Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Aug 3:11:e15797.
doi: 10.7717/peerj.15797. eCollection 2023.

Risk factors for high CAD-RADS scoring in CAD patients revealed by machine learning methods: a retrospective study

Yueli Dai #  1 , Chenyu Ouyang #  2 , Guanghua Luo  2 , Yi Cao  1 , Jianchun Peng  1 , Anbo Gao  3   4   5 , Hong Zhou  2
Affiliations

Risk factors for high CAD-RADS scoring in CAD patients revealed by machine learning methods: a retrospective study

Yueli Dai et al. PeerJ. .

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 (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.

Keywords: CAD; CAD-RADS; ML; Plasma fibrinogen; Prediction; Risk factor.

PubMed Disclaimer

Conflict of interest statement

The authors declare that there are no competing interests.

Figures

Figure 1
Figure 1. The flowchart of patients recruited in this study.
CCTA, coronary computed tomography angiography; PCI, percutaneous coronary intervention; CAD-RADS, Coronary Artery Disease-Reporting and Data System.
Figure 2
Figure 2. MPR images of different degrees of coronary artery stenosis.
MPR images showing different degrees of coronary artery stenosis (yellow arrows): (A) Normal LAD without any plaque or stenosis (CAD-RADS 0); (B) minimal calcified plaque in the proximal LAD with minimal luminal narrowing <25% (CAD-RADS 1); (C) predominantly calcified plaque in the proximal LAD with 25%–49% diameter stenosis (CAD- RADS 2); (D) non-calcified plaque in the proximal LAD with 50%–69% diameter stenosis (CAD- RADS 3); (E) segmental non-calcified plaque in the mid LAD with 70%–99% diameter stenosis (CAD- RADS 4); (F) total occlusion of proximal and mid LAD; calcified and non-calcified mixed plaques support the diagnosis of chronic total occlusion (CAD- RADS 5). CAD-RADS, Coronary Artery Disease-Reporting and Data System; MPR, multiplanar reconstruction; LAD, left anterior descending artery.
Figure 3
Figure 3. The ROC curve of each machine learning model.
Each machine learning model was assessed by the ROC curve, which plots a curve according to its true positive rate (y-axis) against its false positive rate (x-axis). The larger area under the curve, the better the prediction accuracy of the model. (A) Random forest (RF). (B) Linear discriminant analysis (LDA). (C) Decision tree classification (DTC). (D) k-nearest neighbors (KNN). (E) Neural network (NN). (F) Support vector machine (SVM).
Figure 4
Figure 4. Feature importance based on the random forest model.
Feature importance based on the random forest model. HDL-C, high-density lipoprotein cholesterol; LDL-C, low-density lipoprotein cholesterol.
See this image and copyright information in PMC

References

    1. Akella A, Akella S. Machine learning algorithms for predicting coronary artery disease: efforts toward an open source solution. Future Science OA. 2021;7:Fso698. doi: 10.2144/fsoa-2020-0206. - DOI - PMC - PubMed
    1. Chuah J, Kruger U, Wang G, Yan P, Hahn J. Framework for testing robustness of machine learning-based classifiers. Journal of Personalized Medicine. 2022;12(8):1314. doi: 10.3390/jpm12081314. - DOI - PMC - PubMed
    1. Cury RC, Abbara S, Achenbach S, Agatston A, Berman DS, Budoff MJ, Dill KE, Jacobs JE, Maroules CD, Rubin GD, Rybicki FJ, Schoepf UJ, Shaw LJ, Stillman AE, White CS, Woodard PK, Leipsic JA. 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;9:1099–1113. doi: 10.1016/j.jcmg.2016.05.005. - DOI - PubMed
    1. Danesh J, Lewington S, Thompson SG, Lowe GD, Collins R, Kostis JB, Wilson AC, Folsom AR, Wu K, Benderly M, Goldbourt U, Willeit J, Kiechl S, Yarnell JW, Sweetnam PM, Elwood PC, Cushman M, Psaty BM, Tracy RP, Tybjaerg-Hansen A, Haverkate F, De Maat MP, Fowkes FG, Lee AJ, Smith FB, Salomaa V, Harald K, Rasi R, Vahtera E, Jousilahti P, Pekkanen J, D’Agostino R, Kannel WB, Wilson PW, Tofler G, Arocha-Piñango CL, Rodriguez-Larralde A, Nagy E, Mijares M, Espinosa R, Rodriquez-Roa E, Ryder E, Diez-Ewald MP, Campos G, Fernandez V, Torres E, Marchioli R, Valagussa F, Rosengren A, Wilhelmsen L, Lappas G, Eriksson H, Cremer P, Nagel D, Curb JD, Rodriguez B, Yano K, Salonen JT, Nyyssönen K, Tuomainen TP, Hedblad B, Lind P, Loewel H, Koenig W, Meade TW, Cooper JA, De Stavola B, Knottenbelt C, Miller GJ, Cooper JA, Bauer KA, Rosenberg RD, Sato S, Kitamura A, Naito Y, Palosuo T, Ducimetiere P, Amouyel P, Arveiler D, Evans AE, Ferrieres J, Juhan-Vague I, Bingham A, Schulte H, Assmann G, Cantin B, Lamarche B, Després JP, Dagenais GR, Tunstall-Pedoe H, Woodward M, Ben-Shlomo Y, Davey Smith G, Palmieri V, Yeh JL, Rudnicka A, Ridker P, Rodeghiero F, Tosetto A, Shepherd J, Ford I, Robertson M, Brunner E, Shipley M, Feskens EJ, Kromhout D, Dickinson A, Ireland B, Juzwishin K, Kaptoge S, Lewington S, Memon A, Sarwar N, Walker M, Wheeler J, White I, Wood A. Plasma fibrinogen level and the risk of major cardiovascular diseases and nonvascular mortality: an individual participant meta-analysis. JAMA. 2005;294:1799–1809. doi: 10.1001/jama.294.14.1799. - DOI - PubMed
    1. Foldyna B, Szilveszter B, Scholtz JE, Banerji D, Maurovich-Horvat P, Hoffmann U. CAD-RADS—a new clinical decision support tool for coronary computed tomography angiography. European Radiology. 2018;28:1365–1372. doi: 10.1007/s00330-017-5105-4. - DOI - PMC - PubMed

Publication types