Risk Factors for High CAD-RADS Scoring in CAD Patients Revealed by Machine Learning Methods: a Retrospective Study

Overview

Journal PeerJ

Specialties Biology
Environmental Health
General Medicine

Date 2023 Aug 8

PMID 37551346

Authors

Yueli Dai

Chenyu Ouyang

Guanghua Luo

Yi Cao

Jianchun Peng

Anbo Gao

Hong Zhou

Affiliations

Soon will be listed here.

Abstract

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 ( < 0.001), and high-density lipoprotein (HDL-C) lower ( < 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.

Citing Articles

Association of Pulse Prssure Index With Mortality in Patients With Hypertension: Results From NHANES 1999-2018.

Jin H, Fang S, An S, Ding Y J Clin Hypertens (Greenwich). 2025; 27(1):e70004.

PMID: 39878378 PMC: 11775918. DOI: 10.1111/jch.70004.

Lack of incremental prognostic value of triglyceride glucose index beyond coronary computed tomography angiography features for major events.

Huang Z, Tang R, Ding Y, Wang X, Du X, Wang W Sci Rep. 2024; 14(1):25670.

PMID: 39465316 PMC: 11514186. DOI: 10.1038/s41598-024-77043-z.

The Plaque Analysis Classifies the Coronary Artery Disease-Reporting and Data System (CAD-RADS) Stenosis and Plaque Burden Categories: Association of the Plaque Features, Fat Attenuation Index, Coronary Computed Tomography Fractional Flow Reserve,....

Chen W, Nie J, Zhang M, Zhu Z, Zhou Y, Wu Q Clin Cardiol. 2024; 47(6):e24305.

PMID: 38884449 PMC: 11181293. DOI: 10.1002/clc.24305.

References

Ricciardi C, Valente A, Edmund K, Cantoni V, Green R, Fiorillo A . Linear discriminant analysis and principal component analysis to predict coronary artery disease. Health Informatics J. 2020; 26(3):2181-2192. DOI: 10.1177/1460458219899210. View

Li J, Liu S, Hu Y, Zhu L, Mao Y, Liu J . Predicting Mortality in Intensive Care Unit Patients With Heart Failure Using an Interpretable Machine Learning Model: Retrospective Cohort Study. J Med Internet Res. 2022; 24(8):e38082. PMC: 9399880. DOI: 10.2196/38082. View

Huang Z, Xiao J, Xie Y, Hu Y, Zhang S, Li X . The correlation of deep learning-based CAD-RADS evaluated by coronary computed tomography angiography with breast arterial calcification on mammography. Sci Rep. 2020; 10(1):11532. PMC: 7359346. DOI: 10.1038/s41598-020-68378-4. View

Saravi B, Zink A, Ulkumen S, Couillard-Despres S, Hassel F, Lang G . Performance of Artificial Intelligence-Based Algorithms to Predict Prolonged Length of Stay after Lumbar Decompression Surgery. J Clin Med. 2022; 11(14). PMC: 9318293. DOI: 10.3390/jcm11144050. View

Laggoune J, Nerlekar N, Munnur K, Ko B, Cameron J, Seneviratne S . The utility of coronary computed tomography angiography in elderly patients. J Geriatr Cardiol. 2019; 16(7):507-513. PMC: 6689518. DOI: 10.11909/j.issn.1671-5411.2019.07.006. View

Gasior Z, Rozek B, Dabek J, Majewski M, Stanisz-Kempa J . Prognostic assessment of selected clinical and ultrasonographic indices in patients with non-critical lesions in coronary angiography. Kardiol Pol. 2017; 76(1):173-180. DOI: 10.5603/KP.a2017.0186. View

Kim M, Lee S, Kwak S, Yang S, Kim Y, Andreini D . Impact of age on coronary artery plaque progression and clinical outcome: A PARADIGM substudy. J Cardiovasc Comput Tomogr. 2020; 15(3):232-239. DOI: 10.1016/j.jcct.2020.09.009. View

Muscogiuri G, Chiesa M, Trotta M, Gatti M, Palmisano V, DellAversana S . Performance of a deep learning algorithm for the evaluation of CAD-RADS classification with CCTA. Atherosclerosis. 2020; 294:25-32. DOI: 10.1016/j.atherosclerosis.2019.12.001. View

Cury R, Abbara S, Achenbach S, Agatston A, Berman D, Budoff M . Coronary Artery Disease - Reporting and Data System (CAD-RADS): An Expert Consensus Document of SCCT, ACR and NASCI: Endorsed by the ACC. JACC Cardiovasc Imaging. 2016; 9(9):1099-1113. DOI: 10.1016/j.jcmg.2016.05.005. View

10.

