Machine-learning phenotypic classification of bicuspid aortopathy

Performance Drift in Machine Learning Models for Cardiac Surgery Risk Prediction: Retrospective Analysis

Background

The Society of Thoracic Surgeons and European System for Cardiac Operative Risk Evaluation (EuroSCORE) II risk scores are the most commonly used risk prediction models for in-hospital mortality after adult cardiac surgery. However, they are prone to miscalibration over time and poor generalization across data sets; thus, their use remains controversial. Despite increased interest, a gap in understanding the effect of data set drift on the performance of machine learning (ML) over time remains a barrier to its wider use in clinical practice. Data set drift occurs when an ML system underperforms because of a mismatch between the data it was developed from and the data on which it is deployed.

Objective

In this study, we analyzed the extent of performance drift using models built on a large UK cardiac surgery database. The objectives were to (1) rank and assess the extent of performance drift in cardiac surgery risk ML models over time and (2) investigate any potential influence of data set drift and variable importance drift on performance drift.

Methods

We conducted a retrospective analysis of prospectively, routinely gathered data on adult patients undergoing cardiac surgery in the United Kingdom between 2012 and 2019. We temporally split the data 70:30 into a training and validation set and a holdout set. Five novel ML mortality prediction models were developed and assessed, along with EuroSCORE II, for relationships between and within variable importance drift, performance drift, and actual data set drift. Performance was assessed using a consensus metric.

Results

A total of 227,087 adults underwent cardiac surgery during the study period, with a mortality rate of 2.76% (n=6258). There was strong evidence of a decrease in overall performance across all models (P<.0001). Extreme gradient boosting (clinical effectiveness metric [CEM] 0.728, 95% CI 0.728-0.729) and random forest (CEM 0.727, 95% CI 0.727-0.728) were the overall best-performing models, both temporally and nontemporally. EuroSCORE II performed the worst across all comparisons. Sharp changes in variable importance and data set drift from October to December 2017, from June to July 2018, and from December 2018 to February 2019 mirrored the effects of performance decrease across models.

Conclusions

All models show a decrease in at least 3 of the 5 individual metrics. CEM and variable importance drift detection demonstrate the limitation of logistic regression methods used for cardiac surgery risk prediction and the effects of data set drift. Future work will be required to determine the interplay between ML models and whether ensemble models could improve on their respective performance advantages.

Aortic diameter is a poor predictor of aortic tissue failure metrics in patients with ascending aneurysms

OBJECTIVES

There is growing consensus that aortic diameter is a flawed predictor of aortic dissection risk. We hypothesized that aortic tissue metrics would be better predicted by clinical metrics other than aortic diameter. Our objectives were to (1) characterize circumferential aortic failure stress and stretch as a result of aortic size and patient demographics, and (2) identify the influence of bicuspid aortic valve on failure metrics.

METHODS

From February 2018 to January 2021, 136 aortic tissue samples were obtained from 86 adults undergoing elective ascending aorta repair. Uniaxial biomechanical testing to failure, defined as a full-thickness central tear, was performed to obtain tissue failure stress and failure stretch and compared with clinical data and preoperative computed tomography imaging. The relationships among aortic diameter, patient demographics, and failure metrics were assessed using random forest regression models.

RESULTS

Median failure stress was 1.46 (1.02-1.94) megapascals, and failure stretch was 1.36 (1.27-1.54). Regression models correlated moderately with failure stress (R2 = 0.557) and highly with failure stretch (R2 = 0.806). Failure stress decreased with increasing age, lower body mass index, thicker tissue, and tricuspid aortic valves, whereas failure stretch was most highly correlated with age. Aortic area-to-height index outperformed aortic diameter in all models.

CONCLUSIONS

Aneurysmal ascending aortic tissue failure metrics correlated with available clinical metrics. Greater tissue thickness, older age, and tricuspid aortic valve morphology outperformed aortic diameter, warranting further investigation into the role of a patient-specific multifactorial dissection risk assessment over aortic diameter as a sole marker of aortic tissue integrity.

The Role of Artificial Intelligence in Cardiac Imaging

Artificial intelligence (AI) is having a significant impact in medical imaging, advancing almost every aspect of the field, from image acquisition and postprocessing to automated image analysis with outreach toward supporting decision making. Noninvasive cardiac imaging is one of the main and most exciting fields for AI development. The aim of this review is to describe the main applications of AI in cardiac imaging, including CT and MR imaging, and provide an overview of recent advancements and available clinical applications that can improve clinical workflow, disease detection, and prognostication in cardiac disease.

Well-functioning bicuspid aortic valves should be preserved during aortic replacement for the ascending aortopathy phenotype

OBJECTIVES

Consensus has not been reached on whether or not to replace or preserve a well-functioning bicuspid aortic valve (BAV) in patients undergoing aortic replacement for the ascending phenotype of BAV aortopathy. We characterize morphology, evaluate progression of aortic regurgitation or aortic stenosis, and investigate the need for aortic valve replacement in patients whose well-functioning BAV was preserved during ascending aortic replacement ≥10 years prior.

