Smooth Muscle Cell Klf4 Expression Is Not Required for Phenotype Modulation or Aneurysm Formation in Marfan Syndrome Mice-Brief Report.

BACKGROUND: Smooth muscle cell (SMC) phenotypic reprogramming toward a mixed synthetic-proteolytic state is a central feature of aortic root aneurysm in Marfan syndrome (MFS). Previous work identified Klf4 as a potential mediator of SMC plasticity in MFS. METHODS: MFS (Fbn1C1041G/+) mouse strains with an inducible vascular SMC fluorescent reporter (MFSSMC) with or without SMC-specific deletion of Klf4 exons 2 to 3 (MFSSMC-Klf4Δ) were generated. Simultaneous SMC tracing and Klf4 loss-of-function (Klf4Δ mice) was induced at 6 weeks of age. Aneurysm growth was assessed via serial echocardiography (4-24 weeks). Twenty-four-week-old mice were assessed via histology, RNA in situ hybridization, and aortic single-cell RNA sequencing. RESULTS: MFS mice demonstrated progressive aortic root dilatation compared with control (WTSMC) mice regardless of Klf4 genotype (P<0.001), but there was no difference in aneurysm growth in MFSSMC-Klf4Δ versus MFSSMC (P=0.884). Efficient SMC Klf4 deletion was confirmed via lineage-stratified genotyping, RNA in situ hybridization, and immunohistochemistry. Single-cell RNA sequencing of traced SMCs revealed a highly similar pattern of phenotype modulation marked by loss of contractile markers (eg, Myh11, Cnn1) and heightened expression of matrix genes (eg, Col1a1, Fn1) between Klf4 genotypes. Pseudotemporal quantitation of SMC dedifferentiation confirmed that Klf4 deletion did not alter the global extent of phenotype modulation, but reduced expression of 23 genes during this phenotype transition in MFSSMC-Klf4Δmice, including multiple chondrogenic genes expressed by only the most severely dedifferentiated SMCs (eg, Cytl1, Tnfrsf11b). CONCLUSIONS: Klf4 is not required to initiate SMC phenotype modulation in MFS aneurysm but may exert regulatory control over chondrogenic genes expressed in highly dedifferentiated SMCs.

Embryologic Origin Influences Smooth Muscle Cell Phenotypic Modulation Signatures in Murine Marfan Syndrome Aortic Aneurysm.

BACKGROUND: Aortic root smooth muscle cells (SMC) develop from both the second heart field (SHF) and neural crest. Disparate responses to disease-causing Fbn1 variants by these lineages are proposed to promote focal aortic root aneurysm formation in Marfan syndrome (MFS), but lineage-stratified SMC analysis in vivo is lacking. METHODS: We generated SHF lineage-traced MFS mice and performed integrated multiomic (single-cell RNA and assay for transposase-accessible chromatin sequencing) analysis stratified by embryological origin. SMC subtypes were spatially identified via RNA in situ hybridization. Response to TWIST1 overexpression was determined via lentiviral transduction in human aortic SMCs. RESULTS: Lineage stratification enabled nuanced characterization of aortic root cells. We identified heightened SHF-derived SMC heterogeneity including a subset of Tnnt2 (cardiac troponin T)-expressing cells distinguished by altered proteoglycan expression. MFS aneurysm-associated SMC phenotypic modulation was identified in both SHF-traced and nontraced (neural crest-derived) SMCs; however, transcriptomic responses were distinct between lineages. SHF-derived modulated SMCs overexpressed collagen synthetic genes and small leucine-rich proteoglycans while nontraced SMCs activated chondrogenic genes. These modulated SMCs clustered focally in the aneurysmal aortic root at the region of SHF/neural crest lineage overlap. Integrated RNA-assay for transposase-accessible chromatin analysis identified enriched Twist1 and Smad2/3/4 complex binding motifs in SHF-derived modulated SMCs. TWIST1 overexpression promoted collagen and SLRP gene expression in vitro, suggesting TWIST1 may drive SHF-enriched collagen synthesis in MFS aneurysm. CONCLUSIONS: SMCs derived from both SHF and neural crest lineages undergo phenotypic modulation in MFS aneurysm but are defined by subtly distinct transcriptional responses. Enhanced TWIST1 transcription factor activity may contribute to enriched collagen synthetic pathways SHF-derived SMCs in MFS.

