This study evaluated the added predictive value of combining clinical information and myocardial perfusion single-photon emission computed tomography (SPECT) imaging (MPI) data using machine learning ...(ML) to predict major adverse cardiac events (MACE).
Traditionally, prognostication by MPI has relied on visual or quantitative analysis of images without objective consideration of the clinical data. ML permits a large number of variables to be considered in combination and at a level of complexity beyond the human clinical reader.
A total of 2,619 consecutive patients (48% men; 62 ± 13 years of age) who underwent exercise (38%) or pharmacological stress (62%) with high-speed SPECT MPI were monitored for MACE. Twenty-eight clinical variables, 17 stress test variables, and 25 imaging variables (including total perfusion deficit TPD) were recorded. Areas under the receiver-operating characteristic curve (AUC) for MACE prediction were compared among: 1) ML with all available data (ML-combined); 2) ML with only imaging data (ML-imaging); 3) 5-point scale visual diagnosis (physician MD diagnosis); and 4) automated quantitative imaging analysis (stress TPD and ischemic TPD). ML involved automated variable selection by information gain ranking, model building with a boosted ensemble algorithm, and 10-fold stratified cross validation.
During follow-up (3.2 ± 0.6 years), 239 patients (9.1%) had MACE. MACE prediction was significantly higher for ML-combined than ML-imaging (AUC: 0.81 vs. 0.78; p < 0.01). ML-combined also had higher predictive accuracy compared with MD diagnosis, automated stress TPD, and automated ischemic TPD (AUC: 0.81 vs. 0.65 vs. 0.73 vs. 0.71, respectively; p < 0.01 for all). Risk reclassification for ML-combined compared with visual MD diagnosis was 26% (p < 0.001).
ML combined with both clinical and imaging data variables was found to have high predictive accuracy for 3-year risk of MACE and was superior to existing visual or automated perfusion assessments. ML could allow integration of clinical and imaging data for personalized MACE risk computations in patients undergoing SPECT MPI.
Display omitted
The association of atherosclerotic features with first acute coronary syndromes (ACS) has not accounted for plaque burden.
The purpose of this study was to identify atherosclerotic features ...associated with precursors of ACS.
We performed a nested case-control study within a cohort of 25,251 patients undergoing coronary computed tomographic angiography (CTA) with follow-up over 3.4 ± 2.1 years. Patients with ACS and nonevent patients with no prior coronary artery disease (CAD) were propensity matched 1:1 for risk factors and coronary CTA–evaluated obstructive (≥50%) CAD. Separate core laboratories performed blinded adjudication of ACS and culprit lesions and quantification of baseline coronary CTA for percent diameter stenosis (%DS), percent cross-sectional plaque burden (PB), plaque volumes (PVs) by composition (calcified, fibrous, fibrofatty, and necrotic core), and presence of high-risk plaques (HRPs).
We identified 234 ACS and control pairs (age 62 years, 63% male). More than 65% of patients with ACS had nonobstructive CAD at baseline, and 52% had HRP. The %DS, cross-sectional PB, fibrofatty and necrotic core volume, and HRP increased the adjusted hazard ratio (HR) of ACS (1.010 per %DS, 95% confidence interval CI: 1.005 to 1.015; 1.008 per percent cross-sectional PB, 95% CI: 1.003 to 1.013; 1.002 per mm3 fibrofatty plaque, 95% CI: 1.000 to 1.003; 1.593 per mm3 necrotic core, 95% CI: 1.219 to 2.082; all p < 0.05). Of the 129 culprit lesion precursors identified by coronary CTA, three-fourths exhibited <50% stenosis and 31.0% exhibited HRP.
Although ACS increases with %DS, most precursors of ACS cases and culprit lesions are nonobstructive. Plaque evaluation, including HRP, PB, and plaque composition, identifies high-risk patients above and beyond stenosis severity and aggregate plaque burden.
Display omitted
Objectives This study examined the performance of percent aggregate plaque volume (%APV), which represents cumulative plaque volume as a function of total vessel volume, by coronary computed ...tomography angiography (CTA) for identification of ischemic lesions of intermediate stenosis severity. Background Coronary lesions of intermediate stenosis demonstrate significant rates of ischemia. Coronary CTA enables quantification of luminal narrowing and %APV. Methods We identified 58 patients with intermediate lesions (30% to 69% diameter stenosis) who underwent invasive angiography and fractional flow reserve. Coronary CTA measures included diameter stenosis, area stenosis, minimal lumen diameter (MLD), minimal lumen area (MLA) and %APV. %APV was defined as the sum of plaque volume divided by the sum of vessel volume from the ostium to the distal portion of the lesion. Fractional flow reserve ≤0.80 was considered diagnostic of lesion-specific ischemia. Area under the receiver operating characteristic curve and net reclassification improvement (NRI) were also evaluated. Results Twenty-two of 58 lesions (38%) caused ischemia. Compared with nonischemic lesions, ischemic lesions had smaller MLD (1.3 vs. 1.7 mm, p = 0.01), smaller MLA (2.5 vs. 3.8 mm2 , p = 0.01), and greater %APV (48.9% vs. 39.3%, p < 0.0001). Area under the receiver operating characteristic curve was highest for %APV (0.85) compared with diameter stenosis (0.68), area stenosis (0.66), MLD (0.75), or MLA (0.78). Addition of %APV to other measures showed significant reclassification over diameter stenosis (NRI 0.77, p < 0.001), area stenosis (NRI 0.63, p = 0.002), MLD (NRI 0.62, p = 0.001), and MLA (NRI 0.43, p = 0.01). Conclusions Compared with diameter stenosis, area stenosis, MLD, and MLA, %APV by coronary CTA improves identification, discrimination, and reclassification of ischemic lesions of intermediate stenosis severity.
Abstract
Aims
Our aim was to evaluate the performance of machine learning (ML), integrating clinical parameters with coronary artery calcium (CAC), and automated epicardial adipose tissue (EAT) ...quantification, for the prediction of long-term risk of myocardial infarction (MI) and cardiac death in asymptomatic subjects.
Methods and results
Our study included 1912 asymptomatic subjects 1117 (58.4%) male, age: 55.8 ± 9.1 years from the prospective EISNER trial with long-term follow-up after CAC scoring. EAT volume and density were quantified using a fully automated deep learning method. ML extreme gradient boosting was trained using clinical co-variates, plasma lipid panel measurements, risk factors, CAC, aortic calcium, and automated EAT measures, and validated using repeated 10-fold cross validation. During mean follow-up of 14.5 ± 2 years, 76 events of MI and/or cardiac death occurred. ML obtained a significantly higher AUC than atherosclerotic cardiovascular disease (ASCVD) risk and CAC score for predicting events (ML: 0.82; ASCVD: 0.77; CAC: 0.77, P < 0.05 for all). Subjects with a higher ML score (by Youden’s index) had high hazard of suffering events (HR: 10.38, P < 0.001); the relationships persisted in multivariable analysis including ASCVD-risk and CAC measures (HR: 2.94, P = 0.005). Age, ASCVD-risk, and CAC were prognostically important for both genders. Systolic blood pressure was more important than cholesterol in women, and the opposite in men.
Conclusions
In this prospective study, machine learning used to integrate clinical and quantitative imaging-based variables significantly improves prediction of MI and cardiac death compared with standard clinical risk assessment. Following further validation, such a personalized paradigm could potentially be used to improve cardiovascular risk assessment.
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.
Atherosclerotic plaque quantification from coronary CT angiography (CCTA) enables accurate assessment of coronary artery disease burden and prognosis. We sought to develop and validate a deep ...learning system for CCTA-derived measures of plaque volume and stenosis severity.
This international, multicentre study included nine cohorts of patients undergoing CCTA at 11 sites, who were assigned into training and test sets. Data were retrospectively collected on patients with a wide range of clinical presentations of coronary artery disease who underwent CCTA between Nov 18, 2010, and Jan 25, 2019. A novel deep learning convolutional neural network was trained to segment coronary plaque in 921 patients (5045 lesions). The deep learning network was then applied to an independent test set, which included an external validation cohort of 175 patients (1081 lesions) and 50 patients (84 lesions) assessed by intravascular ultrasound within 1 month of CCTA. We evaluated the prognostic value of deep learning-based plaque measurements for fatal or non-fatal myocardial infarction (our primary outcome) in 1611 patients from the prospective SCOT-HEART trial, assessed as dichotomous variables using multivariable Cox regression analysis, with adjustment for the ASSIGN clinical risk score.