METHODS

From January 1991 to August 2011, 191 patients with a well-functioning BAV underwent supracoronary aortic replacement (113 valves were minimally repaired). Aortic morphology was evaluated, aortic regurgitation grade and transvalvular aortic gradient modeled parametrically, and survival assessed by the Kaplan-Meier method. Median follow-up was 10 years.

RESULTS

Mean aortic diameter was 2.9 ± 0.53 cm at the annulus and 4.2 ± 0.55 cm at the sinuses. Mean maximum ascending diameter was 5.1 ± 0.49 cm. All patients exhibited a cusp-fusion BAV phenotype. Fifteen-year progression to severe aortic regurgitation was 3.2%. Mean aortic valve gradient began to rise 5 years postoperatively to 27 mm Hg by 14 years. Freedom from aortic valve replacement at 1, 5, 10, and 15 years was 100%, 95%, 83%, and 63%, respectively. Minimal valve repair was not associated with late aortic valve replacement. Fifteen-year survival was 74%.

CONCLUSIONS

Preserving a well-functioning BAV should be considered in carefully selected patients undergoing aortic replacement for the ascending phenotype of BAV aortopathy. The valves remain durable in the long term, with slow progression of regurgitation or stenosis, and low probability of aortic valve replacement through 10 years.

Age is superior to aortopathy phenotype as a predictor of aortic mechanics in patients with bicuspid valve

OBJECTIVES

Bicuspid aortic valve (BAV) aortopathy is defined by 3 phenotypes-root, ascending, and diffuse-based on region of maximal aortic dilation. We sought to determine the association between aortic mechanical behavior and aortopathy phenotype versus other clinical variables.

METHODS

From August 1, 2016, to March 1, 2023, 375 aortic specimens were collected from 105 patients undergoing elective ascending aortic aneurysm repair for BAV aortopathy. Planar biaxial data (191 specimens) informed constitutive descriptors of the arterial wall that were combined with in vivo geometry and hemodynamics to predict stiffness, stress, and energy density under physiologic loads. Uniaxial testing (184 specimens) evaluated failure stretch and failure Cauchy stress. Boosting regression was implemented to model the association between clinical variables and mechanical metrics.

RESULTS

There were no significant differences in mechanical metrics between the root phenotype (N = 33, 31%) and ascending/diffuse phenotypes (N = 72, 69%). Biaxial testing demonstrated older age was associated with increased circumferential stiffness, decreased stress, and decreased energy density. On uniaxial testing, longitudinally versus circumferentially oriented specimens failed at significantly lower Cauchy stress (50th [15th, 85th percentiles]: 1.0 [0.7, 1.6] MPa vs 1.9 [1.3, 3.1] MPa; P < .001). Age was associated with decreased failure stretch and stress. Elongated ascending aortas were also associated with decreased failure stress.

CONCLUSIONS

Aortic mechanical function under physiologic and failure conditions in BAV aortopathy is robustly associated with age and poorly associated with aortopathy phenotype. Data suggesting that the root phenotype of BAV aortopathy portends worse outcomes are unlikely to be related to aberrant, phenotype-specific tissue mechanics.

Ex vivo biaxial load testing analysis of aortic biomechanics demonstrates variation in elastic energy distribution across the aortic zone zero

OBJECTIVES

We hypothesized that tissue characteristics vary significantly along zone zero, which may be reflected by regional differences in stored elastic energy. Our objectives were to (1) characterize the regional variation in stored elastic energy within tissues of the aortic zone zero and (2) identify the association between this variation and patient characteristics.

METHODS

From February 2018 to January 2021, 123 aortic tissue samples were obtained from the aortic root and proximal and distal ascending aortas of 65 adults undergoing elective ascending aorta replacement. Biaxial biomechanics testing was performed to obtain tissue elastic energy at the inflection point and compared with patient demographics and preoperative computed tomography imaging. Coefficient models were fit using B-spline to interrogate the relationship among elastic energy, region, and patient characteristics.

RESULTS

Mean elastic energy at inflection point was 24.3 ± 15.6 kJ/m3. Elastic energy increased significantly between the root and proximal, and root and distal ascending aorta and decreased with increasing age. Differences due to history of connective tissue disorder and bicuspid aortic valve were significant but diminished when controlled for other patient characteristics. Among covariates, age and region were found to be the most important predictors for elastic energy.

CONCLUSIONS

Aortic tissue biomechanical metrics varied across regions and with patient characteristics within the aortic zone zero. Assessment of endovascular outcomes in the ascending aorta must closely consider the region of deployment and variable tissue qualities along the length of the landing zone. Regional variation in tissue characteristics should be incorporated into existing patient-specific models of aortic mechanics.

Unsupervised learning to characterize patients with known coronary artery disease undergoing myocardial perfusion imaging

PURPOSE

Patients with known coronary artery disease (CAD) comprise a heterogenous population with varied clinical and imaging characteristics. Unsupervised machine learning can identify new risk phenotypes in an unbiased fashion. We use cluster analysis to risk-stratify patients with known CAD undergoing single-photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI).

