The value of CCTA combined with machine learning for predicting angina pectoris in the anomalous origin of the right coronary artery.
Angina pectoris
Anomalous origin of coronary artery
Computed tomography
Machine learning
Journal
Biomedical engineering online
ISSN: 1475-925X
Titre abrégé: Biomed Eng Online
Pays: England
ID NLM: 101147518
Informations de publication
Date de publication:
12 Sep 2024
12 Sep 2024
Historique:
received:
23
03
2024
accepted:
27
08
2024
medline:
13
9
2024
pubmed:
13
9
2024
entrez:
12
9
2024
Statut:
epublish
Résumé
Anomalous origin of coronary artery is a common coronary artery anatomy anomaly. The anomalous origin of the coronary artery may lead to problems such as narrowing of the coronary arteries at the beginning of the coronary arteries and abnormal alignment, which may lead to myocardial ischemia due to the compression of the coronary arteries. Clinical symptoms include chest tightness and dyspnea, with angina pectoris as a common symptom that can be life-threatening. Timely and accurate diagnosis of anomalous coronary artery origin is of great importance. Coronary computed tomography angiography (CCTA) can provide detailed information on the characteristics of coronary arteries. Therefore, we combined CCTA and artificial intelligence (AI) technology to analyze the CCTA image features and clinical features of patients with anomalous origin of the right coronary artery to predict angina pectoris and the relevance of different features to angina pectoris. In this retrospective analysis, we compiled data on 15 characteristics from 126 patients diagnosed with anomalous right coronary artery origins. The dataset encompassed both CCTA imaging attributes, such as the positioning of the right coronary artery orifices and the alignment of coronary arteries, and clinical parameters including gender and age. To identify the most salient features, we employed the Chi-square feature selection method, which filters features based on their statistical significance. We then focused on features yielding a Chi-square score exceeding a threshold of 1, thereby narrowing down the selection to seven key variables, including cardiac function and gender. Subsequently, we evaluated seven classifiers known for their efficacy in classification tasks. Through rigorous training and testing, we conducted a comparative analysis to identify the top three classifiers with the highest accuracy rates. The top three classifiers in this study are Support Vector Machine (SVM), Ensemble Learning (EL), and Kernel Approximation Classifier. Among the SVM, EL and Kernel Approximation Classifier-based classifiers, the best performance is achieved for linear SVM, optimizable Ensembles Learning and SVM kernel, respectively. And the corresponding accuracy is 75.7%, 75.7%, and 73.0%, respectively. The AUC values are 0.77, 0.80, and 0.75, respectively. Machine learning (ML) models can predict angina pectoris caused by the origin anomalous of the right coronary artery, providing valuable auxiliary diagnostic information for clinicians and serving as a warning to clinicians. It is hoped that timely intervention and treatment can be realized to avoid serious consequences such as myocardial infarction.
Sections du résumé
BACKGROUND
BACKGROUND
Anomalous origin of coronary artery is a common coronary artery anatomy anomaly. The anomalous origin of the coronary artery may lead to problems such as narrowing of the coronary arteries at the beginning of the coronary arteries and abnormal alignment, which may lead to myocardial ischemia due to the compression of the coronary arteries. Clinical symptoms include chest tightness and dyspnea, with angina pectoris as a common symptom that can be life-threatening. Timely and accurate diagnosis of anomalous coronary artery origin is of great importance. Coronary computed tomography angiography (CCTA) can provide detailed information on the characteristics of coronary arteries. Therefore, we combined CCTA and artificial intelligence (AI) technology to analyze the CCTA image features and clinical features of patients with anomalous origin of the right coronary artery to predict angina pectoris and the relevance of different features to angina pectoris.
METHODS
METHODS
In this retrospective analysis, we compiled data on 15 characteristics from 126 patients diagnosed with anomalous right coronary artery origins. The dataset encompassed both CCTA imaging attributes, such as the positioning of the right coronary artery orifices and the alignment of coronary arteries, and clinical parameters including gender and age. To identify the most salient features, we employed the Chi-square feature selection method, which filters features based on their statistical significance. We then focused on features yielding a Chi-square score exceeding a threshold of 1, thereby narrowing down the selection to seven key variables, including cardiac function and gender. Subsequently, we evaluated seven classifiers known for their efficacy in classification tasks. Through rigorous training and testing, we conducted a comparative analysis to identify the top three classifiers with the highest accuracy rates.
RESULTS
RESULTS
The top three classifiers in this study are Support Vector Machine (SVM), Ensemble Learning (EL), and Kernel Approximation Classifier. Among the SVM, EL and Kernel Approximation Classifier-based classifiers, the best performance is achieved for linear SVM, optimizable Ensembles Learning and SVM kernel, respectively. And the corresponding accuracy is 75.7%, 75.7%, and 73.0%, respectively. The AUC values are 0.77, 0.80, and 0.75, respectively.
