Key result
A machine-learning-based decision support system using seven algorithms and feature selection methods was developed to efficiently identify and classify people with heart disease.
Why the study?
Heart disease diagnosis based on traditional medical history is considered unreliable in many aspects, creating a need for noninvasive machine learning methods to accurately and timely differentiate healthy individuals from those with heart disease.
Does a machine-learning-based diagnosis system accurately classify healthy people and people with heart disease?
Population
Heart disease dataset of healthy people and people with heart disease
Comparison
Full features vs a reduced set of features across seven machine learning algorithms
Design
Machine learning prediction and validation study
Authors
Loading...
ML decision support shows promise for heart disease classification; leaves open real-world efficacy pending prospective validation.
Does a machine-learning-based diagnosis system accurately classify healthy people and people with heart disease?
A machine-learning-based decision support system using feature selection can efficiently assist doctors in diagnosing heart disease.
Haq et al. (2018) studied Heart disease. Machine-learning-based diagnosis system was evaluated on Classification accuracy, specificity, sensitivity, Matthews' correlation coefficient, execution time, and AUC. A machine-learning-based decision support system using seven algorithms and feature selection methods was developed to efficiently identify and classify people with heart disease.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: