A Hybrid Approach for Heart Disease
Diagnosis and Prediction Using Machine
Learning Techniques
Fatma Zahra Abdeldjouad
1(&)
, Menaouer Brahami
1(&) ,
and Nada Matta
2(&)
1 National Polytechnic School of Oran - Maurice Audin, Oran, Algeria
fatma.abdeldjouad@gmail.com, mbrahami@gmail.com
2 University of Technology of Troyes, Troyes, France
nada.matta@utt.fr
Abstract. Heart disease is considered as one of the major causes of death
throughout the world. It cannot be easily predicted by the medical practitioners
as it is a difficult task which demands expertise and higher knowledge for
prediction. Currently, the recent development in medical supportive technologies based on data mining, machine learning plays an important role in predicting cardiovascular diseases. In this paper, we propose a new hybrid approach
to predict cardiovascular disease using different machine learning techniques
such as Logistic Regression (LR), Adaptive Boosting (AdaBoostM1), MultiObjective Evolutionary Fuzzy Classifier (MOEFC), Fuzzy Unordered Rule
Induction (FURIA), Genetic Fuzzy System-LogitBoost (GFS-LB) and Fuzzy
Hybrid Genetic Based Machine Learning (FH-GBML). For this purpose, the
accuracy and results of each classifier have been compared, with the best
classifier chosen for a more accurate cardiovascular prediction. With this
objective, we use two free software (Weka and Keel).
Keywords: Machine learning Á Data mining Á Healthcare informatics Á Heart
disease Á Classification Á Prediction models Á Medical decision support system
1 Introduction
One of the most common reasons of death in Algeria or other Maghreb countries is
chronic disease. Nevertheless, chronic disease is a vital issue to be fixed for a healthy
human life. More recently, Cardiovascular Disease (CVD) is the leading cause of death
for both men and women globally. Though real-life consultants can be able to predict the
disease with an enormous number of tests and requiring a huge processing time, sometimes, their prediction may be incorrect because of lack of skilled knowledge [1].
Meanwhile, the introduction of artificial intelligence and machine learning has helped to
extract relevant data from large databases which are available in hospitals to make a good
decision. It involves data mining techniques to analyze medical data [2]. For this reason,
data mining has gained popularity due to its tools with the potential to identify trends
within data and turn them into knowledge that could serve as the strong basis for the
analysis [3]. To that end, the key issue in the field of CVD prevention is to give an accurate
© The Author(s) 2020
M. Jmaiel et al. (Eds.): ICOST 2020, LNCS 12157, pp. 299–306, 2020.
https://doi.org/10.1007/978-3-030-51517-1_26
Diagnosis and Prediction Using Machine
Learning Techniques
Fatma Zahra Abdeldjouad
1(&)
, Menaouer Brahami
1(&) ,
and Nada Matta
2(&)
1 National Polytechnic School of Oran - Maurice Audin, Oran, Algeria
fatma.abdeldjouad@gmail.com, mbrahami@gmail.com
2 University of Technology of Troyes, Troyes, France
nada.matta@utt.fr
Abstract. Heart disease is considered as one of the major causes of death
throughout the world. It cannot be easily predicted by the medical practitioners
as it is a difficult task which demands expertise and higher knowledge for
prediction. Currently, the recent development in medical supportive technologies based on data mining, machine learning plays an important role in predicting cardiovascular diseases. In this paper, we propose a new hybrid approach
to predict cardiovascular disease using different machine learning techniques
such as Logistic Regression (LR), Adaptive Boosting (AdaBoostM1), MultiObjective Evolutionary Fuzzy Classifier (MOEFC), Fuzzy Unordered Rule
Induction (FURIA), Genetic Fuzzy System-LogitBoost (GFS-LB) and Fuzzy
Hybrid Genetic Based Machine Learning (FH-GBML). For this purpose, the
accuracy and results of each classifier have been compared, with the best
classifier chosen for a more accurate cardiovascular prediction. With this
objective, we use two free software (Weka and Keel).
Keywords: Machine learning Á Data mining Á Healthcare informatics Á Heart
disease Á Classification Á Prediction models Á Medical decision support system
1 Introduction
One of the most common reasons of death in Algeria or other Maghreb countries is
chronic disease. Nevertheless, chronic disease is a vital issue to be fixed for a healthy
human life. More recently, Cardiovascular Disease (CVD) is the leading cause of death
for both men and women globally. Though real-life consultants can be able to predict the
disease with an enormous number of tests and requiring a huge processing time, sometimes, their prediction may be incorrect because of lack of skilled knowledge [1].
Meanwhile, the introduction of artificial intelligence and machine learning has helped to
extract relevant data from large databases which are available in hospitals to make a good
decision. It involves data mining techniques to analyze medical data [2]. For this reason,
data mining has gained popularity due to its tools with the potential to identify trends
within data and turn them into knowledge that could serve as the strong basis for the
analysis [3]. To that end, the key issue in the field of CVD prevention is to give an accurate
© The Author(s) 2020
M. Jmaiel et al. (Eds.): ICOST 2020, LNCS 12157, pp. 299–306, 2020.
https://doi.org/10.1007/978-3-030-51517-1_26