Deep Learning for Echo Analysis, Tracking, and Evaluation of Mitral Regurgitation (DELINEATE-MR).

BACKGROUND: Artificial intelligence, particularly deep learning (DL), has immense potential to improve the interpretation of transthoracic echocardiography (TTE). Mitral regurgitation (MR) is the most common valvular heart disease and presents unique challenges for DL, including the integration of multiple video-level assessments into a final study-level classification. METHODS: A novel DL system was developed to intake complete TTEs, identify color MR Doppler videos, and determine MR severity on a 4-step ordinal scale (none/trace, mild, moderate, and severe) using the reading cardiologist as a reference standard. This DL system was tested in internal and external test sets with performance assessed by agreement with the reading cardiologist, weighted κ, and area under the receiver-operating characteristic curve for binary classification of both moderate or greater and severe MR. In addition to the primary 4-step model, a 6-step MR assessment model was studied with the addition of the intermediate MR classes of mild-moderate and moderate-severe with performance assessed by both exact agreement and ±1 step agreement with the clinical MR interpretation. RESULTS: A total of 61 689 TTEs were split into train (n=43 811), validation (n=8891), and internal test (n=8987) sets with an additional external test set of 8208 TTEs. The model had high performance in MR classification in internal (exact accuracy, 82%; κ=0.84; area under the receiver-operating characteristic curve, 0.98 for moderate/severe MR) and external test sets (exact accuracy, 79%; κ=0.80; area under the receiver-operating characteristic curve, 0.98 for moderate or greater MR). Most (63% internal and 66% external) misclassification disagreements were between none/trace and mild MR. MR classification accuracy was slightly higher using multiple TTE views (accuracy, 82%) than with only apical 4-chamber views (accuracy, 80%). In subset analyses, the model was accurate in the classification of both primary and secondary MR with slightly lower performance in cases of eccentric MR. In the analysis of the 6-step classification system, the exact accuracy was 80% and 76% with a ±1 step agreement of 99% and 98% in the internal and external test set, respectively. CONCLUSIONS: This end-to-end DL system can intake entire echocardiogram studies to accurately classify MR severity and may be useful in helping clinicians refine MR assessments.

StrainNet: Improved Myocardial Strain Analysis of Cine MRI by Deep Learning from DENSE.

Purpose: To develop a three-dimensional (two dimensions + time) convolutional neural network trained with displacement encoding with stimulated echoes (DENSE) data for displacement and strain analysis of cine MRI. Materials and Methods: In this retrospective multicenter study, a deep learning model (StrainNet) was developed to predict intramyocardial displacement from contour motion. Patients with various heart diseases and healthy controls underwent cardiac MRI examinations with DENSE between August 2008 and January 2022. Network training inputs were a time series of myocardial contours from DENSE magnitude images, and ground truth data were DENSE displacement measurements. Model performance was evaluated using pixelwise end-point error (EPE). For testing, StrainNet was applied to contour motion from cine MRI. Global and segmental circumferential strain (Ecc) derived from commercial feature tracking (FT), StrainNet, and DENSE (reference) were compared using intraclass correlation coefficients (ICCs), Pearson correlations, Bland-Altman analyses, paired t tests, and linear mixed-effects models. Results: The study included 161 patients (110 men; mean age, 61 years ± 14 [SD]), 99 healthy adults (44 men; mean age, 35 years ± 15), and 45 healthy children and adolescents (21 males; mean age, 12 years ± 3). StrainNet showed good agreement with DENSE for intramyocardial displacement, with an average EPE of 0.75 mm ± 0.35. The ICCs between StrainNet and DENSE and FT and DENSE were 0.87 and 0.72, respectively, for global Ecc and 0.75 and 0.48, respectively, for segmental Ecc. Bland-Altman analysis showed that StrainNet had better agreement than FT with DENSE for global and segmental Ecc. Conclusion: StrainNet outperformed FT for global and segmental Ecc analysis of cine MRI.Keywords: Image Postprocessing, MR Imaging, Cardiac, Heart, Pediatrics, Technical Aspects, Technology Assessment, Strain, Deep Learning, DENSE Supplemental material is available for this article. © RSNA, 2023.

An ECG-based machine learning model for predicting new-onset atrial fibrillation is superior to age and clinical features in identifying patients at high stroke risk.

BACKGROUND: Several large trials have employed age or clinical features to select patients for atrial fibrillation (AF) screening to reduce strokes. We hypothesized that a machine learning (ML) model trained to predict AF risk from 12­lead electrocardiogram (ECG) would be more efficient than criteria based on clinical variables in indicating a population for AF screening to potentially prevent AF-related stroke. METHODS: We retrospectively included all patients with clinical encounters in Geisinger without a prior history of AF. Incidence of AF within 1 year and AF-related strokes within 3 years of the encounter were identified. AF-related stroke was defined as a stroke where AF was diagnosed at the time of stroke or within a year after the stroke. The efficiency of five methods was evaluated for selecting a cohort for AF screening. The methods were selected from four clinical trials (mSToPS, GUARD-AF, SCREEN-AF and STROKESTOP) and the ECG-based ML model. We simulated patient selection for the five methods between the years 2011 and 2014 and evaluated outcomes for 1 year intervals between 2012 and 2015, resulting in a total of twenty 1-year periods. Patients were considered eligible if they met the criteria before the start of the given 1-year period or within that period. The primary outcomes were numbers needed to screen (NNS) for AF and AF-associated stroke. RESULTS: The clinical trial models indicated large proportions of the population with a prior ECG for AF screening (up to 31%), coinciding with NNS ranging from 14 to 18 for AF and 249-359 for AF-associated stroke. At comparable sensitivity, the ECG ML model indicated a modest number of patients for screening (14%) and had the highest efficiency in NNS for AF (7.3; up to 60% reduction) and AF-associated stroke (223; up to 38% reduction). CONCLUSIONS: An ECG-based ML risk prediction model is more efficient than contemporary AF-screening criteria based on age alone or age and clinical features at indicating a population for AF screening to potentially prevent AF-related strokes.

rECHOmmend: An ECG-Based Machine Learning Approach for Identifying Patients at Increased Risk of Undiagnosed Structural Heart Disease Detectable by Echocardiography.

BACKGROUND: Timely diagnosis of structural heart disease improves patient outcomes, yet many remain underdiagnosed. While population screening with echocardiography is impractical, ECG-based prediction models can help target high-risk patients. We developed a novel ECG-based machine learning approach to predict multiple structural heart conditions, hypothesizing that a composite model would yield higher prevalence and positive predictive values to facilitate meaningful recommendations for echocardiography. METHODS: Using 2 232 130 ECGs linked to electronic health records and echocardiography reports from 484 765 adults between 1984 to 2021, we trained machine learning models to predict the presence or absence of any of 7 echocardiography-confirmed diseases within 1 year. This composite label included the following: moderate or severe valvular disease (aortic/mitral stenosis or regurgitation, tricuspid regurgitation), reduced ejection fraction <50%, or interventricular septal thickness >15 mm. We tested various combinations of input features (demographics, laboratory values, structured ECG data, ECG traces) and evaluated model performance using 5-fold cross-validation, multisite validation trained on 1 site and tested on 10 independent sites, and simulated retrospective deployment trained on pre-2010 data and deployed in 2010. RESULTS: Our composite rECHOmmend model used age, sex, and ECG traces and had a 0.91 area under the receiver operating characteristic curve and a 42% positive predictive value at 90% sensitivity, with a composite label prevalence of 17.9%. Individual disease models had area under the receiver operating characteristic curves from 0.86 to 0.93 and lower positive predictive values from 1% to 31%. Area under the receiver operating characteristic curves for models using different input features ranged from 0.80 to 0.93, increasing with additional features. Multisite validation showed similar results to cross-validation, with an aggregate area under the receiver operating characteristic curve of 0.91 across our independent test set of 10 clinical sites after training on a separate site. Our simulated retrospective deployment showed that for ECGs acquired in patients without preexisting structural heart disease in the year 2010, 11% were classified as high risk and 41% (4.5% of total patients) developed true echocardiography-confirmed disease within 1 year. CONCLUSIONS: An ECG-based machine learning model using a composite end point can identify a high-risk population for having undiagnosed, clinically significant structural heart disease while outperforming single-disease models and improving practical utility with higher positive predictive values. This approach can facilitate targeted screening with echocardiography to improve underdiagnosis of structural heart disease.

Deep-learning-assisted analysis of echocardiographic videos improves predictions of all-cause mortality.

Machine learning promises to assist physicians with predictions of mortality and of other future clinical events by learning complex patterns from historical data, such as longitudinal electronic health records. Here we show that a convolutional neural network trained on raw pixel data in 812,278 echocardiographic videos from 34,362 individuals provides superior predictions of one-year all-cause mortality. The model's predictions outperformed the widely used pooled cohort equations, the Seattle Heart Failure score (measured in an independent dataset of 2,404 patients with heart failure who underwent 3,384 echocardiograms), and a machine learning model involving 58 human-derived variables from echocardiograms and 100 clinical variables derived from electronic health records. We also show that cardiologists assisted by the model substantially improved the sensitivity of their predictions of one-year all-cause mortality by 13% while maintaining prediction specificity. Large unstructured datasets may enable deep learning to improve a wide range of clinical prediction models.