In the overall test set, there was excellent or good agreement, respectively, between deep learning and expert reader measurements of total plaque volume (intraclass correlation coefficient ICC 0·964) and percent diameter stenosis (ICC 0·879; both p<0·0001). When compared with intravascular ultrasound, there was excellent agreement for deep learning total plaque volume (ICC 0·949) and minimal luminal area (ICC 0·904). The mean per-patient deep learning plaque analysis time was 5·65 s (SD 1·87) versus 25·66 min (6·79) taken by experts. Over a median follow-up of 4·7 years (IQR 4·0–5·7), myocardial infarction occurred in 41 (2·5%) of 1611 patients from the SCOT-HEART trial. A deep learning-based total plaque volume of 238·5 mm3 or higher was associated with an increased risk of myocardial infarction (hazard ratio HR 5·36, 95% CI 1·70–16·86; p=0·0042) after adjustment for the presence of deep learning-based obstructive stenosis (HR 2·49, 1·07–5·50; p=0·0089) and the ASSIGN clinical risk score (HR 1·01, 0·99–1·04; p=0·35).
Our novel, externally validated deep learning system provides rapid measurements of plaque volume and stenosis severity from CCTA that agree closely with expert readers and intravascular ultrasound, and could have prognostic value for future myocardial infarction.
National Heart, Lung, and Blood Institute and the Miriam & Sheldon G Adelson Medical Research Foundation.
Increased attenuation of pericoronary adipose tissue (PCAT) around the proximal right coronary artery (RCA) from coronary computed tomography angiography (CTA) has been shown to be associated with ...coronary inflammation and improved prediction of cardiac death over plaque features. Our aim was to investigate whether PCAT CT attenuation is related to progression of coronary plaque burden.
We analysed CTA studies of 111 stable patients (age 59.2 ± 9.8 years, 77% male) who underwent sequential CTA (3.4 ± 1.6 years between scans) with identical acquisition protocols. Total plaque (TP), calcified plaque (CP), non-calcified plaque (NCP), and low-density non-calcified plaque (LD-NCP) volumes and corresponding burden (plaque volume × 100%/vessel volume) were quantified using semi-automated software. PCAT CT attenuation (HU) was measured around the proximal RCA, the most standardized method for PCAT analysis. Patients with an increase in NCP burden (n = 51) showed an increase in PCAT attenuation, whereas patients with a decrease in NCP burden (n = 60) showed a decrease {4.4 95% confidence interval (CI) 2.6-6.2 vs. -2.78 (95% CI -4.6 to -1.0) HU, P < 0.0001}. Changes in PCAT attenuation correlated with changes in the burden of NCP (r = 0.55, P < 0.001) and LD-NCP (r = 0.24, P = 0.01); but not CP burden (P = 0.3). Increased baseline PCAT attenuation ≥-75 HU was independently associated with increase in NCP (odds ratio 3.07, 95% CI 1.4-7.0; P < 0.008) and TP burden on follow-up CTA.
PCAT attenuation measured from routine CTA is related to the progression of NCP and TP burden. This imaging biomarker may help to identify patients at increased risk of high-risk plaque progression and allow monitoring of beneficial changes from medical therapy.
