RESUMEN
Objective. Physiological data are often low quality and thereby compromises the effectiveness of related health monitoring. The primary goal of this study is to develop a robust foundation model that can effectively handle low-quality issue in physiological data.Approach. We introduce SiamQuality, a self-supervised learning approach using convolutional neural networks (CNNs) as the backbone. SiamQuality learns to generate similar representations for both high and low quality photoplethysmography (PPG) signals that originate from similar physiological states. We leveraged a substantial dataset of PPG signals from hospitalized intensive care patients, comprised of over 36 million 30 s PPG pairs.Main results. After pre-training the SiamQuality model, it was fine-tuned and tested on six PPG downstream tasks focusing on cardiovascular monitoring. Notably, in tasks such as respiratory rate estimation and atrial fibrillation detection, the model's performance exceeded the state-of-the-art by 75% and 5%, respectively. The results highlight the effectiveness of our model across all evaluated tasks, demonstrating significant improvements, especially in applications for heart monitoring on wearable devices.Significance. This study underscores the potential of CNNs as a robust backbone for foundation models tailored to physiological data, emphasizing their capability to maintain performance despite variations in data quality. The success of the SiamQuality model in handling real-world, variable-quality data opens new avenues for the development of more reliable and efficient healthcare monitoring technologies.
Asunto(s)
Fotopletismografía , Procesamiento de Señales Asistido por Computador , Fotopletismografía/métodos , Humanos , Redes Neurales de la ComputaciónRESUMEN
PURPOSE: Myocardial infarction (MI) with subsequent inflammation is one of the most common heart conditions leading to progressive tissue damage. A reliable imaging marker to assess tissue viability after MI would help determine the risks and benefits of any intervention. In this study, we investigate whether a new mitochondria-targeted imaging agent, 18F-labeled 2'-deoxy-2'-18F-fluoro-9-ß-d-arabinofuranosylguanine ([18F]F-AraG), a positron emission tomography (PET) agent developed for imaging activated T cells, is suitable for cardiac imaging and to test the myocardial viability after MI. PROCEDURE: To test whether the myocardial [18F]-F-AraG signal is coming from cardiomyocytes or immune infiltrates, we compared cardiac signal in wild-type (WT) mice with that of T cell deficient Rag1 knockout (Rag1 KO) mice. We assessed the effect of dietary nucleotides on myocardial [18F]F-AraG uptake in normal heart by comparing [18F]F-AraG signals between mice fed with purified diet and those fed with purified diet supplemented with nucleotides. The myocardial viability was investigated in rodent model by imaging rat with [18F]F-AraG and 2-deoxy-2[18F]fluoro-D-glucose ([18F]FDG) before and after MI. All PET signals were quantified in terms of the percent injected dose per cc (%ID/cc). We also explored [18F]