Machine Learning Coronary Artery Disease Prediction Based on Imaging and Non-Imaging Data
The prediction of obstructive atherosclerotic disease has significant clinical meaning for the decision making. In this study, a machine learning predictive model based on gradient boosting classifier is presented, aiming to identify the patients of high CAD risk and those of low CAD risk. The machi...
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-06-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/12/6/1466 |
| _version_ | 1827660948406534144 |
|---|---|
| author | Vassiliki I. Kigka Eleni Georga Vassilis Tsakanikas Savvas Kyriakidis Panagiota Tsompou Panagiotis Siogkas Lampros K. Michalis Katerina K. Naka Danilo Neglia Silvia Rocchiccioli Gualtiero Pelosi Dimitrios I. Fotiadis Antonis Sakellarios |
| author_facet | Vassiliki I. Kigka Eleni Georga Vassilis Tsakanikas Savvas Kyriakidis Panagiota Tsompou Panagiotis Siogkas Lampros K. Michalis Katerina K. Naka Danilo Neglia Silvia Rocchiccioli Gualtiero Pelosi Dimitrios I. Fotiadis Antonis Sakellarios |
| author_sort | Vassiliki I. Kigka |
| collection | DOAJ |
| description | The prediction of obstructive atherosclerotic disease has significant clinical meaning for the decision making. In this study, a machine learning predictive model based on gradient boosting classifier is presented, aiming to identify the patients of high CAD risk and those of low CAD risk. The machine learning methodology includes five steps: the preprocessing of the input data, the class imbalance handling applying the Easy Ensemble algorithm, the recursive feature elimination technique implementation, the implementation of gradient boosting classifier, and finally the model evaluation, while the fine tuning of the presented model was implemented through a randomized search optimization of the model’s hyper-parameters over an internal 3-fold cross-validation. In total, 187 participants with suspicion of CAD previously underwent CTCA during EVINCI and ARTreat clinical studies and were prospectively included to undergo follow-up CTCA. The predictive model was trained using imaging data (geometrical and blood flow based) and non-imaging data. The overall predictive accuracy of the model was 0.81, using both imaging and non-imaging data. The innovative aspect of the proposed study is the combination of imaging-based data with the typical CAD risk factors to provide an integrated CAD risk-predictive model. |
| first_indexed | 2024-03-09T23:59:36Z |
| format | Article |
| id | doaj.art-b57d3927625841d7a1c1bef41a244235 |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-09T23:59:36Z |
| publishDate | 2022-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-b57d3927625841d7a1c1bef41a2442352023-11-23T16:18:37ZengMDPI AGDiagnostics2075-44182022-06-01126146610.3390/diagnostics12061466Machine Learning Coronary Artery Disease Prediction Based on Imaging and Non-Imaging DataVassiliki I. Kigka0Eleni Georga1Vassilis Tsakanikas2Savvas Kyriakidis3Panagiota Tsompou4Panagiotis Siogkas5Lampros K. Michalis6Katerina K. Naka7Danilo Neglia8Silvia Rocchiccioli9Gualtiero Pelosi10Dimitrios I. Fotiadis11Antonis Sakellarios12Unit of Medical Technology and Intelligent Information Systems, Department of Materials Science and Engineering, University of Ioannina, GR 45110 Ioannina, GreeceUnit of Medical Technology and Intelligent Information Systems, Department of Materials Science and Engineering, University of Ioannina, GR 45110 Ioannina, GreeceUnit of Medical Technology and Intelligent Information Systems, Department of Materials Science and Engineering, University of Ioannina, GR 45110 Ioannina, GreeceUnit of Medical Technology and Intelligent Information Systems, Department of Materials Science and Engineering, University of Ioannina, GR 45110 Ioannina, GreeceUnit of Medical Technology and Intelligent Information Systems, Department of Materials Science and Engineering, University of Ioannina, GR 45110 Ioannina, GreeceUnit of Medical Technology and Intelligent Information Systems, Department of Materials Science and Engineering, University of Ioannina, GR 45110 Ioannina, GreeceDepartment of Cardiology, Medical School, University of Ioannina, GR 45110 Ioannina, GreeceDepartment of Cardiology, Medical School, University of Ioannina, GR 45110 Ioannina, GreeceFondazione Toscana Gabriele Monasterio, IT 56126 Pisa, ItalyInstitute of Clinical Physiology, National Research Council, IT 56124 Pisa, ItalyInstitute of Clinical