Dataset Information

Machine learning of clinical variables and coronary artery calcium scoring for the prediction of obstructive coronary artery disease on coronary computed tomography angiography: analysis from the CONFIRM registry.

ABSTRACT:

Aims

Symptom-based pretest probability scores that estimate the likelihood of obstructive coronary artery disease (CAD) in stable chest pain have moderate accuracy. We sought to develop a machine learning (ML) model, utilizing clinical factors and the coronary artery calcium score (CACS), to predict the presence of obstructive CAD on coronary computed tomography angiography (CCTA).

Methods and results

The study screened 35 281 participants enrolled in the CONFIRM registry, who underwent ?64 detector row CCTA evaluation because of either suspected or previously established CAD. A boosted ensemble algorithm (XGBoost) was used, with data split into a training set (80%) on which 10-fold cross-validation was done and a test set (20%). Performance was assessed of the (1) ML model (using 25 clinical and demographic features), (2) ML + CACS, (3) CAD consortium clinical score, (4) CAD consortium clinical score + CACS, and (5) updated Diamond-Forrester (UDF) score. The study population comprised of 13 054 patients, of whom 2380 (18.2%) had obstructive CAD (?50% stenosis). Machine learning with CACS produced the best performance [area under the curve (AUC) of 0.881] compared with ML alone (AUC of 0.773), CAD consortium clinical score (AUC of 0.734), and with CACS (AUC of 0.866) and UDF (AUC of 0.682), P?ConclusionA ML model incorporating clinical features in addition to CACS can accurately estimate the pretest likelihood of obstructive CAD on CCTA. In clinical practice, the utilization of such an approach could improve risk stratification and help guide downstream management.

SUBMITTER: Al'Aref SJ

PROVIDER: S-EPMC7849944 | biostudies-literature | 2020 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Machine learning of clinical variables and coronary artery calcium scoring for the prediction of obstructive coronary artery disease on coronary computed tomography angiography: analysis from the CONFIRM registry.

Al'Aref Subhi J SJ Maliakal Gabriel G Singh Gurpreet G van Rosendael Alexander R AR Ma Xiaoyue X Xu Zhuoran Z Alawamlh Omar Al Hussein OAH Lee Benjamin B Pandey Mohit M Achenbach Stephan S Al-Mallah Mouaz H MH Andreini Daniele D Bax Jeroen J JJ Berman Daniel S DS Budoff Matthew J MJ Cademartiri Filippo F Callister Tracy Q TQ Chang Hyuk-Jae HJ Chinnaiyan Kavitha K Chow Benjamin J W BJW Cury Ricardo C RC DeLago Augustin A Feuchtner Gudrun G Hadamitzky Martin M Hausleiter Joerg J Kaufmann Philipp A PA Kim Yong-Jin YJ Leipsic Jonathon A JA Maffei Erica E Marques Hugo H Gonçalves Pedro de Araújo PA Pontone Gianluca G Raff Gilbert L GL Rubinshtein Ronen R Villines Todd C TC Gransar Heidi H Lu Yao Y Jones Erica C EC Peña Jessica M JM Lin Fay Y FY Min James K JK Shaw Leslee J LJ

European heart journal 20200101 3

<h4>Aims</h4>Symptom-based pretest probability scores that estimate the likelihood of obstructive coronary artery disease (CAD) in stable chest pain have moderate accuracy. We sought to develop a machine learning (ML) model, utilizing clinical factors and the coronary artery calcium score (CACS), to predict the presence of obstructive CAD on coronary computed tomography angiography (CCTA).<h4>Methods and results</h4>The study screened 35 281 participants enrolled in the CONFIRM registry, who und ...[more]