METHODS

From 37,298 patients in the REFINE SPECT registry, we identified 9221 patients with known coronary artery disease. Unsupervised machine learning was performed using clinical (23), acquisition (17), and image analysis (24) parameters from 4774 patients (internal cohort) and validated with 4447 patients (external cohort). Risk stratification for all-cause mortality was compared to stress total perfusion deficit (< 5%, 5-10%, ≥10%).

RESULTS

Three clusters were identified, with patients in Cluster 3 having a higher body mass index, more diabetes mellitus and hypertension, and less likely to be male, have dyslipidemia, or undergo exercise stress imaging (p < 0.001 for all). In the external cohort, during median follow-up of 2.6 [0.14, 3.3] years, all-cause mortality occurred in 312 patients (7%). Cluster analysis provided better risk stratification for all-cause mortality (Cluster 3: hazard ratio (HR) 5.9, 95% confidence interval (CI) 4.0, 8.6, p < 0.001; Cluster 2: HR 3.3, 95% CI 2.5, 4.5, p < 0.001; Cluster 1, reference) compared to stress total perfusion deficit (≥10%: HR 1.9, 95% CI 1.5, 2.5 p < 0.001; < 5%: reference).

CONCLUSIONS

Our unsupervised cluster analysis in patients with known CAD undergoing SPECT MPI identified three distinct phenotypic clusters and predicted all-cause mortality better than ischemia alone.

Selective Sinus Replacement for Aortic Root Aneurysm: Durable Approach in Selected Patients

BACKGROUND

Selective sinus replacement (SSR) allows a tailored repair approach in patients with sinus of Valsalva or asymmetric aortic root aneurysm. SSR avoids the need for coronary reimplantation for nondiseased sinuses and shortens operative time, although potential for late growth of retained sinuses exists. This study describes selection of patients and assesses operative outcomes and late root dimensions after SSR.

METHODS

From 2006 to 2020, 60 patients underwent SSR at a single referral institution. Mixed effect models were used to assess trajectory of postoperative growth of remaining sinuses, adjusting for age of the patient, valve morphology, and baseline root diameter.

RESULTS

Median age of the patients was 57 (interquartile range [IQR], 48-65) years. Twenty-four (40%) had a bicuspid aortic valve. Most patients (n = 55 [92%]) underwent single sinus replacement (n = 46 noncoronary, n = 9 right), whereas 5 (8%) underwent repair of both the right and noncoronary sinuses. Concomitant aortic valve replacement was performed in 15 patients (25%); aortic valve repair with internal ring annuloplasty or cusp plication was performed in 37 (62%). There was no operative death, stroke, renal failure, or respiratory failure. Median preoperative root diameter was 53 mm (IQR, 51-56 mm) vs 42 mm (IQR, 39-45 mm) at median imaging follow-up of 34 (IQR, 13-49) months. Rate of midterm root growth was 0.2 mm/y, and there were no late root reinterventions.

CONCLUSIONS

For patients with sinus of Valsalva or asymmetric root aneurysm, SSR is associated with excellent operative outcomes, and midterm follow-up suggests that the technique is durable. Longer term follow-up is needed to confirm continued stability of the aortic root.

Big Data in cardiac surgery: real world and perspectives

Big Data, and the derived analysis techniques, such as artificial intelligence and machine learning, have been considered a revolution in the modern practice of medicine. Big Data comes from multiple sources, encompassing electronic health records, clinical studies, imaging data, registries, administrative databases, patient-reported outcomes and OMICS profiles. The main objective of such analyses is to unveil hidden associations and patterns. In cardiac surgery, the main targets for the use of Big Data are the construction of predictive models to recognize patterns or associations better representing the individual risk or prognosis compared to classical surgical risk scores. The results of these studies contributed to kindle the interest for personalized medicine and contributed to recognize the limitations of randomized controlled trials in representing the real world. However, the main sources of evidence for guidelines and recommendations remain RCTs and meta-analysis. The extent of the revolution of Big Data and new analytical models in cardiac surgery is yet to be determined.

Neural operator learning of heterogeneous mechanobiological insults contributing to aortic aneurysms

Thoracic aortic aneurysm (TAA) is a localized dilatation of the aorta that can lead to life-threatening dissection or rupture. In vivo assessments of TAA progression are largely limited to measurements of aneurysm size and growth rate. There is promise, however, that computational modelling of the evolving biomechanics of the aorta could predict future geometry and properties from initiating mechanobiological insults. We present an integrated framework to train a deep operator network (DeepONet)-based surrogate model to identify TAA contributing factors using synthetic finite-element-based datasets. For training, we employ a constrained mixture model of aortic growth and remodelling to generate maps of local aortic dilatation and distensibility for multiple TAA risk factors. We evaluate the performance of the surrogate model for insult distributions varying from fusiform (analytically defined) to complex (randomly generated). We propose two frameworks, one trained on sparse information and one on full-field greyscale images, to gain insight into a preferred neural operator-based approach. We show that this continuous learning approach can predict the patient-specific insult profile associated with any given dilatation and distensibility map with high accuracy, particularly when based on full-field images. Our findings demonstrate the feasibility of applying DeepONet to support transfer learning of patient-specific inputs to predict TAA progression.

