Cite this