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.

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. 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. 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.

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.

Introduction: Adverse perinatal outcomes (APO) pose a significant global challenge, particularly in low- and middle-income countries (LMICs). This study aims to analyse two cohorts of high-risk pregnant women for APO to comprehend risk factors and improve prediction accuracy. Methods: We considered an LMIC and a high-income country (HIC) population to derive XGBoost classifiers to predict low birth weight (LBW) from a comprehensive set of maternal and fetal characteristics including socio-demographic, past and current pregnancy information, fetal biometry and fetoplacental Doppler measurements. Data were sourced from the FeDoC (Fetal Doppler Collaborative) study (Pakistan, LMIC) and theIMPACT (Improving Mothers for a Better PrenAtal Care Trial) study (Spain, HIC), and included 520 and 746 pregnancies assessed from 28 weeks gestation, respectively. The models were trained on varying subsets of the mentioned characteristics to evaluate their contribution in predicting LBW cases. For external validation, and to highlight potential differential risk factors for LBW, we investigated the generalisation of these models across cohorts. Models’ performance was evaluated through the area under the curve (AUC), and their interpretability was assessed using SHapley Additive exPlanations. Results: In FeDoC, Doppler variables demonstrated the highest value at predicting LBW compared with biometry and maternal clinical data (AUC_Doppler, 0.67; AUC_Clinical, 0.65; AUC_Biometry, 0.63), and its combination with maternal clinical data yielded the best prediction (AUC_{Clinical+Doppler}, 0.71). In IMPACT, fetal biometry emerged as the most predictive set (AUC_Biometry, 0.75; AUC_Doppler, 0.70; AUC_Clinical, 0.69) and its combination with Doppler and maternal clinical data achieved the highest accuracy (AUC_{Clinical+Biometry+Doppler}, 0.81). External validation consistently indicated that biometry combined with Doppler data yielded the best prediction. Conclusions: Our findings provide new insights into the predictive role of different clinical and ultrasound descriptors in two populations at high risk for APO, highlighting that different approaches are required for different populations. However, Doppler data improves prediction capabilities in both settings, underscoring the value of standardising ultrasound data acquisition, as practiced in HIC, to enhance LBW prediction in LMIC. This alignment contributes to bridging the health equity gap.