Single-Cell Transcriptomic Profiling of Vascular Smooth Muscle Cell Phenotype Modulation in Marfan Syndrome Aortic Aneurysm.

OBJECTIVE: To delineate temporal and spatial dynamics of vascular smooth muscle cell (SMC) transcriptomic changes during aortic aneurysm development in Marfan syndrome (MFS). Approach and Results: We performed single-cell RNA sequencing to study aortic root/ascending aneurysm tissue from Fbn1C1041G/+ (MFS) mice and healthy controls, identifying all aortic cell types. A distinct cluster of transcriptomically modulated SMCs (modSMCs) was identified in adult Fbn1C1041G/+ mouse aortic aneurysm tissue only. Comparison with atherosclerotic aortic data (ApoE-/- mice) revealed similar patterns of SMC modulation but identified an MFS-specific gene signature, including plasminogen activator inhibitor-1 (Serpine1) and Kruppel-like factor 4 (Klf4). We identified 481 differentially expressed genes between modSMC and SMC subsets; functional annotation highlighted extracellular matrix modulation, collagen synthesis, adhesion, and proliferation. Pseudotime trajectory analysis of Fbn1C1041G/+ SMC/modSMC transcriptomes identified genes activated differentially throughout the course of phenotype modulation. While modSMCs were not present in young Fbn1C1041G/+ mouse aortas despite small aortic aneurysm, multiple early modSMCs marker genes were enriched, suggesting activation of phenotype modulation. modSMCs were not found in nondilated adult Fbn1C1041G/+ descending thoracic aortas. Single-cell RNA sequencing from human MFS aortic root aneurysm tissue confirmed analogous SMC modulation in clinical disease. Enhanced expression of TGF-ß (transforming growth factor beta)-responsive genes correlated with SMC modulation in mouse and human data sets. CONCLUSIONS: Dynamic SMC phenotype modulation promotes extracellular matrix substrate modulation and aortic aneurysm progression in MFS. We characterize the disease-specific signature of modSMCs and provide temporal, transcriptomic context to the current understanding of the role TGF-ß plays in MFS aortopathy. Collectively, single-cell RNA sequencing implicates TGF-ß signaling and Klf4 overexpression as potential upstream drivers of SMC modulation.

Almanac - Retrieval-Augmented Language Models for Clinical Medicine.

BACKGROUND: Large language models (LLMs) have recently shown impressive zero-shot capabilities, whereby they can use auxiliary data, without the availability of task-specific training examples, to complete a variety of natural language tasks, such as summarization, dialogue generation, and question answering. However, despite many promising applications of LLMs in clinical medicine, adoption of these models has been limited by their tendency to generate incorrect and sometimes even harmful statements. METHODS: We tasked a panel of eight board-certified clinicians and two health care practitioners with evaluating Almanac, an LLM framework augmented with retrieval capabilities from curated medical resources for medical guideline and treatment recommendations. The panel compared responses from Almanac and standard LLMs (ChatGPT-4, Bing, and Bard) versus a novel data set of 314 clinical questions spanning nine medical specialties. RESULTS: Almanac showed a significant improvement in performance compared with the standard LLMs across axes of factuality, completeness, user preference, and adversarial safety. CONCLUSIONS: Our results show the potential for LLMs with access to domain-specific corpora to be effective in clinical decision-making. The findings also underscore the importance of carefully testing LLMs before deployment to mitigate their shortcomings. (Funded by the National Institutes of Health, National Heart, Lung, and Blood Institute.).

A cell and transcriptome atlas of the human arterial vasculature.

Vascular beds show different propensities for different vascular pathologies, yet mechanisms explaining these fundamental differences remain unknown. We sought to build a transcriptomic, cellular, and spatial atlas of human arterial cells across multiple different arterial segments to understand this phenomenon. We found significant cell type-specific segmental heterogeneity. Determinants of arterial identity are predominantly encoded in fibroblasts and smooth muscle cells, and their differentially expressed genes are particularly enriched for vascular disease-associated loci and genes. Adventitial fibroblast-specific heterogeneity in gene expression coincides with numerous vascular disease risk genes, suggesting a previously unrecognized role for this cell type in disease risk. Adult arterial cells from different segments cluster not by anatomical proximity but by embryonic origin, with differentially regulated genes heavily influenced by developmental master regulators. Non-coding transcriptomes across arterial cells contain extensive variation in lnc-RNAs expressed in cell type- and segment-specific patterns, rivaling heterogeneity in protein coding transcriptomes, and show enrichment for non-coding genetic signals for vascular diseases.

Machine Learning Multicenter Risk Model to Predict Right Ventricular Failure After Mechanical Circulatory Support: The STOP-RVF Score.

Importance: The existing models predicting right ventricular failure (RVF) after durable left ventricular assist device (LVAD) support might be limited, partly due to lack of external validation, marginal predictive power, and absence of intraoperative characteristics. Objective: To derive and validate a risk model to predict RVF after LVAD implantation. Design, Setting, and Participants: This was a hybrid prospective-retrospective multicenter cohort study conducted from April 2008 to July 2019 of patients with advanced heart failure (HF) requiring continuous-flow LVAD. The derivation cohort included patients enrolled at 5 institutions. The external validation cohort included patients enrolled at a sixth institution within the same period. Study data were analyzed October 2022 to August 2023. Exposures: Study participants underwent chronic continuous-flow LVAD support. Main Outcome and Measures: The primary outcome was RVF incidence, defined as the need for RV assist device or intravenous inotropes for greater than 14 days. Bootstrap imputation and adaptive least absolute shrinkage and selection operator variable selection techniques were used to derive a predictive model. An RVF risk calculator (STOP-RVF) was then developed and subsequently externally validated, which can provide personalized quantification of the risk for LVAD candidates. Its predictive accuracy was compared with previously published RVF scores. Results: The derivation cohort included 798 patients (mean [SE] age, 56.1 [13.2] years; 668 male [83.7%]). The external validation cohort included 327 patients. RVF developed in 193 of 798 patients (24.2%) in the derivation cohort and 107 of 327 patients (32.7%) in the validation cohort. Preimplant variables associated with postoperative RVF included nonischemic cardiomyopathy, intra-aortic balloon pump, microaxial percutaneous left ventricular assist device/venoarterial extracorporeal membrane oxygenation, LVAD configuration, Interagency Registry for Mechanically Assisted Circulatory Support profiles 1 to 2, right atrial/pulmonary capillary wedge pressure ratio, use of angiotensin-converting enzyme inhibitors, platelet count, and serum sodium, albumin, and creatinine levels. Inclusion of intraoperative characteristics did not improve model performance. The calculator achieved a C statistic of 0.75 (95% CI, 0.71-0.79) in the derivation cohort and 0.73 (95% CI, 0.67-0.80) in the validation cohort. Cumulative survival was higher in patients composing the low-risk group (estimated <20% RVF risk) compared with those in the higher-risk groups. The STOP-RVF risk calculator exhibited a significantly better performance than commonly used risk scores proposed by Kormos et al (C statistic, 0.58; 95% CI, 0.53-0.63) and Drakos et al (C statistic, 0.62; 95% CI, 0.57-0.67). Conclusions and Relevance: Implementing routine clinical data, this multicenter cohort study derived and validated the STOP-RVF calculator as a personalized risk assessment tool for the prediction of RVF and RVF-associated all-cause mortality.

Early clinical outcomes and molecular smooth muscle cell phenotyping using a prophylactic aortic arch replacement strategy in Loeys-Dietz syndrome.

OBJECTIVES: Patients with Loeys-Dietz syndrome demonstrate a heightened risk of distal thoracic aortic events after valve-sparing aortic root replacement. This study assesses the clinical risks and hemodynamic consequences of a prophylactic aortic arch replacement strategy in Loeys-Dietz syndrome and characterizes smooth muscle cell phenotype in Loeys-Dietz syndrome aneurysmal and normal-sized downstream aorta. METHODS: Patients with genetically confirmed Loeys-Dietz syndrome (n = 8) underwent prophylactic aortic arch replacement during valve-sparing aortic root replacement. Four-dimensional flow magnetic resonance imaging studies were performed in 4 patients with Loeys-Dietz syndrome (valve-sparing aortic root replacement + arch) and compared with patients with contemporary Marfan syndrome (valve-sparing aortic root replacement only, n = 5) and control patients (without aortopathy, n = 5). Aortic tissues from 4 patients with Loeys-Dietz syndrome and 2 organ donors were processed for anatomically segmented single-cell RNA sequencing and histologic assessment. RESULTS: Patients with Loeys-Dietz syndrome valve-sparing aortic root replacement + arch had no deaths, major morbidity, or aortic events in a median of 2 years follow-up. Four-dimensional magnetic resonance imaging demonstrated altered flow parameters in patients with postoperative aortopathy relative to controls, but no clear deleterious changes due to arch replacement. Integrated analysis of aortic single-cell RNA sequencing data (>49,000 cells) identified a continuum of abnormal smooth muscle cell phenotypic modulation in Loeys-Dietz syndrome defined by reduced contractility and enriched extracellular matrix synthesis, adhesion receptors, and transforming growth factor-beta signaling. These modulated smooth muscle cells populated the Loeys-Dietz syndrome tunica media with gradually reduced density from the overtly aneurysmal root to the nondilated arch. CONCLUSIONS: Patients with Loeys-Dietz syndrome demonstrated excellent surgical outcomes without overt downstream flow or shear stress disturbances after concomitant valve-sparing aortic root replacement + arch operations. Abnormal smooth muscle cell-mediated aortic remodeling occurs within the normal diameter, clinically at-risk Loeys-Dietz syndrome arch segment. These initial clinical and pathophysiologic findings support concomitant arch replacement in Loeys-Dietz syndrome.