CONCLUSIONS
CONCLUSIONS
Machine learning (ML) models can predict angina pectoris caused by the origin anomalous of the right coronary artery, providing valuable auxiliary diagnostic information for clinicians and serving as a warning to clinicians. It is hoped that timely intervention and treatment can be realized to avoid serious consequences such as myocardial infarction.
Identifiants
pubmed: 39267079
doi: 10.1186/s12938-024-01286-0
pii: 10.1186/s12938-024-01286-0
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
95Subventions
Organisme : 2020 Joint Research Project of Shanghai Pudong New Area Health
ID : No.PW2020D-14
Informations de copyright
© 2024. The Author(s).
Références
Youniss MA, Ghoshhajra B, Bernard S, et al. Familial anomalous origin of right coronary artery from the left coronary sinus. Am J Cardiol. 2018;122(10):1800–2.
doi: 10.1016/j.amjcard.2018.08.016
Raimondi F, Bonnet D. Imaging of congenital anomalies of the coronary arteries. Diagn Interv Imaging. 2016;97(5):561–9.
doi: 10.1016/j.diii.2016.03.009
Lorenzoni G, Merella P, Viola G, et al. Anomalous origin of right coronary artery from left sinus of valsalva. J Invasive Cardiol. 2019;31(9):E279.
Majewski J, Shelton R, Varma M, et al. Anomalous origin of the right coronary artery from the left Valsalva sinus in a patient presenting with syncope, ventricular tachycardia, and electrocardiographic early repolarization pattern. Kardiol Pol. 2019;77(9):883–5.
doi: 10.33963/KP.14909
Maurovich-Horvat P, Bosserdt M, Kofoed KF, et al. CT or invasive coronary angiography in stable chest pain. N Engl J Med. 2022;386(17):1591–602.
doi: 10.1056/NEJMoa2200963
Patel NH, Dey AK, Sorokin AV, et al. Chronic inflammatory diseases and coronary heart disease: insights from cardiovascular CT. J Cardiovasc Comput Tomogr. 2022;16(1):7–18.
doi: 10.1016/j.jcct.2021.06.003
Cademartiri F, Casolo G, Clemente A, et al. Coronary CT angiography: a guide to examination, interpretation, and clinical indications. Expert Rev Cardiovasc Ther. 2021;19(5):413–25.
doi: 10.1080/14779072.2021.1915132
Lu H, Yao Y, Wang L, et al. Research progress of machine learning and deep learning in intelligent diagnosis of the coronary atherosclerotic heart disease. Comput Math Methods Med. 2022;2022:3016532.
Babaoğlu I, Fındık O, Bayrak M. Effects of principle component analysis on assessment of coronary artery diseases using support vector machine. Expert Syst Appl. 2010;37(3):2182–5.
doi: 10.1016/j.eswa.2009.07.055
Takx RA, de Jong PA, Leiner T, et al. Automated coronary artery calcification scoring in non-gated chest CT: agreement and reliability. PLoS ONE. 2014;9(3): e91239.
doi: 10.1371/journal.pone.0091239
Desai U, Nayak CG, Seshikala G. Application of ensemble classifiers in accurate diagnosis of myocardial ischemia conditions. Progr Artif Intell. 2017;6(3):245–53.
doi: 10.1007/s13748-017-0120-x
Kang D, Dey D, Slomka PJ, et al. Structured learning algorithm for detection of nonobstructive and obstructive coronary plaque lesions from computed tomography angiography. J Med Imaging (Bellingham). 2015;2(1):14003.
doi: 10.1117/1.JMI.2.1.014003
Felix Denzinger M W K B. Deep learning algorithms for coronary artery plaque characterisation from CCTA scans. Informatik aktuell, Springer, Wiesbaden, 2020. p. 1912–6417.
Hosseinzadeh M, Saha A, Brand P, et al. Deep learning-assisted prostate cancer detection on bi-parametric MRI: minimum training data size requirements and effect of prior knowledge. Eur Radiol. 2022;32(4):2224–34.
doi: 10.1007/s00330-021-08320-y
Dimopoulos AC, Nikolaidou M, Caballero FF, et al. Machine learning methodologies versus cardiovascular risk scores, in predicting disease risk. BMC Med Res Methodol. 2018;18(1):179.
doi: 10.1186/s12874-018-0644-1
Molossi S, Martinez-Bravo LE, Mery CM. Anomalous aortic origin of a coronary artery. Methodist Debakey Cardiovasc J. 2019;15(2):111–21.
doi: 10.14797/mdcj-15-2-111
Qi G, Jiang K, Qu J, et al. The material basis and mechanism of Xuefu Zhuyu decoction in treating stable angina pectoris and unstable angina pectoris. Evid Based Complement Alternat Med. 2022;2022:3741027.
doi: 10.1155/2022/3741027
Sousa H, Casanova J. Coronary artery abnormalities: current clinical issues. Rev Port Cardiol (Engl Ed). 2018;37(3):227–35.
doi: 10.1016/j.repc.2017.06.019
Chaosuwannakit N, Makarawate P. Diagnosis and prognostic significance of anomalous origin of coronary artery from the opposite sinus of Valsalva assess by dual-source coronary computed tomography angiography. Int J Cardiol Heart Vasc. 2021;32: 100723.