Sun Z, Liu Y, Zhou D, Qi Y . Use of coronary CT angiography in the diagnosis of patients with suspected coronary artery disease: findings and clinical indications. J Geriatr Cardiol. 2012; 9(2):115-22. PMC: 3418899. DOI: 10.3724/SP.J.1263.2012.01041. View

11.

Shu S, Ren J, Song J . Clinical Application of Machine Learning-Based Artificial Intelligence in the Diagnosis, Prediction, and Classification of Cardiovascular Diseases. Circ J. 2021; 85(9):1416-1425. DOI: 10.1253/circj.CJ-20-1121. View

12.

Song B, Shu Y, Xu Y, Fu P . Plasma fibrinogen lever and risk of coronary heart disease among Chinese population: a systematic review and meta-analysis. Int J Clin Exp Med. 2015; 8(8):13195-202. PMC: 4612928. View

13.

Yang R, Zhang H, Wang Z, Liu X, Lin Z . A study on the relationship between waist phenotype, hypertriglyceridemia, coronary artery lesions and serum free fatty acids in adult and elderly patients with coronary diseases. Immun Ageing. 2018; 15:14. PMC: 6003126. DOI: 10.1186/s12979-018-0119-6. View

14.

Saharan S, Nagar P, Creasy K, Stock E, Feng J, Malloy M . Machine learning and statistical approaches for classification of risk of coronary artery disease using plasma cytokines. BioData Min. 2021; 14(1):26. PMC: 8050889. DOI: 10.1186/s13040-021-00260-z. View

15.

Chuah J, Kruger U, Wang G, Yan P, Hahn J . Framework for Testing Robustness of Machine Learning-Based Classifiers. J Pers Med. 2022; 12(8). PMC: 9409965. DOI: 10.3390/jpm12081314. View

16.

Shariatnia S, Ziaratban M, Rajabi A, Salehi A, Abdi Zarrini K, Vakili M . Modeling the diagnosis of coronary artery disease by discriminant analysis and logistic regression: a cross-sectional study. BMC Med Inform Decis Mak. 2022; 22(1):85. PMC: 8966192. DOI: 10.1186/s12911-022-01823-8. View

17.

van den Hoogen I, van Rosendael A, Lin F, Lu Y, Dimitriu-Leen A, Smit J . Coronary atherosclerosis scoring with semiquantitative CCTA risk scores for prediction of major adverse cardiac events: Propensity score-based analysis of diabetic and non-diabetic patients. J Cardiovasc Comput Tomogr. 2019; 14(3):251-257. DOI: 10.1016/j.jcct.2019.11.015. View

18.

Panteris E, Deda O, Papazoglou A, Karagiannidis E, Liapikos T, Begou O . Machine Learning Algorithm to Predict Obstructive Coronary Artery Disease: Insights from the CorLipid Trial. Metabolites. 2022; 12(9). PMC: 9504538. DOI: 10.3390/metabo12090816. View

19.

Popa L, Petresc B, Catana C, Moldovanu C, Feier D, Lebovici A . Association between cardiovascular risk factors and coronary artery disease assessed using CAD-RADS classification: a cross-sectional study in Romanian population. BMJ Open. 2020; 10(1):e031799. PMC: 6955553. DOI: 10.1136/bmjopen-2019-031799. View

20.

Danesh J, Lewington S, Thompson S, Lowe G, Collins R, Kostis J . Plasma fibrinogen level and the risk of major cardiovascular diseases and nonvascular mortality: an individual participant meta-analysis. JAMA. 2005; 294(14):1799-809. DOI: 10.1001/jama.294.14.1799. View