Physiology, National Research Council, IT 56124 Pisa, ItalyUnit of Medical Technology and Intelligent Information Systems, Department of Materials Science and Engineering, University of Ioannina, GR 45110 Ioannina, GreeceUnit of Medical Technology and Intelligent Information Systems, Department of Materials Science and Engineering, University of Ioannina, GR 45110 Ioannina, GreeceThe prediction of obstructive atherosclerotic disease has significant clinical meaning for the decision making. In this study, a machine learning predictive model based on gradient boosting classifier is presented, aiming to identify the patients of high CAD risk and those of low CAD risk. The machine learning methodology includes five steps: the preprocessing of the input data, the class imbalance handling applying the Easy Ensemble algorithm, the recursive feature elimination technique implementation, the implementation of gradient boosting classifier, and finally the model evaluation, while the fine tuning of the presented model was implemented through a randomized search optimization of the model’s hyper-parameters over an internal 3-fold cross-validation. In total, 187 participants with suspicion of CAD previously underwent CTCA during EVINCI and ARTreat clinical studies and were prospectively included to undergo follow-up CTCA. The predictive model was trained using imaging data (geometrical and blood flow based) and non-imaging data. The overall predictive accuracy of the model was 0.81, using both imaging and non-imaging data. The innovative aspect of the proposed study is the combination of imaging-based data with the typical CAD risk factors to provide an integrated CAD risk-predictive model.https://www.mdpi.com/2075-4418/12/6/1466coronary artery diseasenoninvasive cardiovascular imagingcoronary artery disease risk stratificationmachine learning models |
| spellingShingle | Vassiliki I. Kigka Eleni Georga Vassilis Tsakanikas Savvas Kyriakidis Panagiota Tsompou Panagiotis Siogkas Lampros K. Michalis Katerina K. Naka Danilo Neglia Silvia Rocchiccioli Gualtiero Pelosi Dimitrios I. Fotiadis Antonis Sakellarios Machine Learning Coronary Artery Disease Prediction Based on Imaging and Non-Imaging Data Diagnostics coronary artery disease noninvasive cardiovascular imaging coronary artery disease risk stratification machine learning models |
| title | Machine Learning Coronary Artery Disease Prediction Based on Imaging and Non-Imaging Data |
| title_full | Machine Learning Coronary Artery Disease Prediction Based on Imaging and Non-Imaging Data |
| title_fullStr | Machine Learning Coronary Artery Disease Prediction Based on Imaging and Non-Imaging Data |
| title_full_unstemmed | Machine Learning Coronary Artery Disease Prediction Based on Imaging and Non-Imaging Data |
| title_short | Machine Learning Coronary Artery Disease Prediction Based on Imaging and Non-Imaging Data |
| title_sort | machine learning coronary artery disease prediction based on imaging and non imaging data |
| topic | coronary artery disease noninvasive cardiovascular imaging coronary artery disease risk stratification machine learning models |
| url | https://www.mdpi.com/2075-4418/12/6/1466 |
| work_keys_str_mv | AT vassilikiikigka machinelearningcoronaryarterydiseasepredictionbasedonimagingandnonimagingdata AT elenigeorga machinelearningcoronaryarterydiseasepredictionbasedonimagingandnonimagingdata AT vassilistsakanikas machinelearningcoronaryarterydiseasepredictionbasedonimagingandnonimagingdata AT savvaskyriakidis machinelearningcoronaryarterydiseasepredictionbasedonimagingandnonimagingdata AT panagiotatsompou machinelearningcoronaryarterydiseasepredictionbasedonimagingandnonimagingdata AT panagiotissiogkas machinelearningcoronaryarterydiseasepredictionbasedonimagingandnonimagingdata AT lamproskmichalis machinelearningcoronaryarterydiseasepredictionbasedonimagingandnonimagingdata AT katerinaknaka machinelearningcoronaryarterydiseasepredictionbasedonimagingandnonimagingdata AT daniloneglia machinelearningcoronaryarterydiseasepredictionbasedonimagingandnonimagingdata AT silviarocchiccioli machinelearningcoronaryarterydiseasepredictionbasedonimagingandnonimagingdata AT gualtieropelosi machinelearningcoronaryarterydiseasepredictionbasedonimagingandnonimagingdata AT dimitriosifotiadis machinelearningcoronaryarterydiseasepredictionbasedonimagingandnonimagingdata AT antonissakellarios machinelearningcoronaryarterydiseasepredictionbasedonimagingandnonimagingdata |