Improvement in Cardiac Morphology Demonstrated by Cardiac Magnetic Resonance Imaging and Echocardiography after Haploidentical Hematopoietic Cell Transplantation in Adults with Sickle Cell Disease.

Cardiopulmonary complications account for approximately 40% of deaths in patients with sickle cell disease (SCD). Diffuse myocardial fibrosis, elevated tricuspid regurgitant jet velocity (TRV) and iron overload are all associated with early mortality. Although HLA-matched sibling hematopoietic cell transplantation (HCT) offers a potential cure, less than 20% of patients have a suitable donor. Haploidentical HCT allows for an increased donor pool and has recently demonstrated improved safety and efficacy. Our group has reported improved cardiac morphology via echocardiography at 1 year after HCT. Here we describe the first use of cardiac magnetic resonance imaging (CMR), the gold standard for measuring volume, mass, and ventricular function, to evaluate changes in cardiac morphology post-HCT in adults with SCD. We analyzed baseline and 1-year data from 12 adults with SCD who underwent nonmyeloablative haploidentical peripheral blood HCT at the National Institutes of Health. Patients underwent noncontrast CMR at 3 T, echocardiography, and laboratory studies. At 1 year after HCT, patients showed marked improvement in cardiac chamber morphology by CMR, including left ventricular (LV) mass (70.2 to 60.1 g/m2; P = .02) and volume (114.5 to 90.6 mL/m2; P = .001). Furthermore, mean TRV normalized by 1 year, suggesting that HCT may offer a survival benefit. Fewer patients had pathologically prolonged native myocardial T1 times, an indirect marker of myocardial fibrosis at 1 year; these data showed a trend toward significance. In this small sample, CMR was very sensitive in detecting cardiac mass and volume changes after HCT and provided complementary information to echocardiography. Notably, post-HCT improvement in cardiac parameters can be attributed only in part to the resolution of anemia; further studies are needed to determine the roles of myocardial fibrosis reversal, improved blood flow, and survival impact after HCT for SCD.

Evaluation of an artificial intelligence-based system for echocardiographic estimation of right atrial pressure.

Current noninvasive estimation of right atrial pressure (RAP) by inferior vena cava (IVC) measurement during echocardiography may have significant inter-rater variability due to different levels of observers' experience. Therefore, there is a need to develop new approaches to decrease the variability of IVC analysis and RAP estimation. This study aims to develop a fully automated artificial intelligence (AI)-based system for automated IVC analysis and RAP estimation. We presented a multi-stage AI system to identify the IVC view, select good quality images, delineate the IVC region and quantify its thickness, enabling temporal tracking of its diameter and collapsibility changes. The automated system was trained and tested on expert manual IVC and RAP reference measurements obtained from 255 patients during routine clinical workflow. The performance was evaluated using Pearson correlation and Bland-Altman analysis for IVC values, as well as macro accuracy and chi-square test for RAP values. Our results show an excellent agreement (r=0.96) between automatically computed versus manually measured IVC values, and Bland-Altman analysis showed a small bias of [Formula: see text]0.33 mm. Further, there is an excellent agreement ([Formula: see text]) between automatically estimated versus manually derived RAP values with a macro accuracy of 0.85. The proposed AI-based system accurately quantified IVC diameter, collapsibility index, both are used for RAP estimation. This automated system could serve as a paradigm to perform IVC analysis in routine echocardiography and support various cardiac diagnostic applications.

Proceedings of the NHLBI Workshop on Artificial Intelligence in Cardiovascular Imaging: Translation to Patient Care.

Artificial intelligence (AI) promises to revolutionize many fields, but its clinical implementation in cardiovascular imaging is still rare despite increasing research. We sought to facilitate discussion across several fields and across the lifecycle of research, development, validation, and implementation to identify challenges and opportunities to further translation of AI in cardiovascular imaging. Furthermore, it seemed apparent that a multidisciplinary effort across institutions would be essential to overcome these challenges. This paper summarizes the proceedings of the National Heart, Lung, and Blood Institute-led workshop, creating consensus around needs and opportunities for institutions at several levels to support and advance research in this field and support future translation.

Supervised Exercise Training for Chronic Heart Failure With Preserved Ejection Fraction: A Scientific Statement From the American Heart Association and American College of Cardiology.

Heart failure with preserved ejection fraction (HFpEF) is one of the most common forms of heart failure; its prevalence is increasing, and outcomes are worsening. Affected patients often experience severe exertional dyspnea and debilitating fatigue, as well as poor quality of life, frequent hospitalizations, and a high mortality rate. Until recently, most pharmacological intervention trials for HFpEF yielded neutral primary outcomes. In contrast, trials of exercise-based interventions have consistently demonstrated large, significant, clinically meaningful improvements in symptoms, objectively determined exercise capacity, and usually quality of life. This success may be attributed, at least in part, to the pleiotropic effects of exercise, which may favorably affect the full range of abnormalities-peripheral vascular, skeletal muscle, and cardiovascular-that contribute to exercise intolerance in HFpEF. Accordingly, this scientific statement critically examines the currently available literature on the effects of exercise-based therapies for chronic stable HFpEF, potential mechanisms for improvement of exercise capacity and symptoms, and how these data compare with exercise therapy for other cardiovascular conditions. Specifically, data reviewed herein demonstrate a comparable or larger magnitude of improvement in exercise capacity from supervised exercise training in patients with chronic HFpEF compared with those with heart failure with reduced ejection fraction, although Medicare reimbursement is available only for the latter group. Finally, critical gaps in implementation of exercise-based therapies for patients with HFpEF, including exercise setting, training modalities, combinations with other strategies such as diet and medications, long-term adherence, incorporation of innovative and more accessible delivery methods, and management of recently hospitalized patients are highlighted to provide guidance for future research.

Supervised Exercise Training for Chronic Heart Failure With Preserved Ejection Fraction: A Scientific Statement From the American Heart Association and American College of Cardiology.

Heart failure with preserved ejection fraction (HFpEF) is one of the most common forms of heart failure; its prevalence is increasing, and outcomes are worsening. Affected patients often experience severe exertional dyspnea and debilitating fatigue, as well as poor quality of life, frequent hospitalizations, and a high mortality rate. Until recently, most pharmacological intervention trials for HFpEF yielded neutral primary outcomes. In contrast, trials of exercise-based interventions have consistently demonstrated large, significant, clinically meaningful improvements in symptoms, objectively determined exercise capacity, and usually quality of life. This success may be attributed, at least in part, to the pleiotropic effects of exercise, which may favorably affect the full range of abnormalities-peripheral vascular, skeletal muscle, and cardiovascular-that contribute to exercise intolerance in HFpEF. Accordingly, this scientific statement critically examines the currently available literature on the effects of exercise-based therapies for chronic stable HFpEF, potential mechanisms for improvement of exercise capacity and symptoms, and how these data compare with exercise therapy for other cardiovascular conditions. Specifically, data reviewed herein demonstrate a comparable or larger magnitude of improvement in exercise capacity from supervised exercise training in patients with chronic HFpEF compared with those with heart failure with reduced ejection fraction, although Medicare reimbursement is available only for the latter group. Finally, critical gaps in implementation of exercise-based therapies for patients with HFpEF, including exercise setting, training modalities, combinations with other strategies such as diet and medications, long-term adherence, incorporation of innovative and more accessible delivery methods, and management of recently hospitalized patients are highlighted to provide guidance for future research.

Effect of Torsemide vs Furosemide After Discharge on All-Cause Mortality in Patients Hospitalized With Heart Failure: The TRANSFORM-HF Randomized Clinical Trial.

