What is the clinical evidence from this study?

Study design: Review. Population: Heart disease. Intervention: Machine learning and data mining techniques. Primary outcome: Prediction accuracy.

What does this research mean for the field?

Current machine learning algorithms, such as Naïve Bayes, Decision Trees, and Artificial Neural Networks, have achieved only marginal success in predicting heart disease, highlighting the need for more complex predictive models. Novelty: ClaimNovelty.SYNTHESIS. Consensus alignment: ConsensusAlignment.NEUTRAL.

March 30, 20230 citationsOpen Access

An in-depth analysis of data mining and machine learning methods for heart disease prediction

DKDanial Kamran

Key Result

Various machine learning algorithms have been widely employed to predict heart diseases with varying accuracies, highlighting the need for more complex models incorporating diverse data sources.

Structured PICO

Population

Patients in various heart disease datasets (e.g., Cleveland, Framingham, VA Long Beach) used for machine learning model training and testing

Intervention

Data mining and machine learning techniques (e.g., Naïve Bayes, Decision Tree, Artificial Neural Network, Support Vector Machine, Random Forest)

Outcome

Prediction accuracy of heart disease

Machine learning techniques show promise in predicting heart disease, but current models achieve only marginal success and require more complex, geographically diverse data sources to improve early detection.

Limitations

Most studies used the small and restricted Cleveland heart disease dataset
Limited heart disease features used in existing studies
Classification accuracies obtained could not be generalized

Abstract

Heart disease is one of the major causes of life complicacies and subsequently leading to death. The heart disease diagnosisand treatment are very complex, especially in the developing countries, due to the rare availability of efficient diagnostic tools andshortage of medical professionals and other resources which affect proper prediction and treatment of patients. Inadequate preventivemeasures, lack of experienced or unskilled medical professionals in the field are the leading contributing factors. Although, largeproportion of heart diseases is preventable but they continue to rise mainly because preventive measures are inadequate. In today’sdigital world, several clinical decision support systems on heart disease prediction have been developed by different scholars to simplifyand ensure efficient diagnosis. This paper investigates the state of the art of various clinical decision support systems for heart diseaseprediction, proposed by various researchers using data mining and machine learning techniques. Classification algorithms such as theNaïve Bayes (NB), Decision Tree (DT), and Artificial Neural Network (ANN) have been widely employed to predict heart diseases,where various accuracies were obtained. Hence, only a marginal success is achieved in the creation of such predictive models for heartdisease patients therefore, there is need for more complex model

Ask AI

Helpful

Bookmark

View Full Paper