University of Twente Student Theses
Applying machine learning to diagnose obstructive coronary artery disease
Valk, Jeroen (2024) Applying machine learning to diagnose obstructive coronary artery disease.
|
PDF
1MB |
| Abstract: | Introduction. Risk stratification in patients with chronic coronary syndromes is important. The aim of this thesis is to develop and validate a machine learning-based model to diagnose obstructive coronary artery disease (oCAD) in patients without prior history of CAD using clinical data, medication, and imaging data from CACS and CCTA, and to compare the performance of this model to that of expert readers. Method. An Extra Trees Classifier (ETC) was developed on the training set using ten-fold stratified cross-validation and gridsearch for hyperparameter tuning. Boruta feature selection was utilized to minimize the impact of noise. Results. Imaging features were most important to the predictive performance of the ETC. The ETC achieved a mean ROC-AUC of 0.94 on the training set and showed an ROC-AUC of 0.96 on the test set. The ETC showed similar performance compared to expert readers in accuracy (93% vs. 94%), precision (50% vs. 54%), and recall (94% vs 83%). Conclusion. We have developed and validated a machine learning model to diagnose oCAD. Our findings demonstrate that the ETC performs comparable to expert readers in predicting oCAD. This study highlights the potential of machine learning in oCAD diagnosis. |
| Item Type: | Essay (Master) |
| Faculty: | TNW: Science and Technology |
| Subject: | 44 medicine |
| Programme: | Technical Medicine MSc (60033) |
| Link to this item: | https://purl.utwente.nl/essays/101174 |
| Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page