An Artificial Placenta Experimental System in Sheep: Critical Issues for Successful Transition and Survival up to One Week.

OBJECTIVE: To describe the development of an artificial placenta (AP) system in sheep with learning curve and main bottlenecks to allow survival up to one week. METHODS: A total of 28 fetal sheep were transferred to an AP system at 110-115 days of gestation. The survival goal in the AP system was increased progressively in three consecutive study groups: 1-3 h (n = 8), 4-24 h (n = 10) and 48-168 h (n = 10). Duration of cannulation procedure, technical complications, pH, lactate, extracorporeal circulation (EC) circuit flows, fetal heart rate, and outcomes across experiments were compared. RESULTS: There was a progressive reduction in cannulation complications (75%, 50% and 0%, p = 0.004), improvement in initial pH (7.20 ± 0.06, 7.31 ± 0.04 and 7.33 ± 0.02, p = 0.161), and increment in the rate of experiments reaching survival goal (25%, 70% and 80%, p = 0.045). In the first two groups, cannulation accidents, air bubbles in the extracorporeal circuit, and thrombotic complications were the most common cause of AP system failure. CONCLUSIONS: Achieving a reproducible experimental setting for an AP system is extremely challenging, time- and effort-consuming, and requires a highly multidisciplinary team. As a result of the learning curve, we achieved reproducible transition and survival up to 7 days. Extended survival requires improving instrumentation with custom-designed devices.

Machine-learning-based exploration to identify remodeling patterns associated with death or heart-transplant in pediatric-dilated cardiomyopathy.

AIMS: We investigated left ventricular (LV) remodeling, mechanics, systolic and diastolic function, combined with clinical characteristics and heart-failure treatment in association to death or heart-transplant (DoT) in pediatric idiopathic, genetic or familial dilated cardiomyopathy (DCM), using interpretable machine-learning. METHODS AND RESULTS: Echocardiographic and clinical data from pediatric DCM and healthy controls were retrospectively analyzed. Machine-learning included whole cardiac-cycle regional longitudinal strain, aortic, mitral and pulmonary vein Doppler velocity traces, age and body surface area. We used unsupervised multiple kernel learning for data dimensionality reduction, positioning patients based on complex conglomerate information similarity. Subsequently, k-means identified groups with similar phenotypes. The proportion experiencing DoT was evaluated. Pheno-grouping identified 5 clinically distinct groups that were associated with differing proportions of DoT. All healthy controls clustered in groups 1 to 2, while all, but one, DCM subjects, clustered in groups 3 to 5; internally validating the algorithm. Cluster-5 comprised the oldest, most medicated patients, with combined systolic and diastolic heart-failure and highest proportion of DoT. Cluster-4 included the youngest patients characterized by severe LV remodeling and systolic dysfunction, but mild diastolic dysfunction and the second-highest proportion of DoT. Cluster-3 comprised young patients with moderate remodeling and systolic dysfunction, preserved apical strain, pronounced diastolic dysfunction and lowest proportion of DoT. CONCLUSIONS: Interpretable machine-learning, using full cardiac-cycle systolic and diastolic data, mechanics and clinical parameters, can potentially identify pediatric DCM patients at high-risk for DoT, and delineate mechanisms associated with risk. This may facilitate more precise prognostication and treatment of pediatric DCM.

Automated Pattern Recognition in Whole-Cardiac Cycle Echocardiographic Data: Capturing Functional Phenotypes with Machine Learning.

BACKGROUND: Echocardiography provides complex data on cardiac function that can be integrated into patterns of dysfunction related to the severity of cardiac disease. The aim of this study was to demonstrate the feasibility of applying machine learning (ML) to automate the integration of echocardiographic data from the whole cardiac cycle and to automatically recognize patterns in velocity profiles and deformation curves, allowing the identification of functional phenotypes. METHODS: Echocardiography was performed in 189 clinically managed patients with hypertension and 97 healthy individuals without hypertension. Speckle-tracking analysis of the left ventricle and atrium was performed, and deformation curves were extracted. Aortic and mitral blood pool pulsed-wave Doppler and mitral annular tissue pulsed-wave Doppler velocity profiles were obtained. These whole-cardiac cycle deformation and velocity curves were used as ML input. Unsupervised ML was used to create a representation of patients with hypertension in a virtual space in which patients are positioned on the basis of the similarity of their integrated whole-cardiac cycle echocardiography data. Regression methods were used to explore patterns of echocardiographic traces within this virtual ML-derived space, while clustering was used to define phenogroups. RESULTS: The algorithm captured different patterns in tissue and blood-pool velocity and deformation profiles and integrated the findings, yielding phenotypes related to normal cardiac function and others to advanced remodeling associated with pressure overload in hypertension. The addition of individuals without hypertension into the ML-derived space confirmed the interpretation of normal and remodeled phenotypes. CONCLUSIONS: ML-based pattern recognition is feasible from echocardiographic data obtained during the whole cardiac cycle. Automated algorithms can consistently capture patterns in velocity and deformation data and, on the basis of these patterns, group patients into interpretable, clinically comprehensive phenogroups that describe structural and functional remodeling. Automated pattern recognition may potentially aid interpretation of imaging data and diagnostic accuracy.

Machine Learning for Clinical Decision-Making: Challenges and Opportunities in Cardiovascular Imaging.

The use of machine learning (ML) approaches to target clinical problems is called to revolutionize clinical decision-making in cardiology. The success of these tools is dependent on the understanding of the intrinsic processes being used during the conventional pathway by which clinicians make decisions. In a parallelism with this pathway, ML can have an impact at four levels: for data acquisition, predominantly by extracting standardized, high-quality information with the smallest possible learning curve; for feature extraction, by discharging healthcare practitioners from performing tedious measurements on raw data; for interpretation, by digesting complex, heterogeneous data in order to augment the understanding of the patient status; and for decision support, by leveraging the previous steps to predict clinical outcomes, response to treatment or to recommend a specific intervention. This paper discusses the state-of-the-art, as well as the current clinical status and challenges associated with the two later tasks of interpretation and decision support, together with the challenges related to the learning process, the auditability/traceability, the system infrastructure and the integration within clinical processes in cardiovascular imaging.

Machine Learning in Fetal Cardiology: What to Expect.

In fetal cardiology, imaging (especially echocardiography) has demonstrated to help in the diagnosis and monitoring of fetuses with a compromised cardiovascular system potentially associated with several fetal conditions. Different ultrasound approaches are currently used to evaluate fetal cardiac structure and function, including conventional 2-D imaging and M-mode and tissue Doppler imaging among others. However, assessment of the fetal heart is still challenging mainly due to involuntary movements of the fetus, the small size of the heart, and the lack of expertise in fetal echocardiography of some sonographers. Therefore, the use of new technologies to improve the primary acquired images, to help extract measurements, or to aid in the diagnosis of cardiac abnormalities is of great importance for optimal assessment of the fetal heart. Machine leaning (ML) is a computer science discipline focused on teaching a computer to perform tasks with specific goals without explicitly programming the rules on how to perform this task. In this review we provide a brief overview on the potential of ML techniques to improve the evaluation of fetal cardiac function by optimizing image acquisition and quantification/segmentation, as well as aid in improving the prenatal diagnoses of fetal cardiac remodeling and abnormalities.

Analysis of nonstandardized stress echocardiography sequences using multiview dimensionality reduction.

Alternative stress echocardiography protocols such as handgrip exercise are potentially more favorable towards large-scale screening scenarios than those currently adopted in clinical practice. However, these are still underexplored because the maximal exercise levels are not easily quantified and regulated, requiring the analysis of the complete data sequences (thousands of images), which represents a challenging task for the clinician. We propose a framework for the analysis of these complex datasets, and illustrate it on a handgrip exercise dataset including complete acquisitions of 10 healthy controls and 5 ANT1 mutation patients (1377 cardiac cycles). The framework is based on an unsupervised formulation of multiple kernel learning, which is used to integrate information coming from myocardial velocity traces and heart rate to obtain a lower-dimensional representation of the data. Such simplified representation is then explored to discriminate groups of response and understand the underlying pathophysiological mechanisms. The analysis pipeline involves the reconstruction of population-specific signatures using multiscale kernel regression, and the clustering of subjects based on the trajectories defined by their projected sequences. The results confirm that the proposed framework is able to detect distinctive clusters of response and to provide insight regarding the underlying pathophysiology.

Machine learning-based phenogrouping in heart failure to identify responders to cardiac resynchronization therapy.

AIMS: We tested the hypothesis that a machine learning (ML) algorithm utilizing both complex echocardiographic data and clinical parameters could be used to phenogroup a heart failure (HF) cohort and identify patients with beneficial response to cardiac resynchronization therapy (CRT). METHODS AND RESULTS: We studied 1106 HF patients from the Multicenter Automatic Defibrillator Implantation Trial with Cardiac Resynchronization Therapy (MADIT-CRT) (left ventricular ejection fraction ≤ 30%, QRS ≥ 130 ms, New York Heart Association class ≤ II) randomized to CRT with a defibrillator (CRT-D, n = 677) or an implantable cardioverter defibrillator (ICD, n = 429). An unsupervised ML algorithm (Multiple Kernel Learning and K-means clustering) was used to categorize subjects by similarities in clinical parameters, and left ventricular volume and deformation traces at baseline into mutually exclusive groups. The treatment effect of CRT-D on the primary outcome (all-cause death or HF event) and on volume response was compared among these groups. Our analysis identified four phenogroups, significantly different in the majority of baseline clinical characteristics, biomarker values, measures of left and right ventricular structure and function and the primary outcome occurrence. Two phenogroups included a higher proportion of known clinical characteristics predictive of CRT response, and were associated with a substantially better treatment effect of CRT-D on the primary outcome [hazard ratio (HR) 0.35; 95% confidence interval (CI) 0.19-0.64; P = 0.0005 and HR 0.36; 95% CI 0.19-0.68; P = 0.001] than observed in the other groups (interaction P = 0.02). CONCLUSIONS: Our results serve as a proof-of-concept that, by integrating clinical parameters and full heart cycle imaging data, unsupervised ML can provide a clinically meaningful classification of a phenotypically heterogeneous HF cohort and might aid in optimizing the rate of responders to specific therapies.

