Coronary CTA With AI-QCT Interpretation: Comparison With Myocardial Perfusion Imaging for Detection of Obstructive Stenosis Using Invasive Angiography as Reference Standard.

BACKGROUND. Deep learning frameworks have been applied to interpretation of coronary CTA performed for coronary artery disease (CAD) evaluation. OBJECTIVE. The purpose of our study was to compare the diagnostic performance of myocardial perfusion imaging (MPI) and coronary CTA with artificial intelligence quantitative CT (AI-QCT) interpretation for detection of obstructive CAD on invasive angiography and to assess the downstream impact of including coronary CTA with AI-QCT in diagnostic algorithms. METHODS. This study entailed a retrospective post hoc analysis of the derivation cohort of the prospective 23-center Computed Tomographic Evaluation of Atherosclerotic Determinants of Myocardial Ischemia (CREDENCE) trial. The study included 301 patients (88 women and 213 men; mean age, 64.4 ± 10.2 [SD] years) recruited from May 2014 to May 2017 with stable symptoms of myocardial ischemia referred for nonemergent invasive angiography. Patients underwent coronary CTA and MPI before angiography with quantitative coronary angiography (QCA) measurements and fractional flow reserve (FFR). CTA examinations were analyzed using an FDA-cleared cloud-based software platform that performs AI-QCT for stenosis determination. Diagnostic performance was evaluated. Diagnostic algorithms were compared. RESULTS. Among 102 patients with no ischemia on MPI, AI-QCT identified obstructive (≥ 50%) stenosis in 54% of patients, including severe (≥ 70%) stenosis in 20%. Among 199 patients with ischemia on MPI, AI-QCT identified nonobstructive (1-49%) stenosis in 23%. AI-QCT had significantly higher AUC (all p < .001) than MPI for predicting ≥ 50% stenosis by QCA (0.88 vs 0.66), ≥ 70% stenosis by QCA (0.92 vs 0.81), and FFR < 0.80 (0.90 vs 0.71). An AI-QCT result of ≥ 50% stenosis and ischemia on stress MPI had sensitivity of 95% versus 74% and specificity of 63% versus 43% for detecting ≥ 50% stenosis by QCA measurement. Compared with performing MPI in all patients and those showing ischemia undergoing invasive angiography, a scenario of performing coronary CTA with AIQCT in all patients and those showing ≥ 70% stenosis undergoing invasive angiography would reduce invasive angiography utilization by 39%; a scenario of performing MPI in all patients and those showing ischemia undergoing coronary CTA with AI-QCT and those with ≥ 70% stenosis on AI-QCT undergoing invasive angiography would reduce invasive angiography utilization by 49%. CONCLUSION. Coronary CTA with AI-QCT had higher diagnostic performance than MPI for detecting obstructive CAD. CLINICAL IMPACT. A diagnostic algorithm incorporating AI-QCT could substantially reduce unnecessary downstream invasive testing and costs. TRIAL REGISTRATION. Clinicaltrials.gov NCT02173275.

Quantitative assessment of coronary plaque volume change related to triglyceride glucose index: The Progression of AtheRosclerotic PlAque DetermIned by Computed TomoGraphic Angiography IMaging (PARADIGM) registry.

BACKGROUND: The association between triglyceride glucose (TyG) index and coronary atherosclerotic change remains unclear. We aimed to evaluate the association between TyG index and coronary plaque progression (PP) using serial coronary computed tomography angiography (CCTA). METHODS: A total of 1143 subjects (aged 60.7 ± 9.3 years, 54.6% male) who underwent serial CCTA with available data on TyG index and diabetic status were analyzed from The Progression of AtheRosclerotic PlAque DetermIned by Computed TomoGraphic Angiography IMaging (PARADIGM) registry. PP was defined as plaque volume (PV) (mm3) at follow-up minus PV at index > 0. Annual change of PV (mm3/year) was defined as PV change divided by inter-scan period. Rapid PP was defined as the progression of percent atheroma volume (PV divided by vessel volume multiplied by 100) ≥ 1.0%/year. RESULTS: The median inter-scan period was 3.2 (range 2.6-4.4) years. All participants were stratified into three groups based on TyG index tertiles. The overall incidence of PP was 77.3%. Baseline total PV (group I [lowest]: 30.8 (0.0-117.7), group II: 47.2 (6.2-160.4), and group III [highest]: 57.5 (8.4-154.3); P < 0.001) and the annual change of total PV (group I: 5.7 (0.0-20.2), group II: 7.6 (0.5-23.5), and group III: 9.4 (1.4-27.7); P = 0.010) were different among all groups. The risk of PP (odds ratio [OR] 1.648; 95% confidence interval [CI] 1.167-2.327; P = 0.005) and rapid PP (OR 1.777; 95% CI 1.288-2.451; P < 0.001) was increased in group III compared to that in group I. TyG index had a positive and significant association with an increased risk of PP and rapid PP after adjusting for confounding factors. CONCLUSION: TyG index is an independent predictive marker for the progression of coronary atherosclerosis. Clinical registration ClinicalTrials.gov NCT02803411.

Clinical feasibility of catheter-directed selective intracoronary computed tomography angiography using an extremely low dose of iodine in patients with coronary artery disease.

OBJECTIVE: This study aimed to evaluate the clinical feasibility of catheter-directed selective computed tomography angiography (S-CTA) in patients with coronary artery disease (CAD). METHODS: We prospectively enrolled 65 patients diagnosed with CAD who underwent conventional computed tomography angiography (C-CTA). C-CTA was performed with 60-90 mL of contrast medium (370 mg iodine/mL), whereas S-CTA was performed with 15 mL of contrast medium and 17.19 mg iodine/mL. Luminal enhancement range, homogeneity of luminal enhancement, image quality, plaque volume (PV), and percent aggregate plaque volume (%APV) were measured. Paired Student's t test, Wilcoxon rank-sum test, and Pearson's correlation coefficient were used to compare two methods. RESULTS: Luminal enhancement was significantly higher on S-CTA than on C-CTA (324.4 ± 8.0 Hounsfield unit (HU) vs. 312.0 ± 8.0 HU, p < 0.0001 in the per-vessel analysis). Transluminal attenuation gradient showed a significantly slower reduction pattern on S-CTA than on C-CTA (-0.65 HU/10 mm vs. -0.89 HU/10 mm, p < 0.0001 in the per-vessel analysis). Image noise was significantly lower on S-CTA than on C-CTA (39.6 ± 10.0 HU vs. 43.9 ± 9.4 HU, p < 0.0001). There was excellent correlation between S-CTA and C-CTA with respect to PV and %APV (r = 0.99, r = 0.98, respectively). CONCLUSIONS: S-CTA might be useful in facilitating atherosclerotic plaque analysis and providing guidance for complex lesions such as chronic total occlusion, particularly in cases in which on-site procedure planning is required. KEY POINTS: • Selective computed tomography angiography (S-CTA) can serve as an intraprocedural computed tomography angiography protocol. • S-CTA was performed with low dose of iodine compared with conventional computed tomography angiography. • S-CTA enables on-site atherosclerotic plaque analysis.

Optimal boundary detection method and window settings for coronary atherosclerotic plaque volume analysis in coronary computed tomography angiography: comparison with intravascular ultrasound.

OBJECTIVE: To evaluate optimal methodology for quantitative plaque volume analysis by coronary CT angiography (QCT). METHODS: Fifty-one coronary artery segments were evaluated and contour measurements based on two different methods [(1) no gap, or (2) fixed 0.3-mm gap between inner and outer boundary] were compared with intravascular ultrasound (IVUS). In addition, three different window width (WW) and level (WL) settings [fixed (740/220) Hounsfield unit (HU), adjusted (155 % and 65 % of mean luminal intensity of the segment, and aorta adjusted (155 % and 65 % of mean luminal intensity of central aorta)] were used for semiautomated plaque volume analysis. RESULTS: For boundary detection, the no gap method led to underestimation compared with IVUS (105.4 ± 82.3 vs. 136.1 ± 72.8 mm(3), p < 0.001), while fixed 0.3-mm gap showed no difference between IVUS and QCT (136.1 ± 72.8 vs. 139.8 ± 93.9 mm(3), p = 0.50). Comparison of the three different window settings demonstrated that the aorta adjusted setting underestimated (120.5 ± 74.3 vs. 136.1 ± 72.8 mm(3), p = 0.003), while fixed setting showed the least mean difference compared with IVUS (3.8 ± 39.8 mm(3), p = 0.50). CONCLUSION: For plaque volumetric assessment, optimal results were obtained with fixed 0.3-mm gap with fixed HU setting (740/220). KEY POINTS: • Quantitative plaque volume analysis by coronary CT angiography has recently emerged. • Different boundary detection methods and window width and level settings were evaluated. • Fixed 0.3-mm gap with fixed HU setting (740/220) afforded optimal results.

Warranty Period of Zero Coronary Artery Calcium Score for Predicting All-Cause Mortality According to Cardiac Risk Burden in Asymptomatic Korean Adults.

BACKGROUND: The aim of this study was to examine whether zero coronary artery calcium (CAC) score is associated with favorable prognosis of all-cause mortality (ACM) according to a panel of conventional risk factors (RF) in asymptomatic Korean adults.Methods and Results:A total of 48,215 individuals were stratified according to presence/absence of CAC, and the following RF were examined: hypertension, diabetes, current smoking, high low-density lipoprotein cholesterol, and low high-density lipoprotein cholesterol. The RF were summed on composite score as 0, 1-2, or ≥3 RF present. The warranty period was defined as the time to cumulative mortality rate >1%. Across a median follow-up of 4.4 years (IQR, 2.7-6.6), 415 (0.9%) deaths occurred. Incidence per 1,000 person-years for ACM was consistently higher in subjects with any CAC, irrespective of number of RF. The warranty period was substantially longer (eg, 9 vs. 5 years) for CAC=0 compared with CAC >0. The latter observation did not change materially according to pre-specified RF, but difference in warranty period according to presence/absence of CAC reduced somewhat when RF burden increased. CONCLUSIONS: In asymptomatic Korean adults, the absence of CAC evoked a strong protective effect against ACM as reflected by longer warranty period, when no other RF were present. The usefulness of zero CAC score and its warranty period requires further validation in the presence of multiple RF. (Circ J 2016; 80: 2356-2361).

Clinical Feasibility of 3D Automated Coronary Atherosclerotic Plaque Quantification Algorithm on Coronary Computed Tomography Angiography: Comparison with Intravascular Ultrasound.

OBJECTIVE: To evaluate the diagnostic performance of automated coronary atherosclerotic plaque quantification (QCT) by different users (expert/non-expert/automatic). METHODS: One hundred fifty coronary artery segments from 142 patients who underwent coronary computed tomography angiography (CCTA) and intravascular ultrasound (IVUS) were analyzed. Minimal lumen area (MLA), maximal lumen area stenosis percentage (%AS), mean plaque burden percentage (%PB), and plaque volume were measured semi-automatically by expert, non-expert, and fully automatic QCT analyses, and then compared to IVUS. RESULTS: Between IVUS and expert QCT analysis, the correlation coefficients (r) for the MLA, %AS, %PB, and plaque volume were excellent: 0.89 (p < 0.001), 0.84 (p < 0.001), 0.91 (p < 0.001), and 0.94 (p < 0.001), respectively. There were no significant differences in the mean parameters (all p values >0.05) except %AS (p = 0.01). The automatic QCT analysis showed comparable performance to non-expert QCT analysis, showing correlation coefficients (r) of the MLA (0.80 vs. 0.82), %AS (0.82 vs. 0.80), %PB (0.84 vs. 0.73), and plaque volume (0.84 vs. 0.79) when they were compared to IVUS, respectively. CONCLUSION: Fully automatic QCT analysis showed clinical utility compared with IVUS, as well as a compelling performance when compared with semiautomatic analyses. KEY POINTS: • Coronary CTA enables the assessment of coronary atherosclerotic plaque. • High-risk plaque characteristics and overall plaque burden can predict future cardiac events. • Coronary atherosclerotic plaque quantification is currently unfeasible in practice. • Quantitative computed tomography coronary plaque analysis software (QCT) enables feasible plaque quantification. • Fully automatic QCT analysis shows excellent performance.

CT angiography (CTA) and diagnostic performance of noninvasive fractional flow reserve: results from the Determination of Fractional Flow Reserve by Anatomic CTA (DeFACTO) study.

OBJECTIVE: Fractional flow reserve (FFR) computed from standard coronary CT scans (FFRCT) is a novel noninvasive method for determining the functional significance of coronary artery lesions. Compared with CT alone, FFRCT significantly improves diagnostic accuracy and discrimination for patients with and without hemodynamically significant coronary artery stenoses. To date, the impact of CT image quality on diagnostic performance of FFRCT is unknown. We evaluated the impact of patient preparation, CT scan protocol, and factors related to image quality on the diagnostic accuracy of FFRCT. SUBJECTS AND METHODS: We studied stable patients with suspected coronary artery disease (CAD), enrolled from 17 centers, who underwent CT, invasive coronary angiography, FFR, and FFRCT. The accuracy of CT and FFRCT for diagnosis of ischemia was compared against an invasive FFR reference standard. Anatomically obstructive CAD was defined by a stenosis value of at least 50 by CT or invasive coronary angiography, whereas ischemia was defined by an FFR or FFRCT of up to 0.80. Ischemia was assessed at the per-patient and per-vessel levels. Diagnostic performance of FFRCT was then evaluated in relation to patient preparation, including administration before CT of a ß-blocker or nitroglycerin, as well as in relation to imaging characteristics, including misalignment, noise, motion, and coronary artery calcium. RESULTS: Among 252 study participants, 137 (54.0%) had an abnormal FFR. Administration of a ß-blocker increased FFRCT specificity (51.0% vs 66.0%; p = 0.03) with lower bias (-0.084 vs -0.048; p = 0.008), whereas nitroglycerin pretreatment within 30 minutes of CT was associated with improved specificity (54.0% vs 75.0%; p = 0.013). Misalignment artifacts resulted in impaired sensitivity (43.0% vs 86.0%; p = 0.001) with resultant reductions in overall accuracy (56.0% vs 71.0%; p = 0.03). No differences in diagnostic performance of FFRCT were noted in the presence of coronary motion or increasing coronary artery calcium score. CONCLUSION: Use of ß-blockade and nitroglycerin administration before CT improve diagnostic performance of FFRCT. Diagnostic accuracy of FFRCT is significantly reduced in the setting of misalignment artifacts.

Impact of hypertriglyceridaemia on cardiovascular mortality according to low-density lipoprotein cholesterol in a 15.6-million population.

