-
1.
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, SJ, Maliakal, G, Singh, G, van Rosendael, AR, Ma, X, Xu, Z, Alawamlh, OAH, Lee, B, Pandey, M, Achenbach, S, et al
European heart journal. 2020;(3):359-367
-
-
Free full text
-
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 < 0.05 for all comparisons. CACS, age, and gender were the highest ranking features. CONCLUSION A 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.
-
2.
Standardized reporting systems for computed tomography coronary angiography and calcium scoring: A real-world validation of CAD-RADS and CAC-DRS in patients with stable chest pain.
Williams, MC, Moss, A, Dweck, M, Hunter, A, Pawade, T, Adamson, PD, Shah, ASV, Alam, S, Maroules, CD, van Beek, EJ, et al
Journal of cardiovascular computed tomography. 2020;(1):3-11
Abstract
OBJECTIVES To assess the prognostic implications of standardized reporting systems for coronary computed tomography angiography (CCTA) and coronary artery calcium scores (CACS) in patients with stable chest pain. BACKGROUND The Coronary Artery Disease Reporting And Data System (CAD-RADS) and Coronary Artery Calcium - Data and Reporting System (CAC-DRS) aim to improve communication of CACS and CCTA results, but its influence on prognostication is unknown. METHODS Images from 1769 patients who underwent CCTA as part of the Scottish Computed Tomography of the HEART (SCOT-HEART) multi-center randomized controlled trial were assessed. CACS were classified as CAC-DRS 0 to 3 based on Agatston scores. CCTA were classified as CAD-RADS 0 to 5 based on the most clinically relevant finding per patient. The primary outcome was the five-year events of fatal and non-fatal myocardial infarction. RESULTS Patients had a mean age of 58 ± 10 years and 56% were male. CAC-DRS 0, 1, 2 and 3 occurred in 642 (36%), 510 (29%), 239 (14%) and 379 (21%) patients respectively. CAD-RADS 0, 1, 2, 3, 4A, 4B and 5 occurred in 622 (35%), 327 (18%), 211 (12%), 165 (9%), 221 (12%), 42 (2%) and 181 (10%) patients respectively. Patients classified as CAC-DRS 3 were at an increased risk of fatal or non-fatal myocardial infarction compared to CAC-DRS 0 patients (hazard ratio (HR) 9.41; 95% confidence interval (CI) 3.24, 27.31; p < 0.001). Patients with higher CAD-RADS categories were at an increased risk of fatal or non-fatal myocardial infarction, with patients classified as CAD-RADS 4B at the highest risk compared to CAD-RADS 0 patients (HR 19.14; 95% CI 4.28, 85.53; p < 0.001). CONCLUSION Patients with higher CAC-DRS and CAD-RADS scores were at increased risk of subsequent fatal and non-fatal myocardial infarction. This confirms that the classification provides additional prognostic discrimination for future coronary heart disease events.
-
3.
The Predictive Value of Coronary Artery Calcium Scoring for Major Adverse Cardiac Events According to Renal Function (from the Coronary Computed Tomography Angiography Evaluation for Clinical Outcomes: An International Multicenter [CONFIRM] Registry).
Lee, JH, Rizvi, A, Hartaigh, BÓ, Han, D, Park, MW, Roudsari, HM, Stuijfzand, WJ, Gransar, H, Lu, Y, Callister, TQ, et al
The American journal of cardiology. 2019;(9):1435-1442
Abstract
The prognostic performance of coronary artery calcium score (CACS) for predicting adverse outcomes in patients with decreased renal function remains unclear. We aimed to examine whether CACS improves risk stratification by demonstrating incremental value beyond a traditional risk score according to renal function status. 9,563 individuals without known coronary artery disease were enrolled. Estimated glomerular filtration rate (eGFR, ml/min/1.73 m2) was ascertained using the modified Modification of Diet in Renal Disease formula, and was categorized as: ≥90, 60 to 89, and <60. CACS was categorized as 0, 1 to 100, 101 to 400, and >400. Multivariable Cox regression was used to estimate hazard ratios (HR) with 95% confidence intervals (95% CI) for major adverse cardiac events (MACE), comprising all-cause mortality, myocardial infarction, and late revascularization (>90 days). Mean age was 55.8 ± 11.5 years (52.8% male). In total, 261 (2.7%) patients experienced MACE over a median follow-up of 24.5 months (interquartile range: 16.9 to 41.1). Incident MACE increased with higher CACS across each eGFR category, with the highest rate observed among patients with CACS >400 and eGFR <60 (95.1 per 1,000 person-years). A CACS >400 increased MACE risk with HR 4.46 (95% CI 1.68 to 11.85), 6.63 (95% CI 4.03 to 10.92), and 6.14 (95% CI 2.85 to 13.21) for eGFR ≥90, 60 to 89, and <60, respectively, as compared with CACS 0. Further, CACS improved discrimination and reclassification beyond Framingham 10-year risk score (FRS) (AUC: 0.70 vs 0.64; category free-NRI: 0.51, all p <0.001) for predicting MACE in patients with impaired renal function (eGFR < 90). In conclusion, CACS improved risk stratification and provided incremental value beyond FRS for predicting MACE, irrespective of eGFR status.
-
4.
Impact of iodine concentration and iodine delivery rate on contrast enhancement in coronary CT angiography: a randomized multicenter trial (CT-CON).
Rengo, M, Dharampal, A, Lubbers, M, Kock, M, Wildberger, JE, Das, M, Niezen, A, van Tilborg, F, Kofflard, M, Laghi, A, et al
European radiology. 2019;(11):6109-6118
Abstract
OBJECTIVE To compare the effect of contrast medium iodine concentration on contrast enhancement, heart rate, and injection pressure when injected at a constant iodine delivery rate in coronary CT angiography (CTA). METHODS One thousand twenty-four patients scheduled for coronary CTA were prospectively randomized to receive one of four contrast media: iopromide 300 mg I/ml, iohexol 350 mg I/ml, iopromide 370 mg I/ml, or iomeprol 400 mg I/ml. Contrast media were delivered at an equivalent iodine delivery rate of 2.0 g I/s. Intracoronary attenuation was measured and compared (per vessel and per segment). Heart rate before and after contrast media injection was documented. Injection pressure was recorded (n = 403) during contrast medium injection and compared between groups. RESULTS Intracoronary attenuation values were similar for the different contrast groups. The mean attenuation over all segments ranged between 384 HU for 350 mg I/ml and 395 HU for 400 mg I/ml (p = 0.079). Dose-length product (p = 0.8424), signal-to-noise ratio (all p > 0.05), time to peak (p = 0.324), and changes in heart rate (p = 0.974) were comparable between groups. The peak pressures differed: 197.4 psi for 300 mg I/ml (viscosity 4.6 mPa s), 229.8 psi for 350 mg I/ml (10.4 mPa s), 216.1 psi for 370 mg I/ml (9.5 mPa s), and 243.7 psi for 400 mg I/ml (12.6 mPa s) (p < 0.0001). CONCLUSION Intravascular attenuation and changes in heart rate are independent of iodine concentration when contrast media are injected at the same iodine delivery rate. Differences in injection pressures are associated with the viscosity of the contrast media. KEY POINTS • The contrast enhancement in coronary CT angiography is independent of the iodine concentration when contrast media are injected at body temperature (37 °C) with the same iodine delivery rate. • Iodine concentration does not influence the change in heart rate when contrast media are injected at identical iodine delivery rates. • For a fixed iodine delivery rate and contrast temperature, the viscosity of the contrast medium affects the injection pressure.
-
5.
Risk Reclassification With Coronary Computed Tomography Angiography-Visualized Nonobstructive Coronary Artery Disease According to 2018 American College of Cardiology/American Heart Association Cholesterol Guidelines (from the Coronary Computed Tomography Angiography Evaluation for Clinical Outcomes : An International Multicenter Registry [CONFIRM]).
Han, D, Beecy, A, Anchouche, K, Gransar, H, Dunham, PC, Lee, JH, Achenbach, S, Al-Mallah, MH, Andreini, D, Berman, DS, et al
The American journal of cardiology. 2019;(9):1397-1405
Abstract
The 2018 American College of Cardiology (ACC)/American Heart Association (AHA) cholesterol management guideline recommends risk enhancers in the borderline-risk and statin recommended/intermediate-risk groups. We determined the risk reclassification by the presence and severity of coronary computed tomography angiography (CCTA)-visualized coronary artery disease (CAD) according to statin eligibility groups. Of 35,281 individuals who underwent CCTA, 1,303 asymptomatic patients (age 59, 65% male) were identified. Patients were categorized as low risk, borderline risk, statin recommended/intermediate risk or statin recommended/high risk according to the guideline. CCTA-visualized CAD was categorized as no CAD, nonobstructive, or obstructive. Major adverse cardiovascular events (MACE) were defined as a composite outcome of all-cause mortality, nonfatal myocardial infarction, and late coronary revascularization (>90 days). We tested a reclassification wherein no CAD reclassifies downward, and the presence of any CAD reclassifies upward. During a median follow-up of 2.9 years, 93 MACE events (7.1%) were observed. Among the borderline-risk and statin-recommended/intermediate-risk groups eligible for risk enhancers, the presence or absence of any CCTA-visualized CAD led to a net increase of 2.3% of cases and 22.4% of controls correctly classified (net reclassification index [NRI] 0.27, 95% CI 0.13 to 0.41, p = 0.0002). The NRI was not significant among low- or statin-recommended/high-risk patients (all p >0.05). The presence or absence of CCTA-visualized CAD, including both obstructive and nonobstructive CAD, significantly improves reclassification in patients eligible for risk enhancers in 2018 ACC/AHA guidelines. Patients in low- and high-risk groups derive no significant improvement in risk reclassification from CCTA.
-
6.
Coronary artery calcium scoring in low risk patients with family history of coronary heart disease: Validation of the SCCT guideline approach in the coronary artery calcium consortium.
Dudum, R, Dzaye, O, Mirbolouk, M, Dardari, ZA, Orimoloye, OA, Budoff, MJ, Berman, DS, Rozanski, A, Miedema, MD, Nasir, K, et al
Journal of cardiovascular computed tomography. 2019;(3):21-25
-
-
Free full text
-
Abstract
BACKGROUND The Society of Cardiovascular Computed Tomography (SCCT) recommends consideration of coronary artery calcium (CAC) scoring among individuals with a family history (FH) of coronary heart disease (CHD) and atherosclerotic cardiovascular disease (ASCVD) risk <5%. No dedicated study has examined the prognostic significance of CAC scoring among this population. METHODS The CAC Consortium is a multi-center observational cohort study from four clinical centers linked to long-term follow-up for cause-specific mortality. All CAC scans were physician referred and performed in patients without a history of CHD. Our analysis includes 14,169 patients with ASCVD scores <5% and self-reported FH of CHD. RESULTS This cohort had a mean age of 48.1 (SD 7.4), was 91.3% white, 47.4% female, had an average ASCVD score of 2.3% (SD 1.3), and 59.4% had a CAC = 0. The event rate for all-cause mortality was 1.2 per 1000 person-years, 0.3 per 1000 person-years for CVD-specific mortality, and 0.2 per 1000 person-years for CHD-specific mortality. In multivariable Cox proportional hazard models, those with CAC>100 had a 2.2 (95% CI 1.5-3.3) higher risk of all-cause mortality, 4.3 (95% CI 1.9-9.5) times higher risk of CVD-specific mortality, and a 10.4 (95% CI 3.2-33.7) times higher risk of CHD-specific mortality compared to individuals with CAC = 0. The NNS to detect CAC >100 in this sample was 9. CONCLUSION In otherwise low risk patients with FH of CHD, CAC>100 were associated with increased risk of all-cause and CHD mortality with event rates in a range that may benefit with preventive pharmacotherapy. These data strongly support new SCCT recommendations regarding testing of patients with a family history of CHD.
-
7.
High-Sensitivity Troponin I and Coronary Computed Tomography in Symptomatic Outpatients With Suspected CAD: Insights From the PROMISE Trial.
Januzzi, JL, Suchindran, S, Coles, A, Ferencik, M, Patel, MR, Hoffmann, U, Ginsburg, GS, Douglas, PS, ,
JACC. Cardiovascular imaging. 2019;(6):1047-1055
Abstract
OBJECTIVES The goal of this study was to examine associations between concentrations of high-sensitivity troponin I (hsTnI) (measured by using a single-molecule counting method) and obstructive coronary artery disease (CAD) in 1,844 stable, symptomatic outpatients with suspected CAD randomized to undergo coronary computed tomography angiography (CTA) in the PROMISE (Prospective Multicenter Imaging Study for Evaluation of Chest Pain) trial. BACKGROUND Elevated concentrations of hsTnI are associated with CAD in patients with myocardial infarction. The meaning of hsTnI concentrations in stable symptomatic outpatients is not well understood. METHODS Clinical characteristics and CTA results (including coronary artery calcium [CAC] scores) were expressed across hsTnI quartiles. Determinants of hsTnI concentration were identified. Multivariable logistic regression identified independent predictors of obstructive CAD50 (≥50% stenosis in any vessel) and CAD70 (≥70% stenosis or ≥50% left main). RESULTS The median hsTnI concentration was 1.5 ng/l; nearly all (98.5%) subjects had measurable hsTnI, and 6.1% had concentrations ≥99th percentile concentration for this assay (6 ng/l). Higher CAC scores, as well as more prevalent and diffuse CAD, was seen in upper hsTnI quartiles (all p < 0.001). Independent predictors of hsTnI concentrations included age, sex, and CAC score (all p < 0.05). After adjusting for demographic and clinical characteristics, log-transformed hsTnI concentrations were associated with obstructive CAD50 (odds ratio: 1.15 per interquartile range; p = 0.02) and CAD70 (odds ratio: 1.25 per interquartile range; p = 0.001). CONCLUSIONS In stable symptomatic outpatients undergoing nonemergent coronary CTA for the diagnosis of suspected CAD, higher concentrations of hsTnI were associated with increasing presence and severity of coronary atherosclerosis. (Prospective Multicenter Imaging Study for Evaluation of Chest Pain [PROMISE]; NCT01174550).
-
8.
Quantitative coronary plaque analysis predicts high-risk plaque morphology on coronary computed tomography angiography: results from the ROMICAT II trial.
Liu, T, Maurovich-Horvat, P, Mayrhofer, T, Puchner, SB, Lu, MT, Ghemigian, K, Kitslaar, PH, Broersen, A, Pursnani, A, Hoffmann, U, et al
The international journal of cardiovascular imaging. 2018;(2):311-319
Abstract
Semi-automated software can provide quantitative assessment of atherosclerotic plaques on coronary CT angiography (CTA). The relationship between established qualitative high-risk plaque features and quantitative plaque measurements has not been studied. We analyzed the association between quantitative plaque measurements and qualitative high-risk plaque features on coronary CTA. We included 260 patients with plaque who underwent coronary CTA in the Rule Out Myocardial Infarction/Ischemia Using Computer Assisted Tomography (ROMICAT) II trial. Quantitative plaque assessment and qualitative plaque characterization were performed on a per coronary segment basis. Quantitative coronary plaque measurements included plaque volume, plaque burden, remodeling index, and diameter stenosis. In qualitative analysis, high-risk plaque was present if positive remodeling, low CT attenuation plaque, napkin-ring sign or spotty calcium were detected. Univariable and multivariable logistic regression analyses were performed to assess the association between quantitative and qualitative high-risk plaque assessment. Among 888 segments with coronary plaque, high-risk plaque was present in 391 (44.0%) segments by qualitative analysis. In quantitative analysis, segments with high-risk plaque had higher total plaque volume, low CT attenuation plaque volume, plaque burden and remodeling index. Quantitatively assessed low CT attenuation plaque volume (odds ratio 1.12 per 1 mm3, 95% CI 1.04-1.21), positive remodeling (odds ratio 1.25 per 0.1, 95% CI 1.10-1.41) and plaque burden (odds ratio 1.53 per 0.1, 95% CI 1.08-2.16) were associated with high-risk plaque. Quantitative coronary plaque characteristics (low CT attenuation plaque volume, positive remodeling and plaque burden) measured by semi-automated software correlated with qualitative assessment of high-risk plaque features.
-
9.
Efficacy of alprostadil in preventing contrast-induced nephropathy in patients undergoing percutaneous coronary intervention: A multicenter prospective randomized controlled trial.
Liang, M, Yang, S, Fu, N, Lu, C, Tian, F, Xing, X, Lin, W, Liu, J
Catheterization and cardiovascular interventions : official journal of the Society for Cardiac Angiography & Interventions. 2018;(4):742-750
Abstract
BACKGROUND The role of alprostadil on the prevention of contrast-induced nephropathy (CIN) still remains controversial. The purpose of this study was to examine the effects of short-term alprostadil on the incidence of CIN in patients undergoing elective percutaneous coronary intervention (PCI). METHODS A total of 480 patients with coronary heart disease undergoing PCI were enrolled in our study and randomly assigned to two groups. The control group (n = 240) was given only hydration therapy and the alprostadil group (n = 240) received intravenous administration of 20 ug/day (diluted with 100 ml normal saline) from 0.5∼1 hr before to 3 days after operation on the basis of hydration. The primary endpoint of the study was the incidence of CIN, which was defined as an increase in SCr concentration ≥ 44.2 umol/l or ≥25% above baseline within 48 hr∼72 hr after exposure of contrast media. RESULTS The incidence of CIN was significantly lower in the alprostadil group than that in the control group (6.25% vs 11.67%, P = 0.038). Multivariate logistic regression analysis showed that alprostadil was the protective factor of CIN (OR = 0.699, 95% CI 0.542-0.902, P = 0.006). The benefits against CIN were consistent in prespecified high-risk patients with diabetes mellitus (P = 0.003). In addition, we also found that hs-CRP and blood homocysteine values after PCI were significantly lower in the alprostadil group than those in the control group. CONCLUSION Prophylactic administration of alprostadil may prevent against CIN in coronary heart disease patients undergoing elective PCI, particularly in high-risk patients with diabetes mellitus.
-
10.
Association between diet quality and measures of body adiposity using the Rate Your Plate survey in patients presenting for coronary angiography.
Ganguzza, L, Ngai, C, Flink, L, Woolf, K, Guo, Y, Gianos, E, Burdowski, J, Slater, J, Acosta, V, Shephard, T, et al
Clinical cardiology. 2018;(1):126-130
Abstract
BACKGROUND Diet is a modifiable risk factor for cardiovascular disease; however, dietary patterns are historically difficult to capture in the clinical setting. Healthcare providers need assessment tools that can quickly summarize dietary patterns. Research should evaluate the effectiveness of these tools, such as Rate Your Plate (RYP), in the clinical setting. HYPOTHESIS RYP diet quality scores are associated with measures of body adiposity in patients referred for coronary angiography. METHODS Patients without a history of coronary revascularization (n = 400) were prospectively approached at a tertiary medical center in New York City prior to coronary angiography. Height, weight, and waist circumference (WC) were measured; body mass index (BMI) and waist-to-height ratio (WHtR) were calculated. Participants completed a 24-question RYP diet survey. An overall score was computed, and participants were divided into high (≥58) and low (≤57) diet quality groups. RESULTS Participants in the high diet quality group (n = 98) had significantly lower measures of body adiposity than did those in the low diet quality group (n = 302): BMI (P < 0.001), WC (P = 0.001), WHtR (P = 0.001). There were small but significant inverse correlations between diet score and BMI, WC, and WHtR (P < 0.001). These associations remained significant after adjustment for demographics, tobacco use, and socioeconomic factors. CONCLUSIONS Higher diet quality scores are associated with lower measures of body adiposity. RYP is a potential instrument to capture diet quality in a high-volume clinical setting. Further research should evaluate the utility of RYP in cardiovascular risk-factor control.