Ascending aorta mechanics and dimensions in aortopathy – from science to application

The ascending aorta has a unique microstructure and biomechanical properties that allow it to absorb energy during systole and return energy during diastole (Windkessel effect). Derangements in aortic architecture can result in changes to biomechanics and inefficiencies in function. Ultimately biomechanical failure may occur resulting in aortic dissection or rupture. By measuring aortic biomechanics with either in vivo or ex vivo methods, one may be able to predict tissue failure in patients with aortic disease such as aneurysms. An understanding of the biomechanical changes that lead to these tissue-level failures may help guide therapy, disease surveillance, surgical intervention, and aid in the development of new treatments for this deadly condition.

Artificial intelligence for the echocardiographic assessment of valvular heart disease

Developments in artificial intelligence (AI) have led to an explosion of studies exploring its application to cardiovascular medicine. Due to the need for training and expertise, one area where AI could be impactful would be in the diagnosis and management of valvular heart disease. This is because AI can be applied to the multitude of data generated from clinical assessments, imaging and biochemical testing during the care of the patient. In the area of valvular heart disease, the focus of AI has been on the echocardiographic assessment and phenotyping of patient populations to identify high-risk groups. AI can assist image acquisition, view identification for review, and segmentation of valve and cardiac structures for automated analysis. Using image recognition algorithms, aortic and mitral valve disease states have been directly detected from the images themselves. Measurements obtained during echocardiographic valvular assessment have been integrated with other clinical data to identify novel aortic valve disease subgroups and describe new predictors of aortic valve disease progression. In the future, AI could integrate echocardiographic parameters with other clinical data for precision medical management of patients with valvular heart disease.

Identification of hemodynamic biomarkers for bicuspid aortic valve induced aortic dilation using machine learning

Recent advances in medical imaging have confirmed the presence of altered hemodynamics in bicuspid aortic valve (BAV) patients. Therefore, there is a need for new hemodynamic biomarkers to refine disease monitoring and improve patient risk stratification. This research aims to analyze and extract multiple correlation patterns of hemodynamic parameters from 4D Flow MRI data and find which parameters allow an accurate classification between healthy volunteers (HV) and BAV patients with dilated and non-dilated ascending aorta using machine learning. Sixteen hemodynamic parameters were calculated in the ascending aorta (AAo) and aortic arch (AArch) at peak systole from 4D Flow MRI. We used sequential forward selection (SFS) and principal component analysis (PCA) as feature selection algorithms. Then, eleven machine-learning classifiers were implemented to separate HV and BAV patients (non- and dilated ascending aorta). Multiple correlation patterns from hemodynamic parameters were extracted using hierarchical clustering. The linear discriminant analysis and random forest are the best performing classifiers, using five hemodynamic parameters selected with SFS (velocity angle, forward velocity, vorticity, and backward velocity in AAo; and helicity density in AArch) a 96.31 ± 1.76% and 96.00 ± 0.83% accuracy, respectively. Hierarchical clustering revealed three groups of correlated features. According to this analysis, we observed that features selected by SFS have a better performance than those selected by PCA because the five selected parameters were distributed according to 3 different clusters. Based on the proposed method, we concluded that the feature selection method found five potentially hemodynamic biomarkers related to this disease.

Association of STS database variables with repair durability in ischemic mitral regurgitation using machine learning

BACKGROUND

Machine learning (ML) can identify nonintuitive clinical variable combinations that predict clinical outcomes. To assess the potential predictive contribution of standardized Society of Thoracic Surgeons (STS) Database clinical variables, we used ML to detect their association with repair durability in ischemic mitral regurgitation (IMR) patients in a single institution study.

METHODS

STS Database variables (n = 53) served as predictors of repair durability in ML modeling of 224 patients who underwent surgical revascularization and mitral valve repair for IMR. Follow-up mortality and echocardiography data allowed 1-year outcome analysis in 173 patients. Supervised ML analyses were performed using recurrence (≥3+ IMR) or death versus nonrecurrence (<3+ IMR) as the binary outcome classification.

RESULTS

We tested standard ML and deep learning algorithms, including support vector machines, logistic regression, and deep neural networks. Following training, final models were utilized to predict class labels for the patients in the test set, producing receiver operating characteristic (ROC) curves. The three models produced similar area under the curve (AUC), and predicted class labels with promising accuracy (AUC = 0.72-0.75).

CONCLUSIONS

Readily-available STS Database variables have potential to play a significant role in the development of ML models to direct durable surgical therapy in IMR patients.