AIMS: The aim of this study was to assess the association between triglyceride (TG) levels and cardiovascular disease (CVD) mortality concerning low-density lipoprotein cholesterol (LDL-C) and age in the general population. METHODS AND RESULTS: From the Korean National Health Insurance Service database, 15 672 028 participants aged 18-99 who underwent routine health examinations were followed up for CVD mortality. Hazard ratios for CVD mortality were calculated using Cox models after adjusting for various confounders. During a mean of 8.8 years of follow-up, 105 174 individuals died of CVD. There was a clear log-linear association between TG and overall CVD mortality down to 50 mg/dL. Each two-fold increase in TG was associated with 1.10-fold (overall CVD), 1.22-fold [ischaemic heart disease (IHD)], 1.24-fold [acute myocardial infarction (AMI)], and 1.10-fold (ischaemic stroke) higher CVD mortality. Haemorrhagic stroke and heart failure were not associated with TG levels. The impact of hypertriglyceridaemia (HTG) on CVD weakened but remained present in persons with LDL-C < 100 mg/dL, in whom each two-fold higher TG was associated with 1.05-fold (overall CVD), 1.12-fold (IHD), 1.15-fold (AMI), and 1.05-fold (ischaemic stroke) higher CVD mortality. The younger population (18-44 years) had stronger associations between TG levels and mortality from overall CVD, IHD, and AMI than the older population. CONCLUSION: Hypertriglyceridaemia independently raises CVD mortality with lingering risks in young and older individuals with low LDL-C levels, suggesting the importance of management of HTG even with controlled LDL-C.

This prospective study evaluated the association between triglyceride (TG) levels and cardiovascular disease (CVD) mortality in the general population, particularly in individuals with well-controlled low-density lipoprotein cholesterol (LDL-C) levels. The TG levels log-linearly increased the mortality from CVD, especially ischaemic heart disease and ischaemic stroke, down to at least 50 mg/dL (0.56 mmol/L), as residual CVD risks associated with high TG were apparent in individuals, even with LDL-C < 100 mg/dL (2.59 mmol/L). Maintaining TG levels below 100 mg/dL may be beneficial even in seemingly low-risk groups, such as young people with normal or optimal LDL-C levels.

Identifying Coronary Artery Calcification Using Chest X-ray Radiographs and Machine Learning: The Role of the Radiomics Score.

PURPOSE: To evaluate the ability of radiomics score (RS)-based machine learning to identify moderate to severe coronary artery calcium (CAC) on chest x-ray radiographs (CXR). MATERIALS AND METHODS: We included 559 patients who underwent a CAC scan with CXR obtained within 6 months and divided them into training (n = 391) and validation (n = 168) cohorts. We extracted radiomic features from annotated cardiac contours in the CXR images and developed an RS through feature selection with the least absolute shrinkage and selection operator regression in the training cohort. We evaluated the incremental value of the RS in predicting CAC scores when combined with basic clinical factor in the validation cohort. To predict a CAC score ≥100, we built an RS-based machine learning model using random forest; the input variables were age, sex, body mass index, and RS. RESULTS: The RS was the most prominent factor for the CAC score ≥100 predictions (odds ratio = 2.33; 95% confidence interval: 1.62-3.44; P < 0.001) compared with basic clinical factor. The machine learning model was tested in the validation cohort and showed an area under the receiver operating characteristic curve of 0.808 (95% confidence interval: 0.75-0.87) for a CAC score ≥100 predictions. CONCLUSIONS: The use of an RS-based machine learning model may have the potential as an imaging marker to screen patients with moderate to severe CAC scores before diagnostic imaging tests, and it may improve the pretest probability of detecting coronary artery disease in clinical practice.

Artificial intelligence-enhanced automation of left ventricular diastolic assessment: a pilot study for feasibility, diagnostic validation, and outcome prediction.

Background: Evaluating left ventricular diastolic function (LVDF) is crucial in echocardiography; however, the complexity and time demands of current guidelines challenge clinical use. This study aimed to develop an artificial intelligence (AI)-based framework for automatic LVDF assessment to reduce subjectivity and improve accuracy and outcome prediction. Methods: We developed an AI-based LVDF assessment framework using a nationwide echocardiographic dataset from five tertiary hospitals. This framework automatically identifies views, calculates diastolic parameters, including mitral inflow and annular velocities (E/A ratio, e' velocity, and E/e' ratio), maximal tricuspid regurgitation velocity, left atrial (LA) volume index, and left atrial reservoir strain (LARS). Subsequently, it grades LVDF according to guidelines. The AI-framework was validated on an external dataset composed of randomly screened 173 outpatients who underwent transthoracic echocardiography with suspicion for diastolic dysfunction and 33 individuals from medical check-ups with normal echocardiograms at Seoul National University Bundang Hospital, tertiary medical center in Korea, between May 2012 and June 2022. Additionally, we assessed the predictive value of AI-derived diastolic parameters and LVDF grades for a clinical endpoint, defined as a composite of all-cause death and hospitalization for heart failure, using Cox-regression risk modelling. Results: In an evaluation with 200 echocardiographic examinations (167 suspected diastolic dysfunction patients, 33 controls), it achieves an overall accuracy of 99.1% in identifying necessary views. Strong correlations (Pearson coefficient 0.901-0.959) were observed between AI-derived and manually-derived measurements of diastolic parameters, including LARS as well as conventional parameters. When following the guidelines, whether utilizing AI-derived or manually-derived parameters, the evaluation of LVDF consistently showed high concordance rates (94%). However, both methods exhibited lower concordance rates with the clinician's prior assessments (77.5% and 78.5%, respectively). Importantly, both AI-derived and manually-derived LVDF grades independently demonstrated significant prognostic value [adjusted hazard ratio (HR) =3.03; P=0.03 and adjusted HR =2.75; P=0.04, respectively] for predicting clinical outcome. In contrast, the clinician's prior grading lost its significance as a prognostic indicator after adjusting for clinical risk factors (adjusted HR =1.63; P=0.36). AI-derived LARS values significantly decreased with worsening LVDF (P for trend <0.001), and low LARS (<17%) was associated with increased risk for the clinical outcome (Log-rank P=0.04) relative to that for preserved LARS (≥17%). Conclusions: Our AI-based approach for automatic LVDF assessment on echocardiography is feasible, potentially enhancing clinical diagnosis and outcome prediction.