Almanac: Retrieval-Augmented Language Models for Clinical Medicine.

Large-language models have recently demonstrated impressive zero-shot capabilities in a variety of natural language tasks such as summarization, dialogue generation, and question-answering. Despite many promising applications in clinical medicine, adoption of these models in real-world settings has been largely limited by their tendency to generate incorrect and sometimes even toxic statements. In this study, we develop Almanac, a large language model framework augmented with retrieval capabilities for medical guideline and treatment recommendations. Performance on a novel dataset of clinical scenarios (n= 130) evaluated by a panel of 5 board-certified and resident physicians demonstrates significant increases in factuality (mean of 18% at p-value < 0.05) across all specialties, with improvements in completeness and safety. Our results demonstrate the potential for large language models to be effective tools in the clinical decision-making process, while also emphasizing the importance of careful testing and deployment to mitigate their shortcomings.

Controlled Comparison of Simulated Hemodynamics Across Tricuspid and Bicuspid Aortic Valves.

Bicuspid aortic valve is the most common congenital heart defect, affecting 1-2% of the global population. Patients with bicuspid valves frequently develop dilation and aneurysms of the ascending aorta. Both hemodynamic and genetic factors are believed to contribute to dilation, yet the precise mechanism underlying this progression remains under debate. Controlled comparisons of hemodynamics in patients with different forms of bicuspid valve disease are challenging because of confounding factors, and simulations offer the opportunity for direct and systematic comparisons. Using fluid-structure interaction simulations, we simulate flows through multiple aortic valve models in a patient-specific geometry. The aortic geometry is based on a healthy patient with no known aortic or valvular disease, which allows us to isolate the hemodynamic consequences of changes to the valve alone. Four fully-passive, elastic model valves are studied: a tricuspid valve and bicuspid valves with fusion of the left- and right-, right- and non-, and non- and left-coronary cusps. The resulting tricuspid flow is relatively uniform, with little secondary or reverse flow, and little to no pressure gradient across the valve. The bicuspid cases show localized jets of forward flow, excess streamwise momentum, elevated secondary and reverse flow, and clinically significant levels of stenosis. Localized high flow rates correspond to locations of dilation observed in patients, with the location related to which valve cusps are fused. Thus, the simulations support the hypothesis that chronic exposure to high local flow contributes to localized dilation and aneurysm formation.

Computational Fluid Dynamics Simulations to Predict False Lumen Enlargement After Surgical Repair of Type-A Aortic Dissection.

We aim to use computational fluid dynamics to investigate the hemodynamic conditions that may predispose to false lumen enlargement in this patient population. Nine patients who received surgical repairs of their type-A aortic dissections between 2017-2018 were retrospectively identified. Multiple contrast-enhanced post-operative CT scans were used to construct 3D models of aortic geometries. Computational fluid dynamics simulations of the models were run on a high-performance computing cluster using SimVascular - an open-source simulation package. Physiological pulsatile flow conditions (4.9 L/min) were used at the aortic true lumen inlet, and physiological vascular resistances were applied at the distal vascular ends. Exploratory analyses showed no correlation between rate of false lumen growth and blood pressure, immediate post-op aortic diameter, or the number of fenestrations (p = 0.2). 1-year post-operative CT scans showed a median false lumen growth rate of 4.31 (3.66, 14.67) mm/year Median (Interquartile range) peak systolic, mid-diastolic, and late diastolic velocity magnitudes were 0.90 (1.40); 0.10 (0.16); and 0.06 (0.06) cm/s respectively. Spearman's ranked correlations between fenestration velocity and 1-year false lumen growth rates were found to be statistically significant: Velocity magnitude at peak systolic (p = 0.025; rho = 0.75), mid diastolic (p = 0.025; rho = 0.75) and late diastolic phases of the cardiac cycle (p = 0.006; rho = 0.85). We have shown that false lumen growth is strongly correlated to fenestration flow velocity, which has potential implications for post-operative surveillance and risk stratification.