The evolving role of artificial intelligence in cardiac image analysis

Research in artificial intelligence (AI) have progressed over the last decade. The field of cardiac imaging has seen significant developments using newly developed deep learning methods for automated image analysis and AI tools for disease detection and prognostication. This review article is aimed at those without special background in AI. We review AI concepts and we survey the growing contemporary applications of AI for image analysis in echocardiography, nuclear cardiology, cardiac computed tomography, cardiac magnetic resonance, and invasive angiography.

International Consensus Statement on Nomenclature and Classification of the Congenital Bicuspid Aortic Valve and Its Aortopathy, for Clinical, Surgical, Interventional and Research Purposes

This International Consensus Classification and Nomenclature for the congenital bicuspid aortic valve condition recognizes 3 types of bicuspid valves: 1. The fused type (right-left cusp fusion, right-non-coronary cusp fusion and left-non-coronary cusp fusion phenotypes); 2. The 2-sinus type (latero-lateral and antero-posterior phenotypes); and 3. The partial-fusion (forme fruste) type. The presence of raphe and the symmetry of the fused type phenotypes are critical aspects to describe. The International Consensus also recognizes 3 types of bicuspid valve-associated aortopathy: 1. The ascending phenotype; 2. The root phenotype; and 3. Extended phenotypes. ©  2021 Jointly between the RSNA, the European Association for Cardio-Thoracic Surgery, The Society of Thoracic Surgeons, and the American Association for Thoracic Surgery. The articles are identical except for minor stylistic and spelling differences in keeping with each journal's style. All rights reserved. Keywords: Bicuspid Aortic Valve, Aortopathy, Nomenclature, Classification.

Summary: international consensus statement on nomenclature and classification of the congenital bicuspid aortic valve and its aortopathy, for clinical, surgical, interventional and research purposes

This International evidence-based nomenclature and classification consensus on the congenital bicuspid aortic valve and its aortopathy recognizes 3 types of bicuspid aortic valve: 1. Fused type, with 3 phenotypes: right-left cusp fusion, right-non cusp fusion and left-non cusp fusion; 2. 2-sinus type with 2 phenotypes: Latero-lateral and antero-posterior; and 3. Partial-fusion or forme fruste. This consensus recognizes 3 bicuspid-aortopathy types: 1. Ascending phenotype; root phenotype; and 3. extended phenotypes.

International consensus statement on nomenclature and classification of the congenital bicuspid aortic valve and its aortopathy, for clinical, surgical, interventional and research purposes

This International Consensus Classification and Nomenclature for the congenital bicuspid aortic valve condition recognizes 3 types of bicuspid valves: 1. The fused type (right-left cusp fusion, right-non-coronary cusp fusion and left-non-coronary cusp fusion phenotypes); 2. The 2-sinus type (latero-lateral and antero-posterior phenotypes); and 3. The partial-fusion (forme fruste) type. The presence of raphe and the symmetry of the fused type phenotypes are critical aspects to describe. The International Consensus also recognizes 3 types of bicuspid valve-associated aortopathy: 1. The ascending phenotype; 2. The root phenotype; and 3. Extended phenotypes.

Summary: International consensus statement on nomenclature and classification of the congenital bicuspid aortic valve and its aortopathy, for clinical, surgical, interventional, and research purposes

This International evidence-based nomenclature and classification consensus on the congenital bicuspid aortic valve and its aortopathy recognizes 3 types of bicuspid aortic valve: 1. Fused type, with 3 phenotypes: right-left cusp fusion, right-non cusp fusion and left-non cusp fusion; 2. 2-sinus type with 2 phenotypes: Latero-lateral and antero-posterior; and 3. Partial-fusion or forme fruste. This consensus recognizes 3 bicuspid-aortopathy types: 1. Ascending phenotype; root phenotype; and 3. extended phenotypes.

International consensus statement on nomenclature and classification of the congenital bicuspid aortic valve and its aortopathy, for clinical, surgical, interventional and research purposes

This International Consensus Classification and Nomenclature for the congenital bicuspid aortic valve condition recognizes 3 types of bicuspid valves: 1. The fused type (right-left cusp fusion, right-non-coronary cusp fusion and left-non-coronary cusp fusion phenotypes); 2. The 2-sinus type (latero-lateral and antero-posterior phenotypes); and 3. The partial-fusion (forme fruste) type. The presence of raphe and the symmetry of the fused type phenotypes are critical aspects to describe. The International Consensus also recognizes 3 types of bicuspid valve-associated aortopathy: 1. The ascending phenotype; 2. The root phenotype; and 3. Extended phenotypes.

Summary: International Consensus Statement on Nomenclature and Classification of the Congenital Bicuspid Aortic Valve and Its Aortopathy, for Clinical, Surgical, Interventional and Research Purposes

This International evidence-based nomenclature and classification consensus on the congenital bicuspid aortic valve and its aortopathy recognizes 3 types of bicuspid aortic valve: 1. Fused type, with 3 phenotypes: right-left cusp fusion, right-non cusp fusion and left-non cusp fusion; 2. 2-sinus type with 2 phenotypes: Latero-lateral and antero-posterior; and 3. Partial-fusion or forme fruste. This consensus recognizes 3 bicuspid-aortopathy types: 1. Ascending phenotype; root phenotype; and 3. extended phenotypes.

International Consensus Statement on Nomenclature and Classification of the Congenital Bicuspid Aortic Valve and Its Aortopathy, for Clinical, Surgical, Interventional and Research Purposes

This International Consensus Classification and Nomenclature for the congenital bicuspid aortic valve condition recognizes 3 types of bicuspid valves: 1. The fused type (right-left cusp fusion, right-non-coronary cusp fusion and left-non-coronary cusp fusion phenotypes); 2. The 2-sinus type (latero-lateral and antero-posterior phenotypes); and 3. The partial-fusion (forme fruste) type. The presence of raphe and the symmetry of the fused type phenotypes are critical aspects to describe. The International Consensus also recognizes 3 types of bicuspid valve-associated aortopathy: 1. The ascending phenotype; 2. The root phenotype; and 3. Extended phenotypes.

Machine learning for subtype definition and risk prediction in heart failure, acute coronary syndromes and atrial fibrillation: systematic review of validity and clinical utility

BACKGROUND

Machine learning (ML) is increasingly used in research for subtype definition and risk prediction, particularly in cardiovascular diseases. No existing ML models are routinely used for cardiovascular disease management, and their phase of clinical utility is unknown, partly due to a lack of clear criteria. We evaluated ML for subtype definition and risk prediction in heart failure (HF), acute coronary syndromes (ACS) and atrial fibrillation (AF).

METHODS

For ML studies of subtype definition and risk prediction, we conducted a systematic review in HF, ACS and AF, using PubMed, MEDLINE and Web of Science from January 2000 until December 2019. By adapting published criteria for diagnostic and prognostic studies, we developed a seven-domain, ML-specific checklist.

RESULTS

Of 5918 studies identified, 97 were included. Across studies for subtype definition (n = 40) and risk prediction (n = 57), there was variation in data source, population size (median 606 and median 6769), clinical setting (outpatient, inpatient, different departments), number of covariates (median 19 and median 48) and ML methods. All studies were single disease, most were North American (n = 61/97) and only 14 studies combined definition and risk prediction. Subtype definition and risk prediction studies respectively had limitations in development (e.g. 15.0% and 78.9% of studies related to patient benefit; 15.0% and 15.8% had low patient selection bias), validation (12.5% and 5.3% externally validated) and impact (32.5% and 91.2% improved outcome prediction; no effectiveness or cost-effectiveness evaluations).

CONCLUSIONS

Studies of ML in HF, ACS and AF are limited by number and type of included covariates, ML methods, population size, country, clinical setting and focus on single diseases, not overlap or multimorbidity. Clinical utility and implementation rely on improvements in development, validation and impact, facilitated by simple checklists. We provide clear steps prior to safe implementation of machine learning in clinical practice for cardiovascular diseases and other disease areas.

Bicuspid aortic valve morphology and aortic valvular outflow jets: an experimental analysis using an MRI-compatible pulsatile flow circulation system

The characteristics of aortic valvular outflow jet affect aortopathy in the bicuspid aortic valve (BAV). This study aimed to elucidate the effects of BAV morphology on the aortic valvular outflow jets. Morphotype-specific valve-devising apparatuses were developed to create aortic valve models. A magnetic resonance imaging-compatible pulsatile flow circulation system was developed to quantify the outflow jet. The eccentricity and circulation values of the peak systolic jet were compared among tricuspid aortic valve (TAV), three asymmetric BAVs, and two symmetric BAVs. The results showed mean aortic flow and leakage did not differ among the five BAVs (six samples, each). Asymmetric BAVs demonstrated the eccentric outflow jets directed to the aortic wall facing the smaller leaflets. In the asymmetric BAV with the smaller leaflet facing the right-anterior, left-posterior, and left-anterior quadrants of the aorta, the outflow jets exclusively impinged on the outer curvature of the ascending aorta, proximal arch, and the supra-valvular aortic wall, respectively. Symmetric BAVs demonstrated mildly eccentric outflow jets that did not impinge on the aortic wall. The circulation values at peak systole increased in asymmetric BAVs. The bicuspid symmetry and the position of smaller leaflet were determinant factors of the characteristics of aortic valvular outflow jet.

Cardiac Imaging of Aortic Valve Area From 34 287 UK Biobank Participants Reveals Novel Genetic Associations and Shared Genetic Comorbidity With Multiple Disease Phenotypes

Background:

The aortic valve is an important determinant of cardiovascular physiology and anatomic location of common human diseases.

Methods:

From a sample of 34 287 white British ancestry participants, we estimated functional aortic valve area by planimetry from prospectively obtained cardiac magnetic resonance imaging sequences of the aortic valve. Aortic valve area measurements were submitted to genome-wide association testing, followed by polygenic risk scoring and phenome-wide screening, to identify genetic comorbidities.