Importance: Although furosemide is the most commonly used loop diuretic in patients with heart failure, some studies suggest a potential benefit for torsemide. Objective: To determine whether torsemide results in decreased mortality compared with furosemide among patients hospitalized for heart failure. Design, Setting, and Participants: TRANSFORM-HF was an open-label, pragmatic randomized trial that recruited 2859 participants hospitalized with heart failure (regardless of ejection fraction) at 60 hospitals in the United States. Recruitment occurred from June 2018 through March 2022, with follow-up through 30 months for death and 12 months for hospitalizations. The final date for follow-up data collection was July 2022. Interventions: Loop diuretic strategy of torsemide (n = 1431) or furosemide (n = 1428) with investigator-selected dosage. Main Outcomes and Measures: The primary outcome was all-cause mortality in a time-to-event analysis. There were 5 secondary outcomes with all-cause mortality or all-cause hospitalization and total hospitalizations assessed over 12 months being highest in the hierarchy. The prespecified primary hypothesis was that torsemide would reduce all-cause mortality by 20% compared with furosemide. Results: TRANSFORM-HF randomized 2859 participants with a median age of 65 years (IQR, 56-75), 36.9% were women, and 33.9% were Black. Over a median follow-up of 17.4 months, a total of 113 patients (53 [3.7%] in the torsemide group and 60 [4.2%] in the furosemide group) withdrew consent from the trial prior to completion. Death occurred in 373 of 1431 patients (26.1%) in the torsemide group and 374 of 1428 patients (26.2%) in the furosemide group (hazard ratio, 1.02 [95% CI, 0.89-1.18]). Over 12 months following randomization, all-cause mortality or all-cause hospitalization occurred in 677 patients (47.3%) in the torsemide group and 704 patients (49.3%) in the furosemide group (hazard ratio, 0.92 [95% CI, 0.83-1.02]). There were 940 total hospitalizations among 536 participants in the torsemide group and 987 total hospitalizations among 577 participants in the furosemide group (rate ratio, 0.94 [95% CI, 0.84-1.07]). Results were similar across prespecified subgroups, including among patients with reduced, mildly reduced, or preserved ejection fraction. Conclusions and Relevance: Among patients discharged after hospitalization for heart failure, torsemide compared with furosemide did not result in a significant difference in all-cause mortality over 12 months. However, interpretation of these findings is limited by loss to follow-up and participant crossover and nonadherence. Trial Registration: ClinicalTrials.gov Identifier: NCT03296813.

Increased Susceptibility for Adverse Reactions to Ultrasound Enhancing Agents in Sickle Cell Disease.

BACKGROUND: Pain-related adverse events (AEs) to ultrasound enhancing agents (UEAs) have been reported in patients with sickle cell disease (SCD). The aims of this study were to characterize the scope of these AEs in the SCD population and to investigate potential mechanisms on the basis of pathways involved in SCD vaso-occlusive crisis (VOC) and pain. METHODS: The prevalence and classification of AEs were analyzed from two clinical trials in which high-dose Definity infusions were used in patients with SCD (n = 55) or matched control subjects (n = 43) to study muscle or myocardial microvascular perfusion. Because complement (C') activation can trigger VOC in SCD, C' activation and surface adhesion of C' proteins on lipid UEAs were studied in vitro. C'-mediated UEA attachment to bone marrow immune cells was assessed using flow cytometry in a murine SCD model (Townes mice). Blood from patients receiving Definity was obtained to measure specific lysophospholipid metabolites of lipids in Definity thought to mediate SCD pain. RESULTS: Moderate or greater AEs, all of which were nociceptive (back or bone pain), occurred in one control subject and nine SCD subjects (2% vs 16%, P = .02). Patients with SCD who had AEs tended to have more severe manifestations of SCD. Three of the subjects with SCD had previously received Definity without complications. In patients with SCD, four AEs were classified as severe in intensity and as serious AEs on the basis of need for medical intervention. AEs were described to be similar to SCD-related pain, but there was no evidence for VOC, hemolysis, hypotension, or hypoxemia. At baseline, markers of C' activation were greater in patients with SCD than control subjects. However, after administration of lipid UEAs, SCD and control subjects were similar with regard to C' activation response, anaphylatoxin production, bone marrow microbubble retention, and production of lysophospholipids. There was a trend toward increased deposition of C3b and C3bi on lipid UEAs exposed to serum from patients with SCD. CONCLUSIONS: Patients with SCD are particularly susceptible to nociceptive AEs when given Definity at high doses. The mechanism for these AEs remains unclear but most are not related to the triggering of classic VOC.

