Patient-Specific Myocardial Infarction Risk Thresholds From AI-Enabled Coronary Plaque Analysis.

BACKGROUND: Plaque quantification from coronary computed tomography angiography has emerged as a valuable predictor of cardiovascular risk. Deep learning can provide automated quantification of coronary plaque from computed tomography angiography. We determined per-patient age- and sex-specific distributions of deep learning-based plaque measurements and further evaluated their risk prediction for myocardial infarction in external samples. METHODS: In this international, multicenter study of 2803 patients, a previously validated deep learning system was used to quantify coronary plaque from computed tomography angiography. Age- and sex-specific distributions of coronary plaque volume were determined from 956 patients undergoing computed tomography angiography for stable coronary artery disease from 5 cohorts. Multicenter external samples were used to evaluate associations between coronary plaque percentiles and myocardial infarction. RESULTS: Quantitative deep learning plaque volumes increased with age and were higher in male patients. In the combined external sample (n=1847), patients in the ≥75th percentile of total plaque volume (unadjusted hazard ratio, 2.65 [95% CI, 1.47-4.78]; P=0.001) were at increased risk of myocardial infarction compared with patients below the 50th percentile. Similar relationships were seen for most plaque volumes and persisted in multivariable analyses adjusting for clinical characteristics, coronary artery calcium, stenosis, and plaque volume, with adjusted hazard ratios ranging from 2.38 to 2.50 for patients in the ≥75th percentile of total plaque volume. CONCLUSIONS: Per-patient age- and sex-specific distributions for deep learning-based coronary plaque volumes are strongly predictive of myocardial infarction, with the highest risk seen in patients with coronary plaque volumes in the ≥75th percentile.

AI-based volumetric six-tissue body composition quantification from CT cardiac attenuation scans enhances mortality prediction: multicenter study.

Background: Computed tomography attenuation correction (CTAC) scans are routinely obtained during cardiac perfusion imaging, but currently only utilized for attenuation correction and visual calcium estimation. We aimed to develop a novel artificial intelligence (AI)-based approach to obtain volumetric measurements of chest body composition from CTAC scans and evaluate these measures for all-cause mortality (ACM) risk stratification. Methods: We applied AI-based segmentation and image-processing techniques on CTAC scans from a large international image-based registry (four sites), to define chest rib cage and multiple tissues. Volumetric measures of bone, skeletal muscle (SM), subcutaneous, intramuscular (IMAT), visceral (VAT), and epicardial (EAT) adipose tissues were quantified between automatically-identified T5 and T11 vertebrae. The independent prognostic value of volumetric attenuation, and indexed volumes were evaluated for predicting ACM, adjusting for established risk factors and 18 other body compositions measures via Cox regression models and Kaplan-Meier curves. Findings: End-to-end processing time was <2 minutes/scan with no user interaction. Of 9918 patients studied, 5451(55%) were male. During median 2.5 years follow-up, 610 (6.2%) patients died. High VAT, EAT and IMAT attenuation were associated with increased ACM risk (adjusted hazard ratio (HR) [95% confidence interval] for VAT: 2.39 [1.92, 2.96], p<0.0001; EAT: 1.55 [1.26, 1.90], p<0.0001; IMAT: 1.30 [1.06, 1.60], p=0.0124). Patients with high bone attenuation were at lower risk of death as compared to subjects with lower bone attenuation (adjusted HR 0.77 [0.62, 0.95], p=0.0159). Likewise, high SM volume index was associated with a lower risk of death (adjusted HR 0.56 [0.44, 0.71], p<0.0001). Interpretations: CTAC scans obtained routinely during cardiac perfusion imaging contain important volumetric body composition biomarkers which can be automatically measured and offer important additional prognostic value.

Machine Learning From Quantitative Coronary Computed Tomography Angiography Predicts Fractional Flow Reserve-Defined Ischemia and Impaired Myocardial Blood Flow.

