Machine Learning-based Algorithm Enables the Exclusion of Obstructive Coronary Artery Disease in the Patients Who Underwent Coronary Artery Calcium Scoring

Głowacki, Jan; Krysiński, Mateusz; Czaja-Ziółkowska, Monika; Wasilewski, Jarosław

doi:10.1016/j.acra.2019.11.016

Cited by 10 publications

(4 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… 23 , who performed prospective analysis of 1912 individuals and found ML-derived predictions to be superior to traditional atherosclerotic cardiovascular disease risk algorithm and CAC score. These predictive ML algorithms also predict obstructive CAD with a high degree of accuracy (AUC: 0.77; 24 sensitivity: 100 ± 0.0% and specificity 69.8 ± 3.6% 25 ). Automated identification of CAC score has been performed using k -nearest neighbour, CNN and gradient boosting ML with reasonably good accuracies (sensitivity: 73.8% and false positive rate: 0.1 errors per scan; 16 sensitivity: up to 72% and false positive rate: as low as 0.48 errors per scan; 18 and AUC: 0.67–0.85, 19 respectively).…”

Section: Applications Of Machine Learning In Cardiac Computed Tomographymentioning

confidence: 92%

Machine learning applications in cardiac computed tomography: a composite systematic review

Bray

Hanif

Alradhawi

et al. 2022

European Heart Journal Open

View full text Add to dashboard Cite

Introduction Artificial intelligence (AI) and machine learning (ML) models are rapidly being applied to analysis of cardiac computed tomography (CT). We sought to provide an overview of the contemporary advances brought about by the combination of ML and cardiac CT. Methods Six searches were performed in Medline, Embase and the Cochrane Library up to November 2021 for i) Computed Tomography-Fractional Flow Reserve (CT-FFR), ii) atrial fibrillation, iii) aortic stenosis, iv) plaque characterisation, v) fat quantification and vi) coronary artery calcium score. Results We included 57 studies pertaining to the aforementioned topics. Non-invasive CT-fractional flow reserve (FFR) can accurately be estimated using ML algorithms and has the potential to reduce the requirement for invasive angiography. Coronary artery calcification (CAC) and non-calcified coronary lesions can now be automatically and accurately calculated. Epicardial adipose tissue (EAT) can also be automatically, accurately and rapidly quantified. Effective ML algorithms have been developed to streamline and optimise the safety of aortic annular measurements to facilitate pre-transcatheter aortic valve replacement (TAVR) valve selection. Within electrophysiology, the left atrium (LA) can be segmented and resultant LA volumes have contributed to accurate predictions of post-ablation recurrence of atrial fibrillation. Conclusion In this review, we discuss the latest studies and evolving techniques of ML and cardiac CT.

show abstract

Section: Applications Of Machine Learning In Cardiac Computed Tomographymentioning

confidence: 92%

Machine learning applications in cardiac computed tomography: a composite systematic review

Bray

Hanif

Alradhawi

et al. 2022

European Heart Journal Open

View full text Add to dashboard Cite

show abstract

“…CAC can be estimated semi-quantitatively using three methods: the mass equivalent score, the volume score and the most widely used Agatston score. All these scoring methods are strongly correlated with each other [ 4 ]. The CAC value by the Agatston method is calculated by multiplying the area of calcified plaque by the density score.…”