Results:

A genome-wide association study of aortic valve area in these UK Biobank participants showed 3 significant associations, indexed by rs71190365 (chr13:50764607, DLEU1 , P =1.8×10 −9 ), rs35991305 (chr12:94191968, CRADD , P =3.4×10 −8 ), and chr17:45013271:C:T ( GOSR2 , P =5.6×10 −8 ). Replication on an independent set of 8145 unrelated European ancestry participants showed consistent effect sizes in all 3 loci, although rs35991305 did not meet nominal significance. We constructed a polygenic risk score for aortic valve area, which in a separate cohort of 311 728 individuals without imaging demonstrated that smaller aortic valve area is predictive of increased risk for aortic valve disease (odds ratio, 1.14; P =2.3×10 −6 ). After excluding subjects with a medical diagnosis of aortic valve stenosis (remaining n=308 683 individuals), phenome-wide association of >10 000 traits showed multiple links between the polygenic score for aortic valve disease and key health-related comorbidities involving the cardiovascular system and autoimmune disease. Genetic correlation analysis supports a shared genetic etiology with between aortic valve area and birth weight along with other cardiovascular conditions.

Conclusions:

These results illustrate the use of automated phenotyping of cardiac imaging data from the general population to investigate the genetic etiology of aortic valve disease, perform clinical prediction, and uncover new clinical and genetic correlates of cardiac anatomy.

Aortic stenosis exacerbates flow aberrations related to the bicuspid aortic valve fusion pattern and the aortopathy phenotype

OBJECTIVES

A bicuspid aortic valve (BAV) is characterized by variable phenotypic manifestations, as well as longitudinal evolution of valve dysfunction and ascending aorta dilatation. The present study investigated the impact of severe aortic stenosis (AS) on the flow patterns and wall shear stress (WSS) distribution in BAV patients with right-left (RL) and right-non-coronary (RN) cusp fusion types, and the study aimed to reveal whether aortic dysfunction could further alter intrinsic aortic haemodynamic aberrations generated by abnormal BAV cusp fusion patterns.

METHODS

Four-dimensional flow magnetic resonance imaging was performed in 120 BAV subjects and 20 tricuspid aortic valve controls. BAV patients were evenly categorized into 4 cohorts, including RL and RN BAV with no more than mild aortic dysfunction as well as RL and RN BAV-AS with isolated severe AS.

RESULTS

BAV subjects exhibited eccentric outflow jets resulting in regional WSS elevation at the right-anterior position of the ascending aorta in the RL group and the right-posterior location in the RN group (P < 0.005). The presence of severe AS resulted in accelerated outflow jets and more prominent flow and WSS eccentricity (P < 0.005) by marked helical (P = 0.014) and vortical flow formation (P < 0.005), as well as increased prevalence of tubular and transverse arch dilatation. The changes to the flow jet in BAV-AS subjects blurred the differences in peak flow velocity and WSS distribution between RL and RN BAV. Differences in the phenotypes of aortopathy were associated with changes in functional haemodynamic parameters such as flow displacement and WSS eccentricity.

CONCLUSIONS

Severe AS markedly exacerbated aortic flow aberrations in BAV patients and masked the existing distinct flow features deriving from RL and RN fusion types. Longitudinal studies are needed to investigate the evolution of ascending aortic dilatation relative to the interaction between intrinsic cusp fusion types and acquired severe valve dysfunction.

Machine Learning Outcome Prediction in Dilated Cardiomyopathy Using Regional Left Ventricular Multiparametric Strain

The clinical presentation of idiopathic dilated cardiomyopathy (IDCM) heart failure (HF) patients who will respond to medical therapy (responders) and those who will not (non-responders) is often similar. A machine learning (ML)-based clinical tool to identify responders would prevent unnecessary surgery, while targeting non-responders for early intervention. We used regional left ventricular (LV) contractile injury patterns in ML models to identify IDCM HF non-responders. MRI-based multiparametric strain analysis was performed in 178 test subjects (140 normal subjects and 38 IDCM patients), calculating longitudinal, circumferential, and radial strain over 18 LV sub-regions for inclusion in ML analyses. Patients were identified as responders based upon symptomatic and contractile improvement on medical therapy. We tested the predictive accuracy of support vector machines (SVM), logistic regression (LR), random forest (RF), and deep neural networks (DNN). The DNN model outperformed other models, predicting response to medical therapy with an area under the receiver operating characteristic curve (AUC) of 0.94. The top features were longitudinal strain in (1) basal: anterior, posterolateral and (2) mid: posterior, anterolateral, and anteroseptal sub-regions. Regional contractile injury patterns predict response to medical therapy in IDCM HF patients, and have potential application in ML-based HF patient care.

