TY - CHAP
T1 - Coronary heart disease prognosis using machine-learning techniques on patients with type 2 diabetes mellitus
AU - Pimentel, Ângela
AU - Gamboa, Hugo Filipe Silveira
AU - Almeida, Isa Maria
AU - Matos, Pedro
AU - Ribeiro, Rogério Tavares
AU - Raposo, João F.
PY - 2018/1/1
Y1 - 2018/1/1
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85059707321&partnerID=8YFLogxK
U2 - 10.4018/978-1-5225-7122-3.ch011
DO - 10.4018/978-1-5225-7122-3.ch011
M3 - Chapter
AN - SCOPUS:85059707321
SN - 1522571221
SN - 9781522571223
VL - 1
SP - 198
EP - 217
BT - Chronic Illness and Long-Term Care: Breakthroughs in Research and Practice
PB - IGI Global
ER -