Risk factors for high CAD-RADS scoring in CAD patients revealed by machine learning methods: a retrospective study
Objective This study aimed to investigate a variety of machine learning (ML) methods to predict the association between cardiovascular risk factors and coronary artery disease-reporting and data system (CAD-RADS) scores. Methods This is a retrospective cohort study. Demographical, cardiovascular ris...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
PeerJ Inc.
2023-08-01
|
| Series: | PeerJ |
| Subjects: | |
| Online Access: | https://peerj.com/articles/15797.pdf |
| _version_ | 1797424455233830912 |
|---|---|
| author | Yueli Dai Chenyu Ouyang Guanghua Luo Yi Cao Jianchun Peng Anbo Gao Hong Zhou |
| author_facet | Yueli Dai Chenyu Ouyang Guanghua Luo Yi Cao Jianchun Peng Anbo Gao Hong Zhou |
| author_sort | Yueli Dai |
| collection | DOAJ |
| description | Objective This study aimed to investigate a variety of machine learning (ML) methods to predict the association between cardiovascular risk factors and coronary artery disease-reporting and data system (CAD-RADS) scores. Methods This is a retrospective cohort study. Demographical, cardiovascular risk factors and coronary CT angiography (CCTA) characteristics of the patients were obtained. Coronary artery disease (CAD) was evaluated using CAD-RADS score. The stenosis severity component of the CAD-RADS was stratified into two groups: CAD-RADS score 0-2 group and CAD-RADS score 3–5 group. CAD-RADS scores were predicted with random forest (RF), k-nearest neighbors (KNN), support vector machines (SVM), neural network (NN), decision tree classification (DTC) and linear discriminant analysis (LDA). Prediction sensitivity, specificity, accuracy and area under the curve (AUC) were calculated. Feature importance analysis was utilized to find the most important predictors. Results A total of 442 CAD patients with CCTA examinations were included in this study. 234 (52.9%) subjects were CAD-RADS score 0–2 group and 208 (47.1%) were CAD-RADS score 3–5 group. CAD-RADS score 3-5 group had a high prevalence of hypertension (66.8%), hyperlipidemia (50%) and diabetes mellitus (DM) (35.1%). Age, systolic blood pressure (SBP), mean arterial pressure, pulse pressure, pulse pressure index, plasma fibrinogen, uric acid and blood urea nitrogen were significantly higher (p < 0.001), and high-density lipoprotein (HDL-C) lower (p < 0.001) in CAD-RADS score 3–5 group compared to the CAD-RADS score 0–2 group. Nineteen features were chosen to train the models. RF (AUC = 0.832) and LDA (AUC = 0.81) outperformed SVM (AUC = 0.772), NN (AUC = 0.773), DTC (AUC = 0.682), KNN (AUC = 0.707). Feature importance analysis indicated that plasma fibrinogen, age and DM contributed most to CAD-RADS scores. Conclusion ML algorithms are capable of predicting the correlation between cardiovascular risk factors and CAD-RADS scores with high accuracy. |
| first_indexed | 2024-03-09T08:02:29Z |
| format | Article |
| id | doaj.art-55459ed93fd3486cb361979c96ecad4e |
| institution | Directory Open Access Journal |
| issn | 2167-8359 |
| language | English |
| last_indexed | 2024-03-09T08:02:29Z |
| publishDate | 2023-08-01 |
| publisher | PeerJ Inc. |
| record_format | Article |
| series | PeerJ |
| spelling | doaj.art-55459ed93fd3486cb361979c96ecad4e2023-12-03T00:37:44ZengPeerJ Inc.PeerJ2167-83592023-08-0111e1579710.7717/peerj.15797Risk factors for high CAD-RADS scoring in CAD patients revealed by machine learning methods: a retrospective studyYueli Dai0Chenyu Ouyang1Guanghua Luo2Yi Cao3Jianchun Peng4Anbo Gao5Hong Zhou6Department of Radiology, The Second Affiliated Hospital, Hengyang Medical School, University of South China, Hengyang, Hunan, ChinaDepartment of Radiology, The First Affiliated Hospital, Hengyang Medical School, University of South China, Hengyang, Hunan, ChinaDepartment of Radiology, The First Affiliated Hospital, Hengyang Medical School, University of South China, Hengyang, Hunan, ChinaDepartment of Radiology, The Second Affiliated Hospital, Hengyang Medical School, University of South China, Hengyang, Hunan, ChinaDepartment of Radiology, The Second Affiliated Hospital, Hengyang Medical School, University of South China, Hengyang, Hunan, ChinaClinical Research Institute, The Second Affiliated