Urinary biomarkers for early detection of recovery in patients with acute kidney injury.

Urinary biomarkers of acute kidney injury (AKI) have been revealed recently to be useful for prior prediction of AKI. However, it is unclear whether these urinary biomarkers can also detect recovery from established AKI. Urinary biomarkers, including neutrophil gelatinase-associated lipocalin (NGAL) and cystatin C, were measured every 2 days for 8 days in 66 patients with AKI. At day 0, there were no significant differences in plasma creatinine, BUN, and urine cystatin C between AKI patients in the recovery (n = 33) and non-recovery (n = 33) groups. Plasma creatinine concentrations were significantly lower in the recovery group (3.0 ± 2.0 mg/dL) than in the non-recovery group (5.4 ± 1.9 mg/dL) on day 4 after AKI diagnosis (P < 0.001). In contrast, there were significant differences in urine NGAL between the two groups starting on day 0 (297.2 ± 201.4 vs 407.6 ± 190.4 ng/mL, P = 0.025) through the end of the study (123.7 ± 119.0 vs 434.3 ± 121.5 ng/mL, P < 0.001). The multiple logistic regression analysis showed that urine NGAL could independently predict recovery from AKI. Conclusively, this prospective observational study demonstrates that urine NGAL can be a highly versatile marker for early detection of the recovery phase in established AKI patients.

AI Evaluation of Stenosis on Coronary CTA, Comparison With Quantitative Coronary Angiography and Fractional Flow Reserve: A CREDENCE Trial Substudy.

BACKGROUND: Clinical reads of coronary computed tomography angiography (CTA), especially by less experienced readers, may result in overestimation of coronary artery disease stenosis severity compared with expert interpretation. Artificial intelligence (AI)-based solutions applied to coronary CTA may overcome these limitations. OBJECTIVES: This study compared the performance for detection and grading of coronary stenoses using artificial intelligence-enabled quantitative coronary computed tomography (AI-QCT) angiography analyses to core lab-interpreted coronary CTA, core lab quantitative coronary angiography (QCA), and invasive fractional flow reserve (FFR). METHODS: Coronary CTA, FFR, and QCA data from 303 stable patients (64 ± 10 years of age, 71% male) from the CREDENCE (Computed TomogRaphic Evaluation of Atherosclerotic DEtermiNants of Myocardial IsChEmia) trial were retrospectively analyzed using an Food and Drug Administration-cleared cloud-based software that performs AI-enabled coronary segmentation, lumen and vessel wall determination, plaque quantification and characterization, and stenosis determination. RESULTS: Disease prevalence was high, with 32.0%, 35.0%, 21.0%, and 13.0% demonstrating ≥50% stenosis in 0, 1, 2, and 3 coronary vessel territories, respectively. Average AI-QCT analysis time was 10.3 ± 2.7 minutes. AI-QCT evaluation demonstrated per-patient sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of 94%, 68%, 81%, 90%, and 84%, respectively, for ≥50% stenosis, and of 94%, 82%, 69%, 97%, and 86%, respectively, for detection of ≥70% stenosis. There was high correlation between stenosis detected on AI-QCT evaluation vs QCA on a per-vessel and per-patient basis (intraclass correlation coefficient = 0.73 and 0.73, respectively; P < 0.001 for both). False positive AI-QCT findings were noted in in 62 of 848 (7.3%) vessels (stenosis of ≥70% by AI-QCT and QCA of <70%); however, 41 (66.1%) of these had an FFR of <0.8. CONCLUSIONS: A novel AI-based evaluation of coronary CTA enables rapid and accurate identification and exclusion of high-grade stenosis and with close agreement to blinded, core lab-interpreted quantitative coronary angiography. (Computed TomogRaphic Evaluation of Atherosclerotic DEtermiNants of Myocardial IsChEmia [CREDENCE]; NCT02173275).

Atherosclerosis Imaging Quantitative Computed Tomography (AI-QCT) to guide referral to invasive coronary angiography in the randomized controlled CONSERVE trial.