Nagashima K, Hiro T, Fukamachi D, et al. Anomalous origin of the coronary artery coursing between the great vessels presenting with a cardiovascular event (J-CONOMALY Registry). Eur Heart J Cardiovasc Imaging. 2020;21(2):222–30.
Padalino MA, Franchetti N, Sarris GE, et al. Anomalous aortic origin of coronary arteries: early results on clinical management from an international multicenter study. Int J Cardiol. 2019;291:189–93.
doi: 10.1016/j.ijcard.2019.02.007
Tyczynski P, Kukula K, Pietrasik A, et al. Anomalous origin of culprit coronary arteries in acute coronary syndromes. Cardiol J. 2018;25(6):683–90.
Saade C, Fakhredin RB, El AB, et al. Coronary artery anomalies and associated radiologic findings. J Comput Assist Tomogr. 2019;43(4):572–83.
doi: 10.1097/RCT.0000000000000875
Sirasapalli CN, Christopher J, Ravilla V. Prevalence and spectrum of coronary artery anomalies in 8021 patients: a single center study in South India. Indian Heart J. 2018;70(6):852–6.
doi: 10.1016/j.ihj.2018.01.035
Romeih S, Kaoud A, Shaaban M, et al. Coronary artery anomalies in tetralogy of Fallot patients evaluated by multi slice computed tomography; myocardial bridge is not a rare finding. Medicine (Baltimore). 2021;100(7): e24325.
doi: 10.1097/MD.0000000000024325
Liao J, Huang L, Qu M, et al. Artificial intelligence in coronary CT angiography: current status and future prospects. Front Cardiovasc Med. 2022;9: 896366.
doi: 10.3389/fcvm.2022.896366
Patel VI, Roy SK, Budoff MJ. Coronary computed tomography angiography (CCTA) vs functional imaging in the evaluation of stable ischemic heart disease. J Invasive Cardiol. 2021;33(5):E349–54.
doi: 10.25270/jic/20.00604
van Driest FY, Bijns CM, van der Geest RJ, et al. Utilizing (serial) coronary computed tomography angiography (CCTA) to predict plaque progression and major adverse cardiac events (MACE): results, merits and challenges. Eur Radiol. 2022;32(5):3408–22.
doi: 10.1007/s00330-021-08393-9
Miao KH, Miao JH, Miao GJ. Diagnosing coronary heart disease using ensemble machine learning. Int J Adv Comput Sci Appl. 2016;7(10):30–9.
Joloudari JH, Hassannataj Joloudari E, Saadatfar H, et al. Coronary artery disease diagnosis; ranking the significant features using a random trees model. Int J Environ Res Public Health. 2020;17(3):731.
doi: 10.3390/ijerph17030731
Desai U, Nayak CG, Seshikala G, et al. Automated diagnosis of coronary artery disease using pattern recognition approach. Annu Int Conf IEEE Eng Med Biol Soc. 2017;2017:434–7.
Yoneyama H, Nakajima K, Taki J, et al. Ability of artificial intelligence to diagnose coronary artery stenosis using hybrid images of coronary computed tomography angiography and myocardial perfusion SPECT. Eur J Hybrid Imaging. 2019;3(1):4.
doi: 10.1186/s41824-019-0052-8
van Assen M, Muscogiuri G, Caruso D, et al. Artificial intelligence in cardiac radiology. Radiol Med. 2020;125(11):1186–99.
doi: 10.1007/s11547-020-01277-w
Li Y, Dai Z, Cao D, et al. Chi-MIC-share: a new feature selection algorithm for quantitative structure–activity relationship models. RSC Adv. 2020;10(34):19852–60.
doi: 10.1039/D0RA00061B
Elhazmi A, Al-Omari A, Sallam H, et al. Machine learning decision tree algorithm role for predicting mortality in critically ill adult COVID-19 patients admitted to the ICU. J Infect Public Health. 2022;15(7):826–34.
doi: 10.1016/j.jiph.2022.06.008
Tsai CA, Chang YJ. Efficient selection of Gaussian Kernel SVM parameters for imbalanced data. Genes (Basel). 2023;14(3):583.
doi: 10.3390/genes14030583