PMID: 31513271

Similar Datasets

Project description:BackgroundThe extent to which the presence and extent of subclinical atherosclerosis by coronary computed tomography angiography influences a potential mortality benefit of statin is unknown. We evaluated the relationship between statin therapy, mortality, and subclinical atherosclerosis.MethodsIn the CONFIRM study, patients with normal or non-obstructive plaque (<50% diameter stenosis) for whom data on baseline statin use was available were included. Coronary artery calcium (CAC) was quantified using the Agatston score. The extent of non-obstructive coronary atherosclerosis was quantified using the segment involvement score (SIS). 8,016 patients were followed for a median of 2.5 years with analysis of all-cause mortality and major adverse cardiac events (MACE) including all-cause mortality, myocardial infarction, unstable angina, target vessel revascularization, and coronary artery disease-related hospitalization.Results1.2% of patients experienced all-cause mortality. Patients not on baseline statin therapy had a stepwise increased risk of all-cause mortality by CAC (relative to CAC = 0; CAC 1-99: hazard ratio [HR] 1.65, CAC 100-299: HR 2.19, and CAC≥300: HR 2.98) or SIS (relative to SIS = 0; SIS 1: HR 1.62, SIS 2-3: 2.48 and SIS≥4: 2.95). Conversely, in patients on baseline statin therapy, there was no significant increase in mortality risk with increasing CAC (p value for interaction = 0.049) or SIS (p value for interaction = 0.007). The incidence of MACE was 2.1%. Similar to the all-cause mortality, the risk of MACE was increased with CAC or SIS strata in patient not on baseline statin therapy. However, this relation was not observed in patient on baseline statin therapy.ConclusionIn individuals with non-obstructive coronary artery disease, increased risk of adverse events occurs with increasing CAC or SIS who are not on baseline statin therapy. Statin therapy is associated with a mitigation of risk of cardiac events in the presence of increasing atherosclerosis, with no particular threshold of disease burden.

Project description:AimsCoronary computed tomography angiography (CTA) has emerged as a non-invasive diagnostic method for patients with suspected coronary artery disease, but its usefulness in patients with complex coronary artery disease remains to be investigated. The present study sought to determine the agreement between separate heart teams on treatment decision-making based on either coronary CTA or conventional angiography.Methods and resultsSeparate heart teams composed of an interventional cardiologist, a cardiac surgeon, and a radiologist were randomized to assess the coronary artery disease with either coronary CTA or conventional angiography in patients with de novo left main or three-vessel coronary artery disease. Each heart team, blinded for the other imaging modality, quantified the anatomical complexity using the SYNTAX score and integrated clinical information using the SYNTAX Score II to provide a treatment recommendations based on mortality prediction at 4 years: coronary artery bypass grafting (CABG), percutaneous coronary intervention (PCI), or equipoise between CABG and PCI. The primary endpoint was the agreement between heart teams on the revascularization strategy. The secondary endpoint was the impact of fractional flow reserve derived from coronary CTA (FFRCT) on treatment decision and procedural planning. Overall, 223 patients were included. A treatment recommendation of CABG was made in 28% of the cases with coronary CTA and in 26% with conventional angiography. The agreement concerning treatment decision between coronary CTA and conventional angiography was high (Cohen's kappa 0.82, 95% confidence interval 0.74-0.91). The heart teams agreed on the coronary segments to be revascularized in 80% of the cases. FFRCT was available for 869/1108 lesions (196/223 patients). Fractional flow reserve derived from coronary CTA changed the treatment decision in 7% of the patients.ConclusionIn patients with left main or three-vessel coronary artery disease, a heart team treatment decision-making based on coronary CTA showed high agreement with the decision derived from conventional coronary angiography suggesting the potential feasibility of a treatment decision-making and planning based solely on this non-invasive imaging modality and clinical information.Trial registration numberNCT02813473.