A flexible electronic strain sensor for the real-time monitoring of tumor regression.

Assessing the efficacy of cancer therapeutics in mouse models is a critical step in treatment development. However, low-resolution measurement tools and small sample sizes make determining drug efficacy in vivo a difficult and time-intensive task. Here, we present a commercially scalable wearable electronic strain sensor that automates the in vivo testing of cancer therapeutics by continuously monitoring the micrometer-scale progression or regression of subcutaneously implanted tumors at the minute time scale. In two in vivo cancer mouse models, our sensor discerned differences in tumor volume dynamics between drug- and vehicle-treated tumors within 5 hours following therapy initiation. These short-term regression measurements were validated through histology, and caliper and bioluminescence measurements taken over weeklong treatment periods demonstrated the correlation with longer-term treatment response. We anticipate that real-time tumor regression datasets could help expedite and automate the process of screening cancer therapies in vivo.

A design-based model of the aortic valve for fluid-structure interaction.

This paper presents a new method for modeling the mechanics of the aortic valve and simulates its interaction with blood. As much as possible, the model construction is based on first principles, but such that the model is consistent with experimental observations. We require that tension in the leaflets must support a pressure, then derive a system of partial differential equations governing its mechanical equilibrium. The solution to these differential equations is referred to as the predicted loaded configuration; it includes the loaded leaflet geometry, fiber orientations and tensions needed to support the prescribed load. From this configuration, we derive a reference configuration and constitutive law. In fluid-structure interaction simulations with the immersed boundary method, the model seals reliably under physiological pressures and opens freely over multiple cardiac cycles. Further, model closure is robust to extreme hypo- and hypertensive pressures. Then, exploiting the unique features of this model construction, we conduct experiments on reference configurations, constitutive laws and gross morphology. These experiments suggest the following conclusions: (1) The loaded geometry, tensions and tangent moduli primarily determine model function. (2) Alterations to the reference configuration have little effect if the predicted loaded configuration is identical. (3) The leaflets must have sufficiently nonlinear material response to function over a variety of pressures. (4) Valve performance is highly sensitive to free edge length and leaflet height. These conclusions suggest appropriate gross morphology and material properties for the design of prosthetic aortic valves. In future studies, our aortic valve modeling framework can be used with patient-specific models of vascular or cardiac flow.

Use of patient-specific computational models for optimization of aortic insufficiency after implantation of left ventricular assist device.

OBJECTIVE: Aortic incompetence (AI) is observed to be accelerated in the continuous-flow left ventricular assist device (LVAD) population and is related to increased mortality. Using computational fluid dynamics (CFD), we investigated the hemodynamic conditions related to the orientation of the LVAD outflow in these patients. METHOD: We identified 10 patients with new aortic regurgitation, and 20 who did not, after LVAD implantation between 2009 and 2018. Three-dimensional models of patients' aortas were created from their computed tomography scans. The geometry of the LVAD outflow graft in relation to the aorta was quantified using azimuth angles (AA), polar angles (PAs), and distance from aortic root. The models were used to run CFD simulations, which calculated the pressures and wall shear stress (rWSS) exerted on the aortic root. RESULTS: The AA and PA were found to be similar. However, for combinations of high values of AA and low values of PA, there were no patients with AI. The distance from aortic root to the outflow graft was also smaller in patients who developed AI (3.39 ± 0.7 vs 4.07 ± 0.77 cm, P = .04). There was no significant difference in aortic root pressures in the 2 groups. The rWSS was greater in AI patients (4.60 ± 5.70 vs 2.37 ± 1.20 dyne/cm2, P < .001). Qualitatively, we observed a trend of greater perturbations, regions of high rWSS, and flow eddies in the AI group. CONCLUSIONS: Using CFD simulations, we demonstrated that patients who developed de novo AI have greater rWSS at the aortic root, and their outflow grafts were placed closer to the aortic roots than those patients without de novo AI.