Real-time echocardiography image analysis and quantification of cardiac indices.

Deep learning has a huge potential to transform echocardiography in clinical practice and point of care ultrasound testing by providing real-time analysis of cardiac structure and function. Automated echocardiography analysis is benefited through use of machine learning for tasks such as image quality assessment, view classification, cardiac region segmentation, and quantification of diagnostic indices. By taking advantage of high-performing deep neural networks, we propose a novel and eicient real-time system for echocardiography analysis and quantification. Our system uses a self-supervised modality-specific representation trained using a publicly available large-scale dataset. The trained representation is used to enhance the learning of target echo tasks with relatively small datasets. We also present a novel Trilateral Attention Network (TaNet) for real-time cardiac region segmentation. The proposed network uses a module for region localization and three lightweight pathways for encoding rich low-level, textural, and high-level features. Feature embeddings from these individual pathways are then aggregated for cardiac region segmentation. This network is fine-tuned using a joint loss function and training strategy. We extensively evaluate the proposed system and its components, which are echo view retrieval, cardiac segmentation, and quantification, using four echocardiography datasets. Our experimental results show a consistent improvement in the performance of echocardiography analysis tasks with enhanced computational eiciency that charts a path toward its adoption in clinical practice. Specifically, our results show superior real-time performance in retrieving good quality echo from individual cardiac view, segmenting cardiac chambers with complex overlaps, and extracting cardiac indices that highly agree with the experts' values. The source code of our implementation can be found in the project's GitHub page.

Transcatheter Mitral Cerclage Ventriculoplasty: From Bench to Bedside.

BACKGROUND: Transcatheter mitral valve repair is beneficial in patients with mitral regurgitation (MR), left ventricular dysfunction, and persistent symptoms despite maximally tolerated medical therapy. OBJECTIVES: The aim of this study was to evaluate the safety and feasibility of transcatheter mitral cerclage ventriculoplasty in patients with MR and either heart failure with reduced ejection fraction or preserved ejection fraction and in subjects with prior edge-to-edge repair but persistent or recurrent symptomatic MR. METHODS: The National Heart, Lung, and Blood Institute Division of Intramural Research Transcatheter Mitral Cerclage Ventriculoplasty Early Feasibility Study (NCT03929913) was an investigator-initiated prospective multicenter study. The primary endpoint was technical success measured at exit from the catheterization laboratory. Follow-up included heart failure quality-of-life assessments and serial imaging with echocardiography and cardiac computed tomography. RESULTS: Nineteen subjects consented and underwent cerclage, 63% with heart failure with reduced ejection fraction and 37% with heart failure with preserved ejection fraction, with ischemic cardiomyopathy in 26% and nonischemic cardiomyopathy in 74%. There were no procedural deaths, strokes, or transient ischemic attacks or other major cardiovascular adverse events. The primary endpoint was met in 17 subjects. Cerclage induced sustained reductions in mitral regurgitant volume (-41%) and effective orifice area (-33%) after a median of 337 days. Cerclage resulted in improvements in 6-minute walking distance (+78 m) and Kansas City Cardiomyopathy Questionnaire Overall Summary Score (+22 points) at 30 days that were maintained after a median of 265 days. New complete heart block developed in 6 of 17 subjects. Three deaths occurred on postprocedural days 79, 159, and 756, unrelated to cerclage. CONCLUSIONS: Transcatheter mitral cerclage ventriculoplasty resulted in significant and sustained improvements in mitral regurgitation and in heart failure quality-of-life assessments.