AIMS: We compared diagnostic performance, costs, and association with major adverse cardiovascular events (MACE) of clinical coronary computed tomography angiography (CCTA) interpretation versus semiautomated approach that use artificial intelligence and machine learning for atherosclerosis imaging-quantitative computed tomography (AI-QCT) for patients being referred for nonemergent invasive coronary angiography (ICA). METHODS: CCTA data from individuals enrolled into the randomized controlled Computed Tomographic Angiography for Selective Cardiac Catheterization trial for an American College of Cardiology (ACC)/American Heart Association (AHA) guideline indication for ICA were analyzed. Site interpretation of CCTAs were compared to those analyzed by a cloud-based software (Cleerly, Inc.) that performs AI-QCT for stenosis determination, coronary vascular measurements and quantification and characterization of atherosclerotic plaque. CCTA interpretation and AI-QCT guided findings were related to MACE at 1-year follow-up. RESULTS: Seven hundred forty-seven stable patients (60 ± 12.2 years, 49% women) were included. Using AI-QCT, 9% of patients had no CAD compared with 34% for clinical CCTA interpretation. Application of AI-QCT to identify obstructive coronary stenosis at the ≥50% and ≥70% threshold would have reduced ICA by 87% and 95%, respectively. Clinical outcomes for patients without AI-QCT-identified obstructive stenosis was excellent; for 78% of patients with maximum stenosis < 50%, no cardiovascular death or acute myocardial infarction occurred. When applying an AI-QCT referral management approach to avoid ICA in patients with <50% or <70% stenosis, overall costs were reduced by 26% and 34%, respectively. CONCLUSIONS: In stable patients referred for ACC/AHA guideline-indicated nonemergent ICA, application of artificial intelligence and machine learning for AI-QCT can significantly reduce ICA rates and costs with no change in 1-year MACE.

Impact of statins based on high-risk plaque features on coronary plaque progression in mild stenosis lesions: results from the PARADIGM study.

AIMS: To investigate the impact of statins on plaque progression according to high-risk coronary atherosclerotic plaque (HRP) features and to identify predictive factors for rapid plaque progression in mild coronary artery disease (CAD) using serial coronary computed tomography angiography (CCTA). METHODS AND RESULTS: We analyzed mild stenosis (25-49%) CAD, totaling 1432 lesions from 613 patients (mean age, 62.2 years, 63.9% male) and who underwent serial CCTA at a ≥2 year inter-scan interval using the Progression of AtheRosclerotic PlAque DetermIned by Computed TomoGraphic Angiography Imaging (NCT02803411) registry. The median inter-scan period was 3.5 ± 1.4 years; plaques were quantitatively assessed for annualized percent atheroma volume (PAV) and compositional plaque volume changes according to HRP features, and the rapid plaque progression was defined by the ≥90th percentile annual PAV. In mild stenotic lesions with ≥2 HRPs, statin therapy showed a 37% reduction in annual PAV (0.97 ± 2.02 vs. 1.55 ± 2.22, P = 0.038) with decreased necrotic core volume and increased dense calcium volume compared to non-statin recipient mild lesions. The key factors for rapid plaque progression were ≥2 HRPs [hazard ratio (HR), 1.89; 95% confidence interval (CI), 1.02-3.49; P = 0.042], current smoking (HR, 1.69; 95% CI 1.09-2.57; P = 0.017), and diabetes (HR, 1.55; 95% CI, 1.07-2.22; P = 0.020). CONCLUSION: In mild CAD, statin treatment reduced plaque progression, particularly in lesions with a higher number of HRP features, which was also a strong predictor of rapid plaque progression. Therefore, aggressive statin therapy might be needed even in mild CAD with higher HRPs. CLINICAL TRIAL REGISTRATION: ClinicalTrials.gov NCT02803411.

Risk factors based vessel-specific prediction for stages of coronary artery disease using Bayesian quantile regression machine learning method: Results from the PARADIGM registry.

BACKGROUND AND HYPOTHESIS: The recently introduced Bayesian quantile regression (BQR) machine-learning method enables comprehensive analyzing the relationship among complex clinical variables. We analyzed the relationship between multiple cardiovascular (CV) risk factors and different stages of coronary artery disease (CAD) using the BQR model in a vessel-specific manner. METHODS: From the data of 1,463 patients obtained from the PARADIGM (NCT02803411) registry, we analyzed the lumen diameter stenosis (DS) of the three vessels: left anterior descending (LAD), left circumflex (LCx), and right coronary artery (RCA). Two models for predicting DS and DS changes were developed. Baseline CV risk factors, symptoms, and laboratory test results were used as the inputs. The conditional 10%, 25%, 50%, 75%, and 90% quantile functions of the maximum DS and DS change of the three vessels were estimated using the BQR model. RESULTS: The 90th percentiles of the DS of the three vessels and their maximum DS change were 41%-50% and 5.6%-7.3%, respectively. Typical anginal symptoms were associated with the highest quantile (90%) of DS in the LAD; diabetes with higher quantiles (75% and 90%) of DS in the LCx; dyslipidemia with the highest quantile (90%) of DS in the RCA; and shortness of breath showed some association with the LCx and RCA. Interestingly, High-density lipoprotein cholesterol showed a dynamic association along DS change in the per-patient analysis. CONCLUSIONS: This study demonstrates the clinical utility of the BQR model for evaluating the comprehensive relationship between risk factors and baseline-grade CAD and its progression.

Relation of Gender to Atherosclerotic Plaque Characteristics by Differing Angiographic Stenosis Severity.

