Artificial intelligence using a deep learning versus expert computed tomography human reading in calcium score and coronary artery calcium data and reporting system classification.

BACKGROUND: Artificial intelligence (AI) applied to cardiac imaging may provide improved processing, reading precision and advantages of automation. Coronary artery calcium (CAC) score testing is a standard stratification tool that is rapid and highly reproducible. We analyzed CAC results of 100 studies in order to determine the accuracy and correlation between the AI software (Coreline AVIEW, Seoul, South Korea) and expert level-3 computed tomography (CT) human CAC interpretation and its performance when coronary artery disease data and reporting system (coronary artery calcium data and reporting system) classification is applied. METHODS: A total of 100 non-contrast calcium score images were selected by blinded randomization and processed with the AI software versus human level-3 CT reading. The results were compared and the Pearson correlation index was calculated. The CAC-DRS classification system was applied, and the cause of category reclassification was determined using an anatomical qualitative description by the readers. RESULTS: The mean age was age 64.5 years, with 48% female. The absolute CAC scores between AI versus human reading demonstrated a highly significant correlation (Pearson coefficient R  = 0.996); however, despite these minimal CAC score differences, 14% of the patients had their CAC-DRS category reclassified. The main source of reclassification was observed in CAC-DRS 0-1, where 13 were recategorized, particularly between studies having a CAC Agatston score of 0 versus 1. Qualitative description of the errors showed that the main cause of misclassification was AI underestimation of right coronary calcium, AI overestimation of right ventricle densities and human underestimation of right coronary artery calcium. CONCLUSION: Correlation between AI and human values is excellent with absolute numbers. When the CAC-DRS classification system was adopted, there was a strong correlation in the respective categories. Misclassified were predominantly in the category of CAC = 0, most often with minimal values of calcium volume. Additional algorithm optimization with enhanced sensitivity and specificity for low values of calcium volume will be required to enhance AI CAC score utilization for minimal disease. Over a broad range of calcium scores, AI software for calcium scoring had an excellent correlation compared to human expert reading and in rare cases determined calcium missed by human interpretation.

Plaque Progression Differences Between Apixaban and Rivaroxaban in Patients With Atrial Fibrillation Measured With Cardiac Computed Tomography and Plaque Quantification.

BACKGROUND: Direct oral anticoagulants (DOACs) have been associated with less calcification and coronary plaque progression than warfarin. Whether different DOACs have different effects on coronary plaque burden and progression is not known. We compared the 12-month effects of apixaban and rivaroxaban on plaque characteristics and vascular morphology in patients with atrial fibrillation through quantitative cardiac computed tomographic angiography. STUDY QUESTION: In patients with nonvalvular atrial fibrillation using apixaban or rivaroxaban, are there differences in plaque quantification and progression measured with cardiac computed tomography? STUDY DESIGN: This is a post hoc analysis of 2 paired prospective, single-centered, randomized, open-label trials with blinded adjudication of results. In total, 74 patients were prospectively randomized in parallel trials: 29 to apixaban (2.5-5 mg BID) and 45 to rivaroxaban (20 mg QD). Serial cardiac computed tomographic angiography was performed at baseline and 52 weeks. MEASURES AND OUTCOMES: Comprehensive whole-heart analysis was performed for differences in the progression of percent atheroma volume (PAV), calcified plaque (CP) PAV, noncalcified plaque (NCP) PAV, positive arterial remodeling (PR) ≥1.10, and high-risk plaque (Cleerly Labs, New York, NY). RESULTS: Both groups had progression of all 3 plaque types (apixaban: CP 8.7 mm 3 , NCP 69.7 mm 3 , and LD-NCP 27.2 mm 3 ; rivaroxaban: CP 22.9 mm 3 , NCP 66.3 mm 3 , and LD-NCP 11.0 mm 3 ) and a total annual plaque PAV change (apixaban: PAV 1.5%, PAV-CP 0.12%, and PAV-NCP 0.92%; rivaroxaban: PAV 2.1%, PAV-CP 0.46%, and PAV-NCP 1.40%). There was significantly lower PAV-CP progression in the apixaban group compared with the rivaroxaban group (0.12% vs. 0.46% P = 0.02). High-risk plaque characteristics showed a significant change in PR of apixaban versus rivaroxaban ( P = 0.01). When the propensity score weighting model is applied, only PR changes are statistically significant ( P = 0.04). CONCLUSIONS: In both groups, there is progression of all types of plaque. There was a significant difference between apixaban and rivaroxaban on coronary calcification, with significantly lower calcific plaque progression in the apixaban group, and change in positive remodeling. With weighted modeling, only PR changes are statistically significant between the 2 DOACs.

Major Global Coronary Artery Calcium Guidelines.

This review summarizes the framework behind global guidelines of coronary artery calcium (CAC) in atherosclerotic cardiovascular disease risk assessment, for applications in both the clinical setting and preventive therapy. By comparing similarities and differences in recommendations, this review identifies most notable common features for the application of CAC presented by different cardiovascular societies across the world. Guidelines included from North America are as follows: 1) the 2019 American College of Cardiology/American Heart Association Guideline on the Primary Prevention of Cardiovascular Disease; and 2) the 2021 Canadian Cardiovascular Society Guidelines for the Management of Dyslipidemia for Prevention of Adult Cardiovascular Disease. The authors also included European guidelines: 1) the 2019 European Society for Cardiology/European Atherosclerosis Society Guidelines for the Management of Dyslipidemias; and 2) the 2016 National Institute for Health and Care Excellence Clinical Guidelines. In this comparison, the authors also discuss: 1) the Cardiac Society of Australia and New Zealand Guidelines on CAC; 2) the Chinese Society of Cardiology Guidelines; and 3) the Japanese Atherosclerosis Society Guidelines for Prevention of Atherosclerotic Cardiovascular Diseases. Last, they include statements made by specialty societies including the National Lipid Association, Society of Cardiovascular Computed Tomography, and U.S. Preventive Services Task Force. Utilizing an in-depth review of clinical evidence, these guidelines emphasize the importance of CAC in the primary and secondary prevention of atherosclerotic cardiovascular disease. International guidelines all empower a dynamic clinician-patient relationship and advocate for individualized discussions regarding disease management and pharmacotherapy treatment. Some differences in precise coronary artery calcium score intervals, risk cut points, treatment thresholds, and stratifiers of specific patient subgroups do exist. However, international guidelines employ more similarities than differences from both a clinical and functional perspective. Understanding the parallels among international coronary artery calcium guidelines is essential for clinicians to correctly adjudicate personalized statin and aspirin therapy and further medical management.

Serial Changes in Troponin I in COVID-19 Vaccine-Associated Myocarditis.

A 63-year-old woman presented with atypical chest pain after a third dose of the coronavirus disease 2019 (COVID-19) messenger ribonucleic acid (mRNA) vaccine. Serial cardiac troponin measurements were performed to evaluate the trajectory of her time-concentration curve which showed a typical myocarditis curve with rapid normalization. The diagnosis of myocarditis was confirmed by cardiac magnetic resonance imaging and follow-up imaging showed resolution. All symptoms resolved with weeks.