Surgical management of the aorta in BAV patients

Patients with a bicuspid aortic valve (BAV) frequently develop aneurysms of the aortic root and tubular ascending aorta. Aneurysms of the aortic arch, in the absence of concomitant aortopathies, are much less common. According to the 2018 American Association of Thoracic Surgery consensus guidelines on BAV-related aortopathy, prophylactic surgical aortic repair / replacement is recommended starting at a maximum aortic diameter of 50 mm in patients with risk factors. Concomitant aortic surgery is also recommended at an aortic diameter of 45 mm in those patients with other indications for cardiac surgery (most commonly aortic valve procedures). The ultimate goal of prophylactic aortic surgery is the prevention of aortic catastrophes, e.g. aortic rupture or acute aortic dissection, which are associated with high morbidity and mortality. The surgical technique used - in elective and emergency cases - depends on the involvement and nature of the aortic valve disease, as well as the extent of aortic aneurysm formation. The current review focusses on the surgical management of the aortic root, tubular ascending aorta, and proximal aortic arch in BAV patients. Despite the abovementioned recommendations, many BAV patients develop acute aortic syndromes below the recommended aortic diameter thresholds. Further research is therefore required in order to identify high-risk BAV subgroups that would benefit from earlier surgical repair.

Speaking a common language: Introduction to a standard terminology for the bicuspid aortic valve and its aortopathy

There is a growing need to develop a common language when referring to a frequent and heterogeneous condition such as the congenital bicuspid aortic valve and its aortopathy. The following short manuscript serves as an introduction to a standard terminology for the bicuspid aortic valve and its aortopathy.

Image-Based Cardiac Diagnosis With Machine Learning: A Review

Cardiac imaging plays an important role in the diagnosis of cardiovascular disease (CVD). Until now, its role has been limited to visual and quantitative assessment of cardiac structure and function. However, with the advent of big data and machine learning, new opportunities are emerging to build artificial intelligence tools that will directly assist the clinician in the diagnosis of CVDs. This paper presents a thorough review of recent works in this field and provide the reader with a detailed presentation of the machine learning methods that can be further exploited to enable more automated, precise and early diagnosis of most CVDs.

Clinical-pathological correlations of BAV and the attendant thoracic aortopathies. Part 1: Pluridisciplinary perspective on their hemodynamics and morphomechanics

Clinical BAV manifestations pertain to faulty aortic valve (AOV) function, the associated aortopathy, and other complications such as endocarditis, thrombosis and thromboembolism. BAV arises during valvulogenesis when 2 of the 3 leaflets/cusps of the AOV are fused together. Ensuing asymmetric BAV morphologies alter downstream ejection jet flow-trajectories. Based on BAV morphologies, ejection-flows exhibit different wall-impingement and scouring patterns in the proximal aorta, with excessive hydrodynamic wall-shear that correlates closely with mural vascular smooth muscle cell and extracellular matrix disruptions, revealing hemodynamic participation in the pathogenesis of BAV-associated aortopathies. Since the embryologic regions implicated in both BAV and aortopathies derive from neural crest cells and second heart field cells, there may exist a common multifactorial/polygenic embryological basis linking the abnormalities. The use of Electronic Health Records - encompassing integrated NGS variant panels and phenotypic data - in clinical studies could speed-up comprehensive understanding of multifactorial genetic-phenotypic and environmental factor interactions. This Survey represents the first in a 2-article pluridisciplinary work. Taken in toto, the series covers hemodynamic/morphomechanical and environmental (milieu intérieur) aspects in Part 1, and molecular, genetic and associated epigenetic aspects in Part 2. Together, Parts 1-2 should serve as a reference-milestone and driver for further pluridisciplinary research and its urgent translations in the clinical setting.

Computational modeling of bicuspid aortopathy: Towards personalized risk strategies

This paper describes current advances on the application of in-silico for the understanding of bicuspid aortopathy and future perspectives of this technology on routine clinical care. This includes the impact that artificial intelligence can provide to develop computer-based clinical decision support system and that wearable sensors can offer to remotely monitor high-risk bicuspid aortic valve (BAV) patients. First, we discussed the benefit of computational modeling by providing tangible examples of in-silico software products based on computational fluid-dynamic (CFD) and finite-element method (FEM) that are currently transforming the way we diagnose and treat cardiovascular diseases. Then, we presented recent findings on computational hemodynamic and structural mechanics of BAV to highlight the potentiality of patient-specific metrics (not-based on aortic size) to support the clinical-decision making process of BAV-associated aneurysms. Examples of BAV-related personalized healthcare solutions are illustrated.

Defining Phenotypes from Clinical Data to Drive Genomic Research

The rise in available longitudinal patient information in electronic health records (EHRs) and their coupling to DNA biobanks has resulted in a dramatic increase in genomic research using EHR data for phenotypic information. EHRs have the benefit of providing a deep and broad data source of health-related phenotypes, including drug response traits, expanding the phenome available to researchers for discovery. The earliest efforts at repurposing EHR data for research involved manual chart review of limited numbers of patients but now typically involve applications of rule-based and machine learning algorithms operating on sometimes huge corpora for both genome-wide and phenome-wide approaches. We highlight here the current methods, impact, challenges, and opportunities for repurposing clinical data to define patient phenotypes for genomics discovery. Use of EHR data has proven a powerful method for elucidation of genomic influences on diseases, traits, and drug-response phenotypes and will continue to have increasing applications in large cohort studies.