Project description:BackgroundTo analyze the imaging features of coronary artery-to-pulmonary artery fistula (CPAF) on coronary computed tomography angiography (CCTA).MethodsThis was a retrospective study of 3,975 patients who underwent 320 row detector CCTA examinations in our hospital from May 2015 to July 2020. A total of 22 patients who diagnosed with CPAF were reviewed for CCTA imaging characteristics, including the origin, number, blood volume, opening size, and course of fistula vessels, and the drainage site, size, and imaging features of the fistula. All cases were analyzed for the presence of coronary atherosclerotic plaque and that of deficient left ventricular myocardial perfusion.ResultsA total of 22 CPAF cases detected by CCTA were collected (men, 11; women, 11; median age, 59.6±10.1 years). There were 7, 10, and 5 cases detected with 1, 2, and 3 fistula vessels, respectively, among which 4 originated from the left coronary artery, 4 from the right coronary artery, and 14 had bilateral origins. There were 10 cases in which the fistula vessels presented as a worm-like tortuous dilation with (n=5) or without (n=5) aneurysm, while 12 cases showed malformed vascular networks with (n=8) or without (n=4) aneurysm, respectively. The calculated incidence of aneurysm formation was 59.09%, and fistula vessels with an aneurysm had larger blood volume than those without. All fistula showed a single drainage site, with an average diameter of 2.81±1.48 mm where the diameter of fistula with aneurysm was larger than that without. The fistula vessels drained into the left anterolateral and anterior walls of main pulmonary artery and the proximal left inferior PA, respectively. Typical jet sign, smoke sign, and isodensity sign were presented in 22, 14 and 1 case, respectively. For the coexistent abnormalities analyzed in 22 cases, 17 participants with CPAF demonstrated hypoperfusion of the fistula vessels, and 11 demonstrated calcified plaque accompanied with luminal stenosis to different degrees.ConclusionsThe 320-row detector CCTA can comprehensively characterize the morphological features of CPAF, which is an optimal choice for physicians to make an accurate assessment before formulating patient management strategies.

Project description:ObjectivesCoronary artery calcium (CAC) scores derived from computed tomography (CT) scans are used for cardiovascular risk stratification. Artificial intelligence (AI) can assist in CAC quantification and potentially reduce the time required for human analysis. This study aimed to develop and evaluate a fully automated model that identifies and quantifies CAC.MethodsFully convolutional neural networks for automated CAC scoring were developed and trained on 2439 cardiac CT scans and validated using 771 scans. The model was tested on an independent set of 1849 cardiac CT scans. Agatston CAC scores were further categorised into five risk categories (0, 1-10, 11-100, 101-400, and > 400). Automated scores were compared to the manual reference standard (level 3 expert readers).ResultsOf 1849 scans used for model testing (mean age 55.7 ± 10.5 years, 49% males), the automated model detected the presence of CAC in 867 (47%) scans compared with 815 (44%) by human readers (p = 0.09). CAC scores from the model correlated very strongly with the manual score (Spearman's r = 0.90, 95% confidence interval [CI] 0.89-0.91, p < 0.001 and intraclass correlation coefficient = 0.98, 95% CI 0.98-0.99, p < 0.001). The model classified 1646 (89%) into the same risk category as human observers. The Bland-Altman analysis demonstrated little difference (1.69, 95% limits of agreement: -41.22, 44.60) and there was almost excellent agreement (Cohen's κ = 0.90, 95% CI 0.88-0.91, p < 0.001). Model analysis time was 13.1 ± 3.2 s/scan.ConclusionsThis artificial intelligence-based fully automated CAC scoring model shows high accuracy and low analysis times. Its potential to optimise clinical workflow efficiency and patient outcomes requires evaluation.Key points• Coronary artery calcium (CAC) scores are traditionally assessed using cardiac computed tomography and require manual input by human operators to identify calcified lesions. • A novel artificial intelligence (AI)-based model for fully automated CAC scoring was developed and tested on an independent dataset of computed tomography scans, showing very high levels of correlation and agreement with manual measurements as a reference standard. • AI has the potential to assist in the identification and quantification of CAC, thereby reducing the time required for human analysis.

Dataset Information

Machine learning of clinical variables and coronary artery calcium scoring for the prediction of obstructive coronary artery disease on coronary computed tomography angiography: analysis from the CONFIRM registry.

Aims

Methods and results

Publications

Machine learning of clinical variables and coronary artery calcium scoring for the prediction of obstructive coronary artery disease on coronary computed tomography angiography: analysis from the CONFIRM registry.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets