Related Experiment Videos
Analysing and improving the diagnosis of ischaemic heart disease with machine learning
M Kukar1, I Kononenko, C Groselj
1Faculty of Computer and Information Science, University of Ljubljana, Slovenia. matjaz.kukar@fri.uni-lj.si
Insights
Machine learning enhances the diagnosis of ischaemic heart disease by objectively interpreting patient data. This approach significantly improves diagnostic accuracy and the trade-off between sensitivity and specificity compared to traditional methods.
Area of Science:
- Cardiology
- Medical Informatics
- Artificial Intelligence
Background:
- Ischaemic heart disease is a leading global cause of mortality.
- Current diagnostic procedures for ischaemic heart disease involve multiple sequential steps, including ECG, exercise testing, scintigraphy, and coronary angiography.
- There is a need for improved diagnostic accuracy and efficiency.
Purpose of the Study:
- To investigate the application of machine learning methods for objective interpretation of diagnostic data in ischaemic heart disease.
- To enhance the diagnostic accuracy of individual steps in the ischaemic heart disease diagnostic pathway.
- To compare the performance of machine learning techniques against clinical expertise.
Main Methods:
- Experiments were conducted using various machine learning algorithms to analyze patient data from different diagnostic levels.
- Algorithms were adapted to handle non-uniform misclassification costs for Receiver Operating Characteristic (ROC) analysis.
- Performance was evaluated by comparing sensitivity and specificity against clinician performance.
Main Results:
- Machine learning methods achieved performance levels comparable to those of experienced clinicians.
- ROC analysis demonstrated significant improvements in both sensitivity and specificity when using machine learning.
- The predictive power of standard diagnostic tests was shown to be substantially improved by machine learning techniques.
Conclusions:
- Machine learning offers a powerful tool for objective interpretation of ischaemic heart disease diagnostic data.
- The integration of machine learning can significantly enhance the accuracy and efficiency of ischaemic heart disease diagnosis.
- Machine learning-based approaches show promise in improving patient outcomes by enabling earlier and more accurate disease detection.
Abstract:
Ischaemic heart disease is one of the world's most important causes of mortality, so improvements and rationalization of diagnostic procedures would be very useful. The four diagnostic levels consist of evaluation of signs and symptoms of the disease and ECG (electrocardiogram) at rest, sequential ECG testing during the controlled exercise, myocardial scintigraphy, and finally coronary angiography (which is considered to be the reference method). Machine learning methods may enable objective interpretation of all available results for the same patient and in this way may increase the diagnostic accuracy of each step. We conducted many experiments with various learning algorithms and achieved the performance level comparable to that of clinicians. We also extended the algorithms to deal with non-uniform misclassification costs in order to perform ROC analysis and control the trade-off between sensitivity and specificity. The ROC analysis shows significant improvements of sensitivity and specificity compared to the performance of the clinicians. We further compare the predictive power of standard tests with that of machine learning techniques and show that it can be significantly improved in this way.