Proceedings From a National Heart, Lung, and Blood Institute and the Centers for Disease Control and Prevention Workshop to Control Hypertension.

Hypertension treatment and control prevent more cardiovascular events than management of other modifiable risk factors. Although the age-adjusted proportion of US adults with controlled blood pressure (BP) defined as <140/90 mm Hg, improved from 31.8% in 1999-2000 to 48.5% in 2007-2008, it remained stable through 2013-2014 and declined to 43.7% in 2017-2018. To address the rapid decline in hypertension control, the National Heart, Lung, and Blood Institute and the Division for Heart Disease and Stroke Prevention of the Centers for Disease Control and Prevention convened a virtual workshop with multidisciplinary national experts. Also, the group sought to identify opportunities to reverse the adverse trend and further improve hypertension control. The workshop immediately preceded the Surgeon General's Call to Action to Control Hypertension, which recognized a stagnation in progress with hypertension control. The presentations and discussions included potential reasons for the decline and challenges in hypertension control, possible "big ideas," and multisector approaches that could reverse the current trend while addressing knowledge gaps and research priorities. The broad set of "big ideas" was comprised of various activities that may improve hypertension control, including: interventions to engage patients, promotion of self-measured BP monitoring with clinical support, supporting team-based care, implementing telehealth, enhancing community-clinical linkages, advancing precision population health, developing tailored public health messaging, simplifying hypertension treatment, using process and outcomes quality metrics to foster accountability and efficiency, improving access to high-quality health care, addressing social determinants of health, supporting cardiovascular public health and research, and lowering financial barriers to hypertension control.

Ascertaining Death Events in a Pragmatic Clinical Trial: Insights From the TRANSFORM-HF Trial.

BACKGROUND: Death ascertainment can be challenging for pragmatic clinical trials that limit site follow-up activities to usual clinical care. METHODS AND RESULTS: We used blinded aggregate data from the ongoing ToRsemide comparison with furoSemide FOR Management of Heart Failure (TRANSFORM-HF) pragmatic clinical trial in patients with heart failure to evaluate the agreement between centralized call center death event identification and the United States National Death Index (NDI). Of 2284 total patients randomized through April 12, 2021, 1480 were randomized in 2018-2019 and 804 in 2020-2021. The call center identified 416 total death events (177 in 2018-2019 and 239 in 2020-2021). The NDI 2018-2019 final file identified 178 death events, 165 of which were also identified by the call center. The study's inter-rater reliability metric (Cohen's kappa coefficient, 0.920; 95% confidence interval, 0.889-0.951) demonstrates a high level of agreement. The time between a death event and its identification was less for the call center (median, 47 days; interquartile range, 11-103 days) than for the NDI (median, 270 days; interquartile range, 186-391 days). CONCLUSIONS: There is substantial agreement between deaths identified by a centralized call center and the NDI. However, the time between a death event and its identification is significantly less for the call center.

Leptin Attenuates Cardiac Hypertrophy in Patients With Generalized Lipodystrophy.

CONTEXT: Lipodystrophy syndromes are rare disorders of deficient adipose tissue, low leptin, and severe metabolic disease, affecting all adipose depots (generalized lipodystrophy, GLD) or only some (partial lipodystrophy, PLD). Left ventricular (LV) hypertrophy is common (especially in GLD); mechanisms may include hyperglycemia, dyslipidemia, or hyperinsulinemia. OBJECTIVE: Determine effects of recombinant leptin (metreleptin) on cardiac structure and function in lipodystrophy. METHODS: Open-label treatment study of 38 subjects (18 GLD, 20 PLD) at the National Institutes of Health before and after 1 (N = 27), and 3 to 5 years (N = 23) of metreleptin. Outcomes were echocardiograms, blood pressure (BP), triglycerides, A1c, and homeostasis model assessment of insulin resistance. RESULTS: In GLD, metreleptin lowered triglycerides (median [interquartile range] 740 [403-1239], 138 [88-196], 211 [136-558] mg/dL at baseline, 1 year, 3-5 years, P < .0001), A1c (9.5 ±â€…3.0, 6.5 ±â€…1.6, 6.5 ±â€…1.9%, P < .001), and HOMA-IR (34.1 [15.2-43.5], 8.7 [2.4-16.0], 8.9 [2.1-16.4], P < .001). Only HOMA-IR improved in PLD (P < .01). Systolic BP decreased in GLD but not PLD. Metreleptin improved cardiac parameters in patients with GLD, including reduced posterior wall thickness (9.8 ±â€…1.7, 9.1 ±â€…1.3, 8.3 ±â€…1.7 mm, P < .01), and LV mass (140.7 ±â€…45.9, 128.7 ±â€…37.9, 110.9 ±â€…29.1 g, P < .01), and increased septal e' velocity (8.6 ±â€…1.7, 10.0 ±â€…2.1, 10.7 ±â€…2.4 cm/s, P < .01). Changes remained significant after adjustment for BP. In GLD, multivariate models suggested that reduced posterior wall thickness and LV mass index correlated with reduced triglycerides and increased septal e' velocity correlated with reduced A1c. No changes in echocardiographic parameters were seen in PLD. CONCLUSION: Metreleptin attenuated cardiac hypertrophy and improved septal e' velocity in GLD, which may be mediated by reduced lipotoxicity and glucose toxicity. The applicability of these findings to leptin-sufficient populations remains to be determined.

Mechanistic insights into cell-free hemoglobin-induced injury during septic shock.

Cell-free hemoglobin (CFH) levels are elevated in septic shock and are higher in nonsurvivors. Whether CFH is only a marker of sepsis severity or is involved in pathogenesis is unknown. This study aimed to investigate whether CFH worsens sepsis-associated injuries and to determine potential mechanisms of harm. Fifty-one, 10-12 kg purpose-bred beagles were randomized to receive Staphylococcus aureus intrapulmonary challenges or saline followed by CFH infusions (oxyhemoglobin >80%) or placebo. Animals received antibiotics and intensive care support for 96 h. CFH significantly increased mean pulmonary arterial pressures and right ventricular afterload in both septic and nonseptic animals, effects that were significantly greater in nonsurvivors. These findings are consistent with CFH-associated nitric oxide (NO) scavenging and were associated with significantly depressed cardiac function, and worsened shock, lactate levels, metabolic acidosis, and multiorgan failure. In septic animals only, CFH administration significantly increased mean alveolar-arterial oxygenation gradients, also to a significantly greater degree in nonsurvivors. CFH-associated iron levels were significantly suppressed in infected animals, suggesting that bacterial iron uptake worsened pneumonia. Notably, cytokine levels were similar in survivors and nonsurvivors and were not predictive of outcome. In the absence and presence of infection, CFH infusions resulted in pulmonary hypertension, cardiogenic shock, and multiorgan failure, likely through NO scavenging. In the presence of infection alone, CFH infusions worsened oxygen exchange and lung injury, presumably by supplying iron that promoted bacterial growth. CFH elevation, a known consequence of clinical septic shock, adversely impacts sepsis outcomes through more than one mechanism, and is a biologically plausible, nonantibiotic, noncytokine target for therapeutic intervention.NEW & NOTEWORTHY Cell-free hemoglobin (CFH) elevations are a known consequence of clinical sepsis. Using a two-by-two factorial design and extensive physiological and biochemical evidence, we found a direct mechanism of injury related to nitric oxide scavenging leading to pulmonary hypertension increasing right heart afterload, depressed cardiac function, worsening circulatory failure, and death, as well as an indirect mechanism related to iron toxicity. These discoveries alter conventional thinking about septic shock pathogenesis and provide novel therapeutic approaches.

Pragmatic Design of Randomized Clinical Trials for Heart Failure: Rationale and Design of the TRANSFORM-HF Trial.