Hospital, Hengyang Medical School, University of South China, Hengyang, Hunan, ChinaDepartment of Radiology, The First Affiliated Hospital, Hengyang Medical School, University of South China, Hengyang, Hunan, ChinaObjective This study aimed to investigate a variety of machine learning (ML) methods to predict the association between cardiovascular risk factors and coronary artery disease-reporting and data system (CAD-RADS) scores. Methods This is a retrospective cohort study. Demographical, cardiovascular risk factors and coronary CT angiography (CCTA) characteristics of the patients were obtained. Coronary artery disease (CAD) was evaluated using CAD-RADS score. The stenosis severity component of the CAD-RADS was stratified into two groups: CAD-RADS score 0-2 group and CAD-RADS score 3–5 group. CAD-RADS scores were predicted with random forest (RF), k-nearest neighbors (KNN), support vector machines (SVM), neural network (NN), decision tree classification (DTC) and linear discriminant analysis (LDA). Prediction sensitivity, specificity, accuracy and area under the curve (AUC) were calculated. Feature importance analysis was utilized to find the most important predictors. Results A total of 442 CAD patients with CCTA examinations were included in this study. 234 (52.9%) subjects were CAD-RADS score 0–2 group and 208 (47.1%) were CAD-RADS score 3–5 group. CAD-RADS score 3-5 group had a high prevalence of hypertension (66.8%), hyperlipidemia (50%) and diabetes mellitus (DM) (35.1%). Age, systolic blood pressure (SBP), mean arterial pressure, pulse pressure, pulse pressure index, plasma fibrinogen, uric acid and blood urea nitrogen were significantly higher (p < 0.001), and high-density lipoprotein (HDL-C) lower (p < 0.001) in CAD-RADS score 3–5 group compared to the CAD-RADS score 0–2 group. Nineteen features were chosen to train the models. RF (AUC = 0.832) and LDA (AUC = 0.81) outperformed SVM (AUC = 0.772), NN (AUC = 0.773), DTC (AUC = 0.682), KNN (AUC = 0.707). Feature importance analysis indicated that plasma fibrinogen, age and DM contributed most to CAD-RADS scores. Conclusion ML algorithms are capable of predicting the correlation between cardiovascular risk factors and CAD-RADS scores with high accuracy.https://peerj.com/articles/15797.pdfCADCAD-RADSMLRisk factorPredictionPlasma fibrinogen |
| spellingShingle | Yueli Dai Chenyu Ouyang Guanghua Luo Yi Cao Jianchun Peng Anbo Gao Hong Zhou Risk factors for high CAD-RADS scoring in CAD patients revealed by machine learning methods: a retrospective study PeerJ CAD CAD-RADS ML Risk factor Prediction Plasma fibrinogen |
| title | Risk factors for high CAD-RADS scoring in CAD patients revealed by machine learning methods: a retrospective study |
| title_full | Risk factors for high CAD-RADS scoring in CAD patients revealed by machine learning methods: a retrospective study |
| title_fullStr | Risk factors for high CAD-RADS scoring in CAD patients revealed by machine learning methods: a retrospective study |
| title_full_unstemmed | Risk factors for high CAD-RADS scoring in CAD patients revealed by machine learning methods: a retrospective study |
| title_short | Risk factors for high CAD-RADS scoring in CAD patients revealed by machine learning methods: a retrospective study |
| title_sort | risk factors for high cad rads scoring in cad patients revealed by machine learning methods a retrospective study |
| topic | CAD CAD-RADS ML Risk factor Prediction Plasma fibrinogen |
| url | https://peerj.com/articles/15797.pdf |
| work_keys_str_mv | AT yuelidai riskfactorsforhighcadradsscoringincadpatientsrevealedbymachinelearningmethodsaretrospectivestudy AT chenyuouyang riskfactorsforhighcadradsscoringincadpatientsrevealedbymachinelearningmethodsaretrospectivestudy AT guanghualuo riskfactorsforhighcadradsscoringincadpatientsrevealedbymachinelearningmethodsaretrospectivestudy AT yicao riskfactorsforhighcadradsscoringincadpatientsrevealedbymachinelearningmethodsaretrospectivestudy AT jianchunpeng riskfactorsforhighcadradsscoringincadpatientsrevealedbymachinelearningmethodsaretrospectivestudy AT anbogao riskfactorsforhighcadradsscoringincadpatientsrevealedbymachinelearningmethodsaretrospectivestudy AT hongzhou riskfactorsforhighcadradsscoringincadpatientsrevealedbymachinelearningmethodsaretrospectivestudy |