Deep Neural Networks Can Predict New-Onset Atrial Fibrillation From the 12-Lead ECG and Help Identify Those at Risk of Atrial Fibrillation-Related Stroke.

BACKGROUND: Atrial fibrillation (AF) is associated with substantial morbidity, especially when it goes undetected. If new-onset AF could be predicted, targeted screening could be used to find it early. We hypothesized that a deep neural network could predict new-onset AF from the resting 12-lead ECG and that this prediction may help identify those at risk of AF-related stroke. METHODS: We used 1.6 M resting 12-lead digital ECG traces from 430 000 patients collected from 1984 to 2019. Deep neural networks were trained to predict new-onset AF (within 1 year) in patients without a history of AF. Performance was evaluated using areas under the receiver operating characteristic curve and precision-recall curve. We performed an incidence-free survival analysis for a period of 30 years following the ECG stratified by model predictions. To simulate real-world deployment, we trained a separate model using all ECGs before 2010 and evaluated model performance on a test set of ECGs from 2010 through 2014 that were linked to our stroke registry. We identified the patients at risk for AF-related stroke among those predicted to be high risk for AF by the model at different prediction thresholds. RESULTS: The area under the receiver operating characteristic curve and area under the precision-recall curve were 0.85 and 0.22, respectively, for predicting new-onset AF within 1 year of an ECG. The hazard ratio for the predicted high- versus low-risk groups over a 30-year span was 7.2 (95% CI, 6.9-7.6). In a simulated deployment scenario, the model predicted new-onset AF at 1 year with a sensitivity of 69% and specificity of 81%. The number needed to screen to find 1 new case of AF was 9. This model predicted patients at high risk for new-onset AF in 62% of all patients who experienced an AF-related stroke within 3 years of the index ECG. CONCLUSIONS: Deep learning can predict new-onset AF from the 12-lead ECG in patients with no previous history of AF. This prediction may help identify patients at risk for AF-related strokes.

Prediction of mortality from 12-lead electrocardiogram voltage data using a deep neural network.

The electrocardiogram (ECG) is a widely used medical test, consisting of voltage versus time traces collected from surface recordings over the heart1. Here we hypothesized that a deep neural network (DNN) can predict an important future clinical event, 1-year all-cause mortality, from ECG voltage-time traces. By using ECGs collected over a 34-year period in a large regional health system, we trained a DNN with 1,169,662 12-lead resting ECGs obtained from 253,397 patients, in which 99,371 events occurred. The model achieved an area under the curve (AUC) of 0.88 on a held-out test set of 168,914 patients, in which 14,207 events occurred. Even within the large subset of patients (n = 45,285) with ECGs interpreted as 'normal' by a physician, the performance of the model in predicting 1-year mortality remained high (AUC = 0.85). A blinded survey of cardiologists demonstrated that many of the discriminating features of these normal ECGs were not apparent to expert reviewers. Finally, a Cox proportional-hazard model revealed a hazard ratio of 9.5 (P < 0.005) for the two predicted groups (dead versus alive 1 year after ECG) over a 25-year follow-up period. These results show that deep learning can add substantial prognostic information to the interpretation of 12-lead resting ECGs, even in cases that are interpreted as normal by physicians.

A Machine Learning Approach to Management of Heart Failure Populations.

BACKGROUND: Heart failure is a prevalent, costly disease for which new value-based payment models demand optimized population management strategies. OBJECTIVES: This study sought to generate a strategy for managing populations of patients with heart failure by leveraging large clinical datasets and machine learning. METHODS: Geisinger electronic health record data were used to train machine learning models to predict 1-year all-cause mortality in 26,971 patients with heart failure who underwent 276,819 clinical episodes. There were 26 clinical variables (demographics, laboratory test results, medications), 90 diagnostic codes, 41 electrocardiogram measurements and patterns, 44 echocardiographic measurements, and 8 evidence-based "care gaps": flu vaccine, blood pressure of <130/80 mm Hg, A1c of <8%, cardiac resynchronization therapy, and active medications (active angiotensin-converting enzyme inhibitor/angiotensin II receptor blocker/angiotensin receptor-neprilysin inhibitor, aldosterone receptor antagonist, hydralazine, and evidence-based beta-blocker) were collected. Care gaps represented actionable variables for which associations with all-cause mortality were modeled from retrospective data and then used to predict the benefit of prospective interventions in 13,238 currently living patients. RESULTS: Machine learning models achieved areas under the receiver-operating characteristic curve (AUCs) of 0.74 to 0.77 in a split-by-year training/test scheme, with the nonlinear XGBoost model (AUC: 0.77) outperforming linear logistic regression (AUC: 0.74). Out of 13,238 currently living patients, 2,844 were predicted to die within a year, and closing all care gaps was predicted to save 231 of these lives. Prioritizing patients for intervention by using the predicted reduction in 1-year mortality risk outperformed all other priority rankings (e.g., random selection or Seattle Heart Failure risk score). CONCLUSIONS: Machine learning can be used to priority-rank patients most likely to benefit from interventions to optimize evidence-based therapies. This approach may prove useful for optimizing heart failure population health management teams within value-based payment models.