Diagnosis of Heart Failure With Preserved Ejection Fraction: Machine Learning of Spatiotemporal Variations in Left Ventricular Deformation.

BACKGROUND: Stress testing helps diagnose heart failure with preserved ejection fraction (HFpEF), but there are no established criteria for quantifying left ventricular (LV) functional reserve. The aim of this study was to investigate whether comprehensive analysis of the timing and amplitude of LV long-axis myocardial motion and deformation throughout the cardiac cycle during rest and stress can provide more informative criteria than standard measurements. METHODS: Velocity, strain, and strain rate traces were measured from all 18 LV segments by echocardiographic myocardial velocity imaging at rest and during semisupine bicycle exercise in 100 subjects aged 69 ± 7 years, including patients with HFpEF and healthy, hypertensive, and breathless control subjects. A machine-learning algorithm, composed of an unsupervised statistical method and a supervised classifier, was used to model spatiotemporal patterns of the traces and compare the predicted labels with the clinical diagnoses. RESULTS: The learned strain rate parameters gave the highest accuracy for allocating subjects into the four groups (overall, 57%; for patients with HFpEF, 81%), and into two classes (asymptomatic vs symptomatic; area under the curve, 0.89; accuracy, 85%; sensitivity, 86%; specificity, 82%). Machine learning of strain rate, compared with standard measurements, gave the greatest improvement in accuracy for the two-class task (+23%, P < .0001), compared with +11% (P < .0001) using velocity and +4% (P < .05) using strain. Strain rate was also best at predicting 6-min walk distance as an independent reference criterion. CONCLUSIONS: Machine learning of spatiotemporal variations of LV strain rate during rest and exercise could be used to identify patients with HFpEF and to provide an objective basis for diagnostic classification.

Machine Learning Analysis of Left Ventricular Function to Characterize Heart Failure With Preserved Ejection Fraction.

BACKGROUND: Current diagnosis of heart failure with preserved ejection fraction (HFpEF) is suboptimal. We tested the hypothesis that comprehensive machine learning (ML) of left ventricular function at rest and exercise objectively captures differences between HFpEF and healthy subjects. METHODS AND RESULTS: One hundred fifty-six subjects aged >60 years (72 HFpEF+33 healthy for the initial analyses; 24 hypertensive+27 breathless for independent evaluation) underwent stress echocardiography, in the MEDIA study (Metabolic Road to Diastolic Heart Failure). Left ventricular long-axis myocardial velocity patterns were analyzed using an unsupervised ML algorithm that orders subjects according to their similarity, allowing exploration of the main trends in velocity patterns. ML identified a continuum from health to disease, including a transition zone associated to an uncertain diagnosis. Clinical validation was performed (1) to characterize the main trends in the patterns for each zone, which corresponded to known characteristics and new features of HFpEF; the ML-diagnostic zones differed for age, body mass index, 6-minute walk distance, B-type natriuretic peptide, and left ventricular mass index (P<0.05) and (2) to evaluate the consistency of the proposed groupings against diagnosis by current clinical criteria; correlation with diagnosis was good (κ, 72.6%; 95% confidence interval, 58.1-87.0); ML identified 6% of healthy controls as HFpEF. Blinded reinterpretation of imaging from subjects with discordant clinical and ML diagnoses revealed abnormalities not included in diagnostic criteria. The algorithm was applied independently to another 51 subjects, classifying 33% of hypertensive and 67% of breathless controls as mild-HFpEF. CONCLUSIONS: The analysis of left ventricular long-axis function on exercise by interpretable ML may improve the diagnosis and understanding of HFpEF.

Characterization of myocardial motion patterns by unsupervised multiple kernel learning.

We propose an independent objective method to characterize different patterns of functional responses to stress in the heart failure with preserved ejection fraction (HFPEF) syndrome by combining multiple temporally-aligned myocardial velocity traces at rest and during exercise, together with temporal information on the occurrence of cardiac events (valves openings/closures and atrial activation). The method builds upon multiple kernel learning, a machine learning technique that allows the combination of data of different nature and the reduction of their dimensionality towards a meaningful representation (output space). The learning process is kept unsupervised, to study the variability of the input traces without being conditioned by data labels. To enhance the physiological interpretation of the output space, the variability that it encodes is analyzed in the space of input signals after reconstructing the velocity traces via multiscale kernel regression. The methodology was applied to 2D sequences from a stress echocardiography protocol from 55 subjects (22 healthy, 19 HFPEF and 14 breathless subjects). The results confirm that characterization of the myocardial functional response to stress in the HFPEF syndrome may be improved by the joint analysis of multiple relevant features.