It is unknown whether gender influences the atherosclerotic plaque characteristics (APCs) of lesions of varying angiographic stenosis severity. This study evaluated the imaging data of 303 symptomatic patients from the derivation arm of the CREDENCE (Computed TomogRaphic Evaluation of Atherosclerotic Determinants of Myocardial IsChEmia) trial, all of whom underwent coronary computed tomographic angiography and clinically indicated nonemergent invasive coronary angiography upon study enrollment. Index tests were interpreted by 2 blinded core laboratories, one of which performed quantitative coronary computed tomographic angiography using an artificial intelligence application to characterize and quantify APCs, including percent atheroma volume (PAV), low-density noncalcified plaque (LD-NCP), noncalcified plaque (NCP), calcified plaque (CP), lesion length, positive arterial remodeling, and high-risk plaque (a combination of LD-NCP and positive remodeling ≥1.10); the other classified lesions as obstructive (≥50% diameter stenosis) or nonobstructive (<50% diameter stenosis) based on quantitative invasive coronary angiography. The relation between APCs and angiographic stenosis was further examined by gender. The mean age of the study cohort was 64.4 ± 10.2 years (29.0% female). In patients with obstructive disease, men had more LD-NCP PAV (0.5 ± 0.4 vs 0.3 ± 0.8, p = 0.03) and women had more CP PAV (11.7 ± 1.6 vs 8.0 ± 0.8, p = 0.04). Obstructive lesions had more NCP PAV compared with their nonobstructive lesions in both genders, however, obstructive lesions in women also demonstrated greater LD-NCP PAV (0.4 ± 0.5 vs 1.0 ± 1.8, p = 0.03), and CP PAV (17.4 ± 16.5 vs 25.9 ± 18.7, p = 0.03) than nonobstructive lesions. Comparing the composition of obstructive lesions by gender, women had more CP PAV (26.3 ± 3.4 vs 15.8 ± 1.5, p = 0.005) whereas men had more NCP PAV (33.0 ± 1.6 vs 26.7 ± 2.5, p = 0.04). Men had more LD-NCP PAV in nonobstructive lesions compared with women (1.2 ± 0.2 vs 0.6 ± 0.2, p = 0.02). In conclusion, there are gender-specific differences in plaque composition based on stenosis severity.

Diabetes, Atherosclerosis, and Stenosis by AI.

OBJECTIVE: This study evaluates the relationship between atherosclerotic plaque characteristics (APCs) and angiographic stenosis severity in patients with and without diabetes. Whether APCs differ based on lesion severity and diabetes status is unknown. RESEARCH DESIGN AND METHODS: We retrospectively evaluated 303 subjects from the Computed TomogRaphic Evaluation of Atherosclerotic Determinants of Myocardial IsChEmia (CREDENCE) trial referred for invasive coronary angiography with coronary computed tomographic angiography (CCTA) and classified lesions as obstructive (≥50% stenosed) or nonobstructive using blinded core laboratory analysis of quantitative coronary angiography. CCTA quantified APCs, including plaque volume (PV), calcified plaque (CP), noncalcified plaque (NCP), low-density NCP (LD-NCP), lesion length, positive remodeling (PR), high-risk plaque (HRP), and percentage of atheroma volume (PAV; PV normalized for vessel volume). The relationship between APCs, stenosis severity, and diabetes status was assessed. RESULTS: Among the 303 patients, 95 (31.4%) had diabetes. There were 117 lesions in the cohort with diabetes, 58.1% of which were obstructive. Patients with diabetes had greater plaque burden (P = 0.004). Patients with diabetes and nonobstructive disease had greater PV (P = 0.02), PAV (P = 0.02), NCP (P = 0.03), PAV NCP (P = 0.02), diseased vessels (P = 0.03), and maximum stenosis (P = 0.02) than patients without diabetes with nonobstructive disease. APCs were similar between patients with diabetes with nonobstructive disease and patients without diabetes with obstructive disease. Diabetes status did not affect HRP or PR. Patients with diabetes had similar APCs in obstructive and nonobstructive lesions. CONCLUSIONS: Patients with diabetes and nonobstructive stenosis had an association to similar APCs as patients without diabetes who had obstructive stenosis. Among patients with nonobstructive disease, patients with diabetes had more total PV and NCP.

Association between low-density lipoprotein cholesterol and cardiovascular mortality in statin non-users: a prospective cohort study in 14.9 million Korean adults.

BACKGROUND: Limited information is available on detailed sex/age-specific associations between low-density lipoprotein cholesterol (LDL-C) and cardiovascular disease (CVD) mortality and 'the optimal range' associated with the lowest CVD mortality in the general population. METHODS: Korean adults (N = 14 884 975) who received routine health screenings during 2009-2010 were followed until 2018 for CVD mortality. RESULTS: During 8.8 years (mean) of follow-up, 94 344 individuals died from CVD. LDL-C had U-curve associations with mortality from CVD and its subtypes, except haemorrhagic stroke. Optimal range was 90-149 mg/dL for CVD; 70-114 for ischaemic heart disease; 85-129 for ischaemic stroke; ≥85 for subarachnoid haemorrhage; ≥130 for intracerebral haemorrhage; 115-159 for hypertension and heart failure; and 100-144 for sudden cardiac death. Assuming linear associations between 100 and 300 mg/dL, LDL-C was positively associated with CVD mortality [hazard ratio (HR) per 39-mg/dL (1-mmol/L) higher LDL-C = 1.10], largely due to ischaemic heart disease (HR = 1.26), followed by sudden cardiac death (HR = 1.13), ischaemic stroke (HR = 1.11) and heart failure (HR = 1.05). Intracerebral haemorrhage (HR = 0.90), but not subarachnoid haemorrhage, had inverse associations. Women and older adults had weaker positive associations than men and younger adults (Pinteraction < 0.001 for both sex and age). Individuals aged 75-84 years had modest positive associations with CVD mortality, especially ischaemic heart disease and ischaemic stroke. CONCLUSION: LDL-C had U-curve associations for CVD mortality. The associations and optimal ranges differed across CVD subtypes. Women and older adults had weaker positive associations than men and younger adults. Positive associations with ischaemic heart disease and ischaemic stroke were maintained in adults aged 75-84 years.