Routinely reported ejection fraction and mortality in clinical practice: where does the nadir of risk lie?

AIMS: We investigated the relationship between clinically assessed left ventricular ejection fraction (LVEF) and survival in a large, heterogeneous clinical cohort. METHODS AND RESULTS: Physician-reported LVEF on 403 977 echocardiograms from 203 135 patients were linked to all-cause mortality using electronic health records (1998-2018) from US regional healthcare system. Cox proportional hazards regression was used for analyses while adjusting for many patient characteristics including age, sex, and relevant comorbidities. A dataset including 45 531 echocardiograms and 35 976 patients from New Zealand was used to provide independent validation of analyses. During follow-up of the US cohort, 46 258 (23%) patients who had undergone 108 578 (27%) echocardiograms died. Overall, adjusted hazard ratios (HR) for mortality showed a u-shaped relationship for LVEF with a nadir of risk at an LVEF of 60-65%, a HR of 1.71 [95% confidence interval (CI) 1.64-1.77] when ≥70% and a HR of 1.73 (95% CI 1.66-1.80) at LVEF of 35-40%. Similar relationships with a nadir at 60-65% were observed in the validation dataset as well as for each age group and both sexes. The results were similar after further adjustments for conditions associated with an elevated LVEF, including mitral regurgitation, increased wall thickness, and anaemia and when restricted to patients reported to have heart failure at the time of the echocardiogram. CONCLUSION: Deviation of LVEF from 60% to 65% is associated with poorer survival regardless of age, sex, or other relevant comorbidities such as heart failure. These results may herald the recognition of a new phenotype characterized by supra-normal LVEF.

Prevalence and Electronic Health Record-Based Phenotype of Loss-of-Function Genetic Variants in Arrhythmogenic Right Ventricular Cardiomyopathy-Associated Genes.

BACKGROUND: Arrhythmogenic right ventricular cardiomyopathy (ARVC) is associated with variants in desmosome genes. Secondary findings of pathogenic/likely pathogenic variants, primarily loss-of-function (LOF) variants, are recommended for clinical reporting; however, their prevalence and associated phenotype in a general clinical population are not fully characterized. METHODS: From whole-exome sequencing of 61 019 individuals in the DiscovEHR cohort, we screened for putative loss-of-function variants in PKP2, DSC2, DSG2, and DSP. We evaluated measures from prior clinical ECG and echocardiograms, manually over-read to evaluate ARVC diagnostic criteria, and performed a PheWAS (phenome-wide association study). Finally, we estimated expected penetrance using Bayesian inference. RESULTS: One hundred forty individuals (0.23%; 59±18 years old at last encounter; 33% male) had an ARVC variant (G+). None had an existing diagnosis of ARVC in the electronic health record, nor significant differences in prior ECG or echocardiogram findings compared with matched controls without variants. Several G+ individuals satisfied major repolarization (n=4) and ventricular function (n=5) criteria, but this prevalence matched controls. PheWAS showed no significant associations of other heart disease diagnoses. Combining our best genetic and disease prevalence estimates yields an estimated penetrance of 6.0%. CONCLUSIONS: The prevalence of ARVC loss-of-function variants is ≈1:435 in a general clinical population of predominantly European descent, but with limited electronic health record-based evidence of phenotypic association in our population, consistent with a low penetrance estimate. Prospective deep phenotyping and longitudinal follow-up of a large sequenced cohort is needed to determine the true clinical relevance of an incidentally identified ARVC loss-of-function variant.

Predicting Survival From Large Echocardiography and Electronic Health Record Datasets: Optimization With Machine Learning.