BACKGROUND: A pathophysiological interplay exists between plaque morphology and coronary physiology. Machine learning (ML) is increasingly being applied to coronary computed tomography angiography (CCTA) for cardiovascular risk stratification. We sought to assess the performance of a ML score integrating CCTA-based quantitative plaque features for predicting vessel-specific ischemia by invasive fractional flow reserve (FFR) and impaired myocardial blood flow (MBF) by positron emission tomography (PET). METHODS: This post-hoc analysis of the PACIFIC trial (Prospective Comparison of Cardiac Positron Emission Tomography/Computed Tomography [CT]' Single Photon Emission Computed Tomography/CT Perfusion Imaging and CT Coronary Angiography with Invasive Coronary Angiography) included 208 patients with suspected coronary artery disease who prospectively underwent CCTA' [15O]H2O PET, and invasive FFR. Plaque quantification from CCTA was performed using semiautomated software. An ML algorithm trained on the prospective NXT trial (484 vessels) was used to develop a ML score for the prediction of ischemia (FFR≤0.80), which was then evaluated in 581 vessels from the PACIFIC trial. Thereafter, the ML score was applied for predicting impaired hyperemic MBF (≤2.30 mL/min per g) from corresponding PET scans. The performance of the ML score was compared with CCTA reads and noninvasive FFR derived from CCTA (FFRCT). RESULTS: One hundred thirty-nine (23.9%) vessels had FFR-defined ischemia, and 195 (33.6%) vessels had impaired hyperemic MBF. For the prediction of FFR-defined ischemia, the ML score yielded an area under the receiver-operating characteristic curve of 0.92, which was significantly higher than that of visual stenosis grade (0.84; P<0.001) and comparable with that of FFRCT (0.93; P=0.34). Quantitative percent diameter stenosis and low-density noncalcified plaque volume had the greatest ML feature importance for predicting FFR-defined ischemia. When applied for impaired MBF prediction, the ML score exhibited an area under the receiver-operating characteristic curve of 0.80; significantly higher than visual stenosis grade (area under the receiver-operating characteristic curve 0.74; P=0.02) and comparable with FFRCT (area under the receiver-operating characteristic curve 0.77; P=0.16). CONCLUSIONS: An externally validated ML score integrating CCTA-based quantitative plaque features accurately predicts FFR-defined ischemia and impaired MBF by PET, performing superiorly to standard CCTA stenosis evaluation and comparably to FFRCT.

Handling missing values in machine learning to predict patient-specific risk of adverse cardiac events: Insights from REFINE SPECT registry.

BACKGROUND: Machine learning (ML) models can improve prediction of major adverse cardiovascular events (MACE), but in clinical practice some values may be missing. We evaluated the influence of missing values in ML models for patient-specific prediction of MACE risk. METHODS: We included 20,179 patients from the multicenter REFINE SPECT registry with MACE follow-up data. We evaluated seven methods for handling missing values: 1) removal of variables with missing values (ML-Remove), 2) imputation with median and unique category for continuous and categorical variables, respectively (ML-Traditional), 3) unique category for missing variables (ML-Unique), 4) cluster-based imputation (ML-Cluster), 5) regression-based imputation (ML-Regression), 6) missRanger imputation (ML-MR), and 7) multiple imputation (ML-MICE). We trained ML models with full data and simulated missing values in testing patients. Prediction performance was evaluated using area under the receiver-operating characteristic curve (AUC) and compared with a model without missing values (ML-All), expert visual diagnosis and total perfusion deficit (TPD). RESULTS: During mean follow-up of 4.7 ± 1.5 years, 3,541 patients experienced at least one MACE (3.7% annualized risk). ML-All (reference model-no missing values) had AUC 0.799 for MACE risk prediction. All seven models with missing values had lower AUC (ML-Remove: 0.778, ML-MICE: 0.774, ML-Cluster: 0.771, ML-Traditional: 0.771, ML-Regression: 0.770, ML-MR: 0.766, and ML-Unique: 0.766; p < 0.01 for ML-Remove vs remaining methods). Stress TPD (AUC 0.698) and visual diagnosis (0.681) had the lowest AUCs. CONCLUSION: Missing values reduce the accuracy of ML models when predicting MACE risk. Removing variables with missing values and retraining the model may yield superior patient-level prediction performance.

Deep learning-enabled coronary CT angiography for plaque and stenosis quantification and cardiac risk prediction: an international multicentre study.

BACKGROUND: 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. METHODS: 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. FINDINGS: 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). INTERPRETATION: 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. FUNDING: National Heart, Lung, and Blood Institute and the Miriam & Sheldon G Adelson Medical Research Foundation.