BACKGROUNDThe utility of performing early myocardial revascularization among patients presenting with inducible myocardial ischemia and low left ventricular ejection fraction (LVEF) is currently ...unknown. OBJECTIVESIn this study, we sought to assess the relationship between stress-induced myocardial ischemia, revascularization, and all-cause mortality (ACM) among patients with normal vs low LVEF. METHODSWe evaluated 43,443 patients undergoing stress-rest single-photon emission computed tomography myocardial perfusion imaging from 1998 to 2017. Median follow-up was 11.4 years. Myocardial ischemia was assessed for its interaction between early revascularization and mortality. A propensity score was used to adjust for nonrandomization to revascularization, followed by multivariable Cox modeling adjusted for the propensity score and clinical variables to predict ACM. RESULTSThe frequency of myocardial ischemia varied markedly according to LVEF and angina, ranging from 6.7% among patients with LVEF ≥55% and no typical angina to 64.0% among patients with LVEF <45% and typical angina (P < 0.001). Among 39,883 patients with LVEF ≥45%, early revascularization was associated with increased mortality risk among patients without ischemia and lower mortality risk among patients with severe (≥15%) ischemia (HR: 0.70; 95% CI: 0.52-0.95). Among 3,560 patients with LVEF <45%, revascularization was not associated with mortality benefit among patients with no or mild ischemia, and was associated with decreased mortality among patients with moderate (10%-14%) (HR: 0.67; 95% CI: 0.49-0.91) and severe (≥15%) (HR: 0.55; 95% CI: 0.38-0.80) ischemia. CONCLUSIONSWithin this cohort, early myocardial revascularization was associated with a significant reduction in mortality among both patients with normal LVEF and severe inducible myocardial ischemia and patients with low LVEF and moderate or severe inducible myocardial ischemia.
The aim of this study was to evaluate whether machine learning (ML) of noncontrast computed tomographic (CT) and clinical variables improves the prediction of atherosclerotic cardiovascular disease ...(ASCVD) and coronary heart disease (CHD) deaths compared with coronary artery calcium (CAC) Agatston scoring and clinical data.
The CAC score provides a measure of the global burden of coronary atherosclerosis, and its long-term prognostic utility has been consistently shown to have incremental value over clinical risk assessment. However, current approaches fail to integrate all available CT and clinical variables for comprehensive risk assessment.
The study included data from 66,636 asymptomatic subjects (mean age 54 ± 11 years, 67% men) without established ASCVD undergoing CAC scanning and followed for cardiovascular disease (CVD) and CHD deaths at 10 years. Clinical risk assessment incorporated the ASCVD risk score. For ML, an ensemble boosting approach was used to fit a predictive classifier for outcomes, followed by automated feature selection using information gain ratio. The model-building process incorporated all available clinical and CT data, including the CAC score; the number, volume, and density of CAC plaques; and extracoronary scores; comprising a total of 77 variables. The overall proposed model (ML all) was evaluated using a 10-fold cross-validation framework on the population data and area under the curve (AUC) as metrics. The prediction performance was also compared with 2 traditional scores (ASCVD risk and CAC score) and 2 additional models that were trained using all the clinical data (ML clinical) and CT variables (ML CT).
The AUC by ML all (0.845) for predicting CVD death was superior compared with those obtained by ASCVD risk alone (0.821), CAC score alone (0.781), and ML CT alone (0.804) (p < 0.001 for all). Similarly, for predicting CHD death, AUC by ML all (0.860) was superior to the other analyses (0.835 for ASCVD risk, 0.816 for CAC, and 0.827 for ML CT; p < 0.001).
The comprehensive ML model was superior to ASCVD risk, CAC score, and an ML model fitted using CT variables alone in the prediction of both CVD and CHD death.
Display omitted
The increased risk associated with pharmacologic versus exercise testing is obscured by the higher prevalence of clinical risk factors among pharmacologic patients. Thus, we assessed comparative ...mortality in a large risk factor-matched group of exercise versus pharmacologic patients undergoing stress/rest SPECT myocardial perfusion imaging (MPI).
39,179 patients undergoing stress/rest SPECT-MPI were followed for 13.3 ± 5.0 years for all-cause mortality (ACM). We applied propensity-matching to create pharmacologic and exercise groups with similar risk profiles.
In comparison to exercise patients, pharmacologic patients had an increased risk-adjusted hazard ratio for ACM for each level of ischemia: increased by 3.8-fold (95%CI 3.5-4.1) among nonischemic patients, 2.5-fold (95%CI 2.0-3.2) among mildly ischemic patients, and 2.6-fold (95%CI 2.1-3.3) among moderate/severe ischemic patients. Similar findings were observed among a propensity-matched cohort of 10,113 exercise and 10,113 pharmacologic patients as well as in an additional cohort that also excluded patients with noncardiac co-morbidities.
Patients requiring pharmacologic stress testing manifest substantially heightened clinical risk at each level of myocardial ischemia and even when myocardial ischemia is absent. These findings suggest the need to study the pathophysiological drivers of increased risk in association with pharmacologic testing and to convey this risk in clinical reports.