OBJECTIVES: The goal of this study was to use machine learning to more accurately predict survival after echocardiography. BACKGROUND: Predicting patient outcomes (e.g., survival) following echocardiography is primarily based on ejection fraction (EF) and comorbidities. However, there may be significant predictive information within additional echocardiography-derived measurements combined with clinical electronic health record data. METHODS: Mortality was studied in 171,510 unselected patients who underwent 331,317 echocardiograms in a large regional health system. The authors investigated the predictive performance of nonlinear machine learning models compared with that of linear logistic regression models using 3 different inputs: 1) clinical variables, including 90 cardiovascular-relevant International Classification of Diseases, Tenth Revision, codes, and age, sex, height, weight, heart rate, blood pressures, low-density lipoprotein, high-density lipoprotein, and smoking; 2) clinical variables plus physician-reported EF; and 3) clinical variables and EF, plus 57 additional echocardiographic measurements. Missing data were imputed with a multivariate imputation by using a chained equations algorithm (MICE). The authors compared models versus each other and baseline clinical scoring systems by using a mean area under the curve (AUC) over 10 cross-validation folds and across 10 survival durations (6 to 60 months). RESULTS: Machine learning models achieved significantly higher prediction accuracy (all AUC >0.82) over common clinical risk scores (AUC = 0.61 to 0.79), with the nonlinear random forest models outperforming logistic regression (p < 0.01). The random forest model including all echocardiographic measurements yielded the highest prediction accuracy (p < 0.01 across all models and survival durations). Only 10 variables were needed to achieve 96% of the maximum prediction accuracy, with 6 of these variables being derived from echocardiography. Tricuspid regurgitation velocity was more predictive of survival than LVEF. In a subset of studies with complete data for the top 10 variables, multivariate imputation by chained equations yielded slightly reduced predictive accuracies (difference in AUC of 0.003) compared with the original data. CONCLUSIONS: Machine learning can fully utilize large combinations of disparate input variables to predict survival after echocardiography with superior accuracy.

Comparison of left ventricular strains and torsion derived from feature tracking and DENSE CMR.

BACKGROUND: Cardiovascular magnetic resonance (CMR) feature tracking is increasingly used to quantify cardiac mechanics from cine CMR imaging, although validation against reference standard techniques has been limited. Furthermore, studies have suggested that commonly-derived metrics, such as peak global strain (reported in 63% of feature tracking studies), can be quantified using contours from just two frames - end-diastole (ED) and end-systole (ES) - without requiring tracking software. We hypothesized that mechanics derived from feature tracking would not agree with those derived from a reference standard (displacement-encoding with stimulated echoes (DENSE) imaging), and that peak strain from feature tracking would agree with that derived using simple processing of only ED and ES contours. METHODS: We retrospectively identified 88 participants with 186 pairs of DENSE and balanced steady state free precession (bSSFP) image slices acquired at the same locations across two institutions. Left ventricular (LV) strains, torsion, and dyssynchrony were quantified from both feature tracking (TomTec Imaging Systems, Circle Cardiovascular Imaging) and DENSE. Contour-based strains from bSSFP images were derived from ED and ES contours. Agreement was assessed with Bland-Altman analyses and coefficients of variation (CoV). All biases are reported in absolute percentage. RESULTS: Comparison results were similar for both vendor packages (TomTec and Circle), and thus only TomTec Imaging System data are reported in the abstract for simplicity. Compared to DENSE, mid-ventricular circumferential strain (Ecc) from feature tracking had acceptable agreement (bias: - 0.4%, p = 0.36, CoV: 11%). However, feature tracking significantly overestimated the magnitude of Ecc at the base (bias: - 4.0% absolute, p < 0.001, CoV: 18%) and apex (bias: - 2.4% absolute, p = 0.01, CoV: 15%), underestimated torsion (bias: - 1.4 deg/cm, p < 0.001, CoV: 41%), and overestimated dyssynchrony (bias: 26 ms, p < 0.001, CoV: 76%). Longitudinal strain (Ell) had borderline-acceptable agreement (bias: - 0.2%, p = 0.77, CoV: 19%). Contour-based strains had excellent agreement with feature tracking (biases: - 1.3-0.2%, CoVs: 3-7%). CONCLUSION: Compared to DENSE as a reference standard, feature tracking was inaccurate for quantification of apical and basal LV circumferential strains, longitudinal strain, torsion, and dyssynchrony. Feature tracking was only accurate for quantification of mid LV circumferential strain. Moreover, feature tracking is unnecessary for quantification of whole-slice strains (e.g. base, apex), since simplified processing of only ED and ES contours yields very similar results to those derived from feature tracking. Current feature tracking technology therefore has limited utility for quantification of cardiac mechanics.

Impact of the cone operation on left ventricular size, function, and dyssynchrony in Ebstein anomaly: a cardiovascular magnetic resonance study.