High-density lipoprotein cholesterol and cardiovascular mortality: a prospective cohort study among 15.8 million adults.

AIMS: We aimed to investigate whether the associations between high-density lipoprotein cholesterol (HDL-C) and cardiovascular disease (CVD) mortality and the optimal range differ by age and CVD subtypes. METHODS AND RESULTS: Korean adults (n = 15 859 501) with no CVD/cancer who received routine health examinations during 2009-2010 were followed until 2018 for CVD mortality. During a mean 8.8 years of follow-up, 108 123 individuals died from CVD. U-curve associations were found between HDL-C and CVD mortality, regardless of sex, age, and CVD subtype. The optimal range was 50-79 mg/dL (1.29-2.06 mmol/L), while it was 40-69 (1.03-1.80), 50-79 (1.29-2.06), and 60-89 (1.55-2.32) mg/dL (mmol/L) in adults aged <45 years, 45-64 years, and 65-99 years, respectively. Assuming linear associations <60 mg/dL, the multivariable-adjusted hazard ratios (HRs) per 39 mg/dL (1 mmol/L) higher level were 0.58 (95% confidence interval = 0.56-0.60), and they were 0.61 (0.52-0.72), 0.58 (0.54-0.62), and 0.59 (0.56-0.61) in individuals aged 18-44, 45-64, and 65-99 years, respectively [Pinteraction (age) = 0.845]. Assuming linear associations in the 60-150 mg/dL range, HDL-C was positively associated with CVD mortality (HR = 1.09, 1.04-1.14). The strongest association was for sudden cardiac death (SCD) (HR = 1.37), followed by heart failure (HF) (HR = 1.20) and intracerebral haemorrhage (ICH) (HR = 1.13). The HRs were 1.47 (1.23-1.76), 1.17 (1.08-1.28), and 1.03 (0.97-1.08) in individuals aged 18-44, 45-64, and 65-99 years, respectively [Pinteraction (age) < 0.001]. CONCLUSION: Both low and high levels of HDL-C were associated with increased mortality from CVD in the general population, especially SCD, HF, and ICH. High HDL-C levels are not necessarily a sign of good cardiovascular health, especially in younger adults.

Fully automated quantification of cardiac chamber and function assessment in 2-D echocardiography: clinical feasibility of deep learning-based algorithms.

We aimed to compare the segmentation performance of the current prominent deep learning (DL) algorithms with ground-truth segmentations and to validate the reproducibility of the manually created 2D echocardiographic four cardiac chamber ground-truth annotation. Recently emerged DL based fully-automated chamber segmentation and function assessment methods have shown great potential for future application in aiding image acquisition, quantification, and suggestion for diagnosis. However, the performance of current DL algorithms have not previously been compared with each other. In addition, the reproducibility of ground-truth annotations which are the basis of these algorithms have not yet been fully validated. We retrospectively enrolled 500 consecutive patients who underwent transthoracic echocardiogram (TTE) from December 2019 to December 2020. Simple U-net, Res-U-net, and Dense-U-net algorithms were compared for the segmentation performances and clinical indices such as left atrial volume (LAV), left ventricular end diastolic volume (LVEDV), left ventricular end systolic volume (LVESV), LV mass, and ejection fraction (EF) were evaluated. The inter- and intra-observer variability analysis was performed by two expert sonographers for a randomly selected echocardiographic view in 100 patients (apical 2-chamber, apical 4-chamber, and parasternal short axis views). The overall performance of all DL methods was excellent [average dice similarity coefficient (DSC) 0.91 to 0.95 and average Intersection over union (IOU) 0.83 to 0.90], with the exception of LV wall area on PSAX view (average DSC of 0.83, IOU 0.72). In addition, there were no significant difference in clinical indices between ground truth and automated DL measurements. For inter- and intra-observer variability analysis, the overall intra observer reproducibility was excellent: LAV (ICC = 0.995), LVEDV (ICC = 0.996), LVESV (ICC = 0.997), LV mass (ICC = 0.991) and EF (ICC = 0.984). The inter-observer reproducibility was slightly lower as compared to intraobserver agreement: LAV (ICC = 0.976), LVEDV (ICC = 0.982), LVESV (ICC = 0.970), LV mass (ICC = 0.971), and EF (ICC = 0.899). The three current prominent DL-based fully automated methods are able to reliably perform four-chamber segmentation and quantification of clinical indices. Furthermore, we were able to validate the four cardiac chamber ground-truth annotation and demonstrate an overall excellent reproducibility, but still with some degree of inter-observer variability.