Section: Methods Of Cac Evaluationmentioning

confidence: 99%

An update on the coronary calcium score: a review for clinicians

Czaja-Ziółkowska¹,

Wasilewski²,

Gąsior³

et al. 2022

pwki

Self Cite

View full text Add to dashboard Cite

The clinical manifestation of coronary artery atherosclerosis is coronary artery disease (CAD) with symptoms ranging from exertional chest pain due to reduction of coronary flow reserve to acute coronary syndrome due to rupture of usually a nonobstructive plaque with abrupt coronary blood flow reduction. CAD is the leading cause of morbidity and mortality worldwide. Therefore, identifying asymptomatic people at risk of CAD is pivotal to guide decision-making for primary prevention. Coronary artery calcium (CAC) is a hallmark of coronary artery atherosclerosis. It can be detected using cardiac computed tomography and quantified by the Agatston method. CAC examination is a cheap, fast and low radiation dose test, without injecting a contrast agent. It provides prognostic information over other traditional cardiovascular risk markers and established scoring systems, especially for low-risk subgroups such as women and younger adults, and indicates the appropriate moment to implement primary prevention, including acetylsalicylic acid and statins. In this review, we discuss the methods of CAC evaluation, the meaning of a zero CAC score (CACS), its conversion to CACS > 0 and the impact of this fact on cardiovascular risk, the effect of statins and proprotein convertase subtilisin/ kexin type 9 inhibitor on CAC progression, interpretation of CACS results, and CACS prognostic value in both asymptomatic and symptomatic patients.

show abstract

“…Raw data from coronary calcium score (CACS) scans were used to screen and predict the presence of obstructive CHD through the elaboration of a gradient boosting machine with a sensitivity of 100% and a specificity of 69.8% and a negative predictive value of 100%. 61 Wang et al 62 investigated the accuracy of a DL algorithm versus the classical quantification of CACS reporting and agreement between the 2 approaches with a correlation coefficient of 0.77, thus providing a reliable method for cardiac risk stratification.…”

Section: Cacs Evaluation and Coronary Plaque Classificationmentioning

confidence: 99%

Section: Ai and Machine Learning Models In Chdmentioning

confidence: 99%

Radiogenomics and Artificial Intelligence Approaches Applied to Cardiac Computed Tomography Angiography and Cardiac Magnetic Resonance for Precision Medicine in Coronary Heart Disease: A Systematic Review

Infante

Cavaliere

Punzo

et al. 2021

Circ: Cardiovascular Imaging

View full text Add to dashboard Cite

The risk of coronary heart disease (CHD) clinical manifestations and patient management is estimated according to risk scores accounting multifactorial risk factors, thus failing to cover the individual cardiovascular risk. Technological improvements in the field of medical imaging, in particular, in cardiac computed tomography angiography and cardiac magnetic resonance protocols, laid the development of radiogenomics. Radiogenomics aims to integrate a huge number of imaging features and molecular profiles to identify optimal radiomic/biomarker signatures. In addition, supervised and unsupervised artificial intelligence algorithms have the potential to combine different layers of data (imaging parameters and features, clinical variables and biomarkers) and elaborate complex and specific CHD risk models allowing more accurate diagnosis and reliable prognosis prediction. Literature from the past 5 years was systematically collected from PubMed and Scopus databases, and 60 studies were selected. We speculated the applicability of radiogenomics and artificial intelligence through the application of machine learning algorithms to identify CHD and characterize atherosclerotic lesions and myocardial abnormalities. Radiomic features extracted by cardiac computed tomography angiography and cardiac magnetic resonance showed good diagnostic accuracy for the identification of coronary plaques and myocardium structure; on the other hand, few studies exploited radiogenomics integration, thus suggesting further research efforts in this field. Cardiac computed tomography angiography resulted the most used noninvasive imaging modality for artificial intelligence applications. Several studies provided high performance for CHD diagnosis, classification, and prognostic assessment even though several efforts are still needed to validate and standardize algorithms for CHD patient routine according to good medical practice.

show abstract

Machine Learning-based Algorithm Enables the Exclusion of Obstructive Coronary Artery Disease in the Patients Who Underwent Coronary Artery Calcium Scoring

Cited by 10 publications

References 21 publications

Machine learning applications in cardiac computed tomography: a composite systematic review

Machine learning applications in cardiac computed tomography: a composite systematic review

An update on the coronary calcium score: a review for clinicians

Radiogenomics and Artificial Intelligence Approaches Applied to Cardiac Computed Tomography Angiography and Cardiac Magnetic Resonance for Precision Medicine in Coronary Heart Disease: A Systematic Review

Contact Info

Product

Resources

About