BACKGROUND: In addition to tricuspid regurgitation (TR) and right ventricular (RV) enlargement, patients with Ebstein anomaly are at risk for left ventricular (LV) dysfunction and dyssynchrony. We studied the impact of the cone tricuspid valve reconstruction operation on LV size, function, and dyssynchrony. METHODS: All Ebstein anomaly patients who had both pre- and postoperative cardiovascular magnetic resonance (CMR) studies were retrospectively identified. From cine images, RV and LV volumes and ejection fractions (EF) were calculated, and LV circumferential and longitudinal strain were measured by feature tracking. To quantify LV dyssynchrony, temporal offsets (TOs) were computed among segmental circumferential strain versus time curves using cross-correlation analysis and patient-specific reference curves. An LV dyssynchrony index was calculated as the standard deviation of the TOs. RESULTS: Twenty patients (65% female) were included with a median age at cone operation of 16 years, and a median time between pre- and postoperative CMR of 2.8 years. Postoperatively, there was a decline in the TR fraction (56 ± 19% vs. 5 ± 4%, p < 0.001), RV end-diastolic volume (EDV) (242 ± 110 ml/m2 vs. 137 ± 82 ml/m2, p < 0.001), and RV stroke volume (SV) (101 ± 35 vs. 51 ± 7 ml/m2, p < 0.001). RV EF was unchanged. Conversely, there was an increase in both LV EDV (68 ± 13 vs. 85 ± 13 ml/m2, p < 0.001) and LV stroke volume (37 ± 8 vs. 48 ± 6 ml/m2, p < 0.001). There was no change in LV EF, or global circumferential and longitudinal strain but basal septal circumferential strain improved (16 ± 7% vs. 22 ± 5%, p = 0.04). LV contraction become more synchronous (dyssynchrony index: 32 ± 17 vs. 21 ± 9 msec, p = 0.02), and the extent correlated with the reduction in RV EDV and TR. CONCLUSIONS: In patients with the Ebstein anomaly, the cone operation led to reduced TR and RV stroke volume, increased LV stroke volume, improved LV basal septal strain, and improved LV synchrony. Our data demonstrates that the detrimental effect of the RV on LV function can be mitigated by the cone operation.

Predicting deterioration of ventricular function in patients with repaired tetralogy of Fallot using machine learning.

Aims: Previous studies using regression analyses have failed to identify which patients with repaired tetralogy of Fallot (rTOF) are at risk for deterioration in ventricular size and function despite using common clinical and cardiac function parameters as well as cardiac mechanics (strain and dyssynchrony). This study used a machine learning pipeline to comprehensively investigate the predictive value of the baseline variables derived from cardiac magnetic resonance (CMR) imaging and provide models for identifying patients at risk for deterioration. Methods and results: Longitudinal deterioration for 153 patients with rTOF was categorized as 'none', 'minor', or 'major' based on changes in ventricular size and ejection fraction between two CMR scans at least 6 months apart (median 2.7 years). Baseline variables were measured at the time of the first CMR. An exhaustive variable search with a support vector machine classifier and five-fold cross-validation was used to predict deterioration and identify the most useful variables. For predicting any deterioration (minor or major) vs. no deterioration, the mean area under the curve (AUC) was 0.82 ± 0.06. For predicting major deterioration vs. minor or no deterioration, the AUC was 0.77 ± 0.07. Baseline left ventricular (LV) ejection fraction, LV circumferential strain, and pulmonary regurgitation were most useful for achieving accurate predictions. Conclusion: For the prediction of deterioration in patients with rTOF, a machine learning pipeline uncovered the utility of baseline variables that was previously lost to regression analyses. The predictive models may be useful for planning early interventions in patients with high risk.

Association between left ventricular mechanics and diffuse myocardial fibrosis in patients with repaired Tetralogy of Fallot: a cross-sectional study.

BACKGROUND: Patients with repaired tetralogy of Fallot (TOF) have progressive, adverse biventricular remodeling, leading to abnormal contractile mechanics. Defining the mechanisms underlying this dysfunction, such as diffuse myocardial fibrosis, may provide insights into poor long-term outcomes. We hypothesized that left ventricular (LV) diffuse fibrosis is related to impaired LV mechanics. METHODS: Patients with TOF were evaluated with cardiac magnetic resonance in which modified Look-Locker (MOLLI) T1-mapping and spiral cine Displacement encoding (DENSE) sequences were acquired at three LV short-axis positions. Linear mixed modeling was used to define the association between regional LV mechanics from DENSE based on regional T1-derived diffuse fibrosis measures, such as extracellular volume fraction (ECV). RESULTS: Forty patients (26 ± 11 years) were included. LV ECV was generally within normal range (0.24 ± 0.05). For LV mechanics, peak circumferential strains (-15 ± 3%) and dyssynchrony indices (16 ± 8 ms) were moderately impaired, while peak radial strains (29 ± 8%) were generally normal. After adjusting for patient age, sex, and regional LV differences, ECV was associated with log-adjusted LV dyssynchrony index (ß = 0.67) and peak LV radial strain (ß = -0.36), but not LV circumferential strain. Moreover, post-contrast T1 was associated with log-adjusted LV diastolic circumferential strain rate (ß = 0.37). CONCLUSIONS: We observed several moderate associations between measures of fibrosis and impaired mechanics, particularly the LV dyssynchrony index and peak radial strain. Diffuse fibrosis may therefore be a causal factor in some ventricular dysfunction in TOF.