Patient-Specific Computational Fluid Dynamics Reveal Localized Flow Patterns Predictive of Post-Left Ventricular Assist Device Aortic Incompetence.

BACKGROUND: Progressive aortic valve disease has remained a persistent cause of concern in patients with left ventricular assist devices. Aortic incompetence (AI) is a known predictor of both mortality and readmissions in this patient population and remains a challenging clinical problem. METHODS: Ten left ventricular assist device patients with de novo aortic regurgitation and 19 control left ventricular assist device patients were identified. Three-dimensional models of patients' aortas were created from their computed tomography scans, following which large-scale patient-specific computational fluid dynamics simulations were performed with physiologically accurate boundary conditions using the SimVascular flow solver. RESULTS: The spatial distributions of time-averaged wall shear stress and oscillatory shear index show no significant differences in the aortic root in patients with and without AI (mean difference, 0.67 dyne/cm2 [95% CI, -0.51 to 1.85]; P=0.23). Oscillatory shear index was also not significantly different between both groups of patients (mean difference, 0.03 [95% CI, -0.07 to 0.019]; P=0.22). The localized wall shear stress on the leaflet tips was significantly higher in the AI group than the non-AI group (1.62 versus 1.35 dyne/cm2; mean difference [95% CI, 0.15-0.39]; P<0.001), whereas oscillatory shear index was not significantly different between both groups (95% CI, -0.009 to 0.001; P=0.17). CONCLUSIONS: Computational fluid dynamics serves a unique role in studying the hemodynamic features in left ventricular assist device patients where 4-dimensional magnetic resonance imaging remains unfeasible. Contrary to the widely accepted notions of highly disturbed flow, in this study, we demonstrate that the aortic root is a region of relatively stagnant flow. We further identified localized hemodynamic features in the aortic root that challenge our understanding of how AI develops in this patient population.

Long-term survival in patients with post-LVAD right ventricular failure: multi-state modelling with competing outcomes of heart transplant.

BACKGROUND: Multicenter data on long term survival following LVAD implantation that make use of contemporary definitions of RV failure are limited. Furthermore, traditional survival analyses censor patients who receive a bridge to heart transplant. Here we compare the outcomes of LVAD patients who develop post-operative RV failure accounting for the transitional probability of receiving an interim heart transplantation. METHODS: We use a retrospective cohort of LVAD patients sourced from multiple high-volume centers based in the United States. Five- and ten-year survival accounting for transition probabilities of receiving a heart transplant were calculated using a multi-state Aalen Johansen survival model. RESULTS: Of the 897 patients included in the study, 238 (26.5%) developed post-operative RV failure at index hospitalization. At 10 years the probability of death with post-op RV failure was 79.28% vs 61.70% in patients without (HR 2.10; 95% CI 1.72 - 2.57; p = < .001). Though not significant, patients with RV failure were less likely to be bridged to a heart transplant (HR 0.87, p = .4). Once transplanted the risk of death between both patient groups remained equivalent; the probability of death after a heart transplant was 3.97% in those with post-operative RV failure shortly after index LVAD implant, as compared to 14.71% in those without. CONCLUSIONS AND RELEVANCE: Long-term durable mechanical circulatory support is associated with significantly higher mortality in patients who develop post-operative RV failure. Improving outcomes may necessitate expeditious bridge to heart transplant wherever appropriate, along with critical reassessment of organ allocation policies.

Predicting post-operative right ventricular failure using video-based deep learning.

Despite progressive improvements over the decades, the rich temporally resolved data in an echocardiogram remain underutilized. Human assessments reduce the complex patterns of cardiac wall motion, to a small list of measurements of heart function. All modern echocardiography artificial intelligence (AI) systems are similarly limited by design - automating measurements of the same reductionist metrics rather than utilizing the embedded wealth of data. This underutilization is most evident where clinical decision making is guided by subjective assessments of disease acuity. Predicting the likelihood of developing post-operative right ventricular failure (RV failure) in the setting of mechanical circulatory support is one such example. Here we describe a video AI system trained to predict post-operative RV failure using the full spatiotemporal density of information in pre-operative echocardiography. We achieve an AUC of 0.729, and show that this ML system significantly outperforms a team of human experts at the same task on independent evaluation.