Randomized clinical trials are the foundation of evidence-based medicine and central to practice guidelines and patient care decisions. Nonetheless, randomized trials in heart failure (HF) populations have become increasingly difficult to conduct and are frequently associated with slow patient enrollment, highly selected populations, extensive data collection, and high costs. The traditional model for HF trials has become particularly difficult to execute in the United States, where challenges to site-based research have frequently led to modest U.S. representation in global trials. In this context, the TRANSFORM-HF (Torsemide Comparison with Furosemide for Management of Heart Failure) trial aims to overcome traditional trial challenges and compare the effects of torsemide versus furosemide among patients with HF in the United States. Loop diuretic agents are regularly used by most patients with HF and practice guidelines recommend optimal use of diuretic agents as key to a successful treatment strategy. Long-time clinical experience has contributed to dominant use of furosemide for loop diuretic therapy, although preclinical and small clinical studies suggest potential advantages of torsemide. However, due to the lack of appropriately powered clinical outcome studies, there is insufficient evidence to conclude that torsemide should be routinely recommended over furosemide. Given this gap in knowledge and the fundamental role of loop diuretic agents in HF care, the TRANSFORM-HF trial was designed as a prospective, randomized, event-driven, pragmatic, comparative-effectiveness study to definitively compare the effect of a treatment strategy of torsemide versus furosemide on long-term mortality, hospitalization, and patient-reported outcomes among patients with HF. (TRANSFORM-HF: ToRsemide compArisoN With furoSemide FORManagement of Heart Failure [TRANSFORM-HF]; NCT03296813).

A phenotypic risk score for predicting mortality in sickle cell disease.

Risk assessment for patients with sickle cell disease (SCD) remains challenging as it depends on an individual physician's experience and ability to integrate a variety of test results. We aimed to provide a new risk score that combines clinical, laboratory, and imaging data. In a prospective cohort of 600 adult patients with SCD, we assessed the relationship of 70 baseline covariates to all-cause mortality. Random survival forest and regularised Cox regression machine learning (ML) methods were used to select top predictors. Multivariable models and a risk score were developed and internally validated. Over a median follow-up of 4·3 years, 131 deaths were recorded. Multivariable models were developed using nine independent predictors of mortality: tricuspid regurgitant velocity, estimated right atrial pressure, mitral E velocity, left ventricular septal thickness, body mass index, blood urea nitrogen, alkaline phosphatase, heart rate and age. Our prognostic risk score had superior performance with a bias-corrected C-statistic of 0·763. Our model stratified patients into four groups with significantly different 4-year mortality rates (3%, 11%, 35% and 75% respectively). Using readily available variables from patients with SCD, we applied ML techniques to develop and validate a mortality risk scoring method that reflects the summation of cardiopulmonary, renal and liver end-organ damage. Trial Registration: ClinicalTrials.gov Identifier: NCT#00011648.

Trilateral Attention Network for Real-Time Cardiac Region Segmentation.

The accurate segmentation of cardiac images into anatomically meaningful regions is critical for the extraction of quantitative cardiac indices. The common pipeline for segmentation comprises regions of interest (ROIs) localization and segmentation stages that are independent of each other and typically performed using separate models. In this paper, we propose an end-to-end network, called Trilateral Attention Network (TaNet), for real-time region localization and segmentation. TaNet has a module for ROIs localization and three segmentation pathways: spatial pathway, handcrafted pathway, and context pathway. The localization module focuses segmentation attention on the desired region while learning the context relationship between different regions in the image. The localized regions are then sent to the three pathways for segmentation. The spatial pathway, which has regular convolutional kernels, is used to extract deep features at different levels of abstraction. The handcrafted pathway, which has hand-designed convolutional kernels, is used to extract a unique set of features complementary to the deep features. Finally, the context (or global) pathway is used to enlarge the receptive field. By jointly training TaNet for localization and segmentation, TaNet achieved superior performance, in terms of accuracy and speed, when evaluated on two echocardiography datasets for cardiac region segmentation.