Ambulatory systolic blood pressure and obesity are independently associated with left ventricular hypertrophic remodeling in children.

BACKGROUND: Children with obesity have hypertrophic cardiac remodeling. Hypertension is common in pediatric obesity, and may independently contribute to hypertrophy. We hypothesized that both the degree of obesity and ambulatory blood pressure (ABP) would independently associate with measures of hypertrophic cardiac remodeling in children. METHODS: Children, aged 8-17 years, prospectively underwent cardiovascular magnetic resonance (CMR) and ABP monitoring. Left ventricular (LV) mass indexed to height2.7 (LVMI), myocardial thickness and end-diastolic volume were quantified from a 3D LV model reconstructed from cine balanced steady state free precession images. Categories of remodeling were determined based on cutoff values for LVMI and mass/volume. Principal component analysis was used to define a "hypertrophy score" to study the continuous relationship between concentric hypertrophy and ABP. RESULTS: Seventy-two children were recruited, and 68 of those (37 healthy weight and 31 obese/overweight) completed both CMR and ABP monitoring. Obese/overweight children had increased LVMI (27 ± 4 vs 22 ± 3 g/m2.7, p < 0.001), myocardial thickness (5.6 ± 0.9 vs 4.9 ± 0.7 mm, p < 0.001), mass/volume (0.69 ± 0.1 vs 0.61 ± 0.06, p < 0.001), and hypertrophy score (1.1 ± 2.2 vs -0.96 ± 1.1, p < 0.001). Thirty-five percent of obese/overweight children had concentric hypertrophy. Ambulatory hypertension was observed in 26% of the obese/overweight children and none of the controls while masked hypertension was observed in 32% of the obese/overweight children and 16% of the controls. Univariate linear regression showed that BMI z-score, systolic BP (24 h, day and night), and systolic load correlated with LVMI, thickness, mass/volume and hypertrophy score, while 24 h and nighttime diastolic BP and load also correlated with thickness and mass/volume. Multivariate analysis showed body mass index z-score and systolic blood pressure were both independently associated with left ventricular mass index (ß=0.54 [p < 0.001] and 0.22 [p = 0.03]), thickness (ß=0.34 [p < 0.001] and 0.26 [p = 0.001]) and hypertrophy score (ß=0.47 and 0.36, both p < 0.001). CONCLUSIONS: In children, both the degree of obesity and ambulatory blood pressures are independently associated with measures of cardiac hypertrophic remodeling, however the correlations were generally stronger for the degree of obesity. This suggests that interventions targeted at weight loss or obesity-associated co-morbidities including hypertension may be effective in reversing or preventing cardiac remodeling in obese children.

Impaired right ventricular contractile function in childhood obesity and its association with right and left ventricular changes: a cine DENSE cardiac magnetic resonance study.

