Machine learning algorithms for predicting coronary artery disease: efforts toward an open source solution
Aravind Akella1, Sudheer Akella1
1Qualicel Global Inc., Huntington Station, NY 11746, USA.
Insights
Machine learning (ML) models can predict coronary artery disease (CAD) with high accuracy. A neural network model achieved over 93% accuracy, showing potential for clinical CAD detection tools.
Area of Science:
- Cardiology
- Medical Informatics
- Machine Learning
Background:
- Coronary artery disease (CAD) is a widespread global health concern.
- Modifiable risk factors significantly influence CAD development.
- Machine learning (ML) offers potential for early CAD detection and improved patient outcomes.
Purpose of the Study:
- To evaluate the efficacy of six ML algorithms in predicting CAD.
- To develop a clinically applicable tool for CAD detection using ML.
Main Methods:
- Applied six distinct ML algorithms to the Cleveland dataset for CAD prediction.
- Utilized open-source code for reproducibility and clinical application.
Main Results:
- All tested ML algorithms exceeded 80% accuracy in CAD prediction.
- The neural network algorithm demonstrated the highest accuracy (over 93%).
- The neural network model achieved the highest recall (0.93), indicating strong diagnostic value.
Conclusions:
- Predictive ML models show significant diagnostic value for CAD.
- The developed ML approach can serve as a viable clinical tool for CAD detection.
Aim:
The development of coronary artery disease (CAD), a highly prevalent disease worldwide, is influenced by several modifiable risk factors. Predictive models built using machine learning (ML) algorithms may assist clinicians in timely detection of CAD and may improve outcomes.
Materials & Methods:
In this study, we applied six different ML algorithms to predict the presence of CAD amongst patients listed in 'the Cleveland dataset.' The generated computer code is provided as a working open source solution with the ultimate goal to achieve a viable clinical tool for CAD detection.
Results:
All six ML algorithms achieved accuracies greater than 80%, with the 'neural network' algorithm achieving accuracy greater than 93%. The recall achieved with the 'neural network' model is also the highest of the six models (0.93), indicating that predictive ML models may provide diagnostic value in CAD.
More Related Videos
Related Concept Videos
01:30Coronary Artery Disease I: Introduction
01:26Coronary Artery Disease IV: Preventive Measures
01:27Coronary Artery Disease V: Interprofessional Care
01:27Atherosclerosis II: Clinical Manifestations and Diagnostic Tests