BACKGROUND: Pediatric obesity is a growing public health problem, which is associated with increased risk of cardiovascular disease and premature death. Left ventricular (LV) remodeling (increased myocardial mass and thickness) and contractile dysfunction (impaired longitudinal strain) have been documented in obese children, but little attention has been paid to the right ventricle (RV). We hypothesized that obese/overweight children would have evidence of RV remodeling and contractile dysfunction. METHODS: One hundred and three children, ages 8-18 years, were prospectively recruited and underwent cardiovascular magnetic resonance (CMR), including both standard cine imaging and displacement encoding with stimulated echoes (DENSE) imaging, which allowed for quantification of RV geometry and function/mechanics. RV free wall longitudinal strain was quantified from the end-systolic four-chamber DENSE image. Linear regression was used to quantify correlations of RV strain with LV strain and measurements of body composition (adjusted for sex and height). Analysis of variance was used to study the relationship between RV strain and LV remodeling types (concentric remodeling, eccentric/concentric hypertrophy). RESULTS: The RV was sufficiently visualized with DENSE in 70 (68%) subjects, comprising 36 healthy weight (13.6 ± 2.7 years) and 34 (12.1 ± 2.9 years) obese/overweight children. Obese/overweight children had a 22% larger RV mass index (8.2 ± 0.9 vs 6.7 ± 1.1 g/m2.7, p < 0.001) compared to healthy controls. RV free wall longitudinal strain was impaired in obese/overweight children (-16 ± 4% vs -19 ± 5%, p = 0.02). Ten (14%) out of 70 children had LV concentric hypertrophy, and these children had the most impaired RV longitudinal strain compared to those with normal LV geometry (-13 ± 4% vs -19 ± 5%, p = 0.002). RV longitudinal strain was correlated with LV longitudinal strain (r = 0.34, p = 0.004), systolic blood pressure (r = 0.33, p = 0.006), as well as BMI z-score (r = 0.28, p = 0.02), waist (r = 0.31, p = 0.01), hip (r = 0.40, p = 0.004) and abdominal (r = 0.38, p = 0.002) circumference, height and sex adjusted. CONCLUSIONS: Obese/overweight children have evidence of RV remodeling (increased RV mass) and RV contractile dysfunction (impaired free wall longitudinal strain). Moreover, RV longitudinal strain correlates with LV longitudinal strain, and children with LV concentric hypertrophy show the most impaired RV function. These results suggest there may be a common mechanism underlying both remodeling and dysfunction of the left and right ventricles in obese/overweight children.

Right Ventricular Strain, Torsion, and Dyssynchrony in Healthy Subjects Using 3D Spiral Cine DENSE Magnetic Resonance Imaging.

Mechanics of the left ventricle (LV) are important indicators of cardiac function. The role of right ventricular (RV) mechanics is largely unknown due to the technical limitations of imaging its thin wall and complex geometry and motion. By combining 3D Displacement Encoding with Stimulated Echoes (DENSE) with a post-processing pipeline that includes a local coordinate system, it is possible to quantify RV strain, torsion, and synchrony. In this study, we sought to characterize RV mechanics in 50 healthy individuals and compare these values to their LV counterparts. For each cardiac frame, 3D displacements were fit to continuous and differentiable radial basis functions, allowing for the computation of the 3D Cartesian Lagrangian strain tensor at any myocardial point. The geometry of the RV was extracted via a surface fit to manually delineated endocardial contours. Throughout the RV, a local coordinate system was used to transform from a Cartesian strain tensor to a polar strain tensor. It was then possible to compute peak RV torsion as well as peak longitudinal and circumferential strain. A comparable analysis was performed for the LV. Dyssynchrony was computed from the standard deviation of regional activation times. Global circumferential strain was comparable between the RV and LV (-18.0% for both) while longitudinal strain was greater in the RV (-18.1% vs. -15.7%). RV torsion was comparable to LV torsion (6.2 vs. 7.1 degrees, respectively). Regional activation times indicated that the RV contracted later but more synchronously than the LV. 3D spiral cine DENSE combined with a post-processing pipeline that includes a local coordinate system can resolve both the complex geometry and 3D motion of the RV.

Left and right ventricular dyssynchrony and strains from cardiovascular magnetic resonance feature tracking do not predict deterioration of ventricular function in patients with repaired tetralogy of Fallot.

BACKGROUND: Patients with repaired tetralogy of Fallot (rTOF) suffer from progressive ventricular dysfunction decades after their surgical repair. We hypothesized that measures of ventricular strain and dyssynchrony would predict deterioration of ventricular function in patients with rTOF. METHODS: A database search identified all patients at a single institution with rTOF who underwent cardiovascular magnetic resonance (CMR) at least twice, >6 months apart, without intervening surgical or catheter procedures. Seven primary predictors were derived from the first CMR using a custom feature tracking algorithm: left (LV), right (RV) and inter-ventricular dyssynchrony, LV and RV peak global circumferential strains, and LV and RV peak global longitudinal strains. Three outcomes were defined, whose changes were assessed over time: RV end-diastolic volume, and RV and LV ejection fraction. Multivariate linear mixed models were fit to investigate relationships of outcomes to predictors and ten potential baseline confounders. RESULTS: One hundred fifty-three patients with rTOF (23 ± 14 years, 50 % male) were included. The mean follow-up duration between the first and last CMR was 2.9 ± 1.3 years. After adjustment for confounders, none of the 7 primary predictors were significantly associated with change over time in the 3 outcome variables. Only 1-17 % of the variability in the change over time in the outcome variables was explained by the baseline predictors and potential confounders. CONCLUSIONS: In patients with repaired tetralogy of Fallot, ventricular dyssynchrony and global strain derived from cine CMR were not significantly related to changes in ventricular size and function over time. The ability to predict deterioration in ventricular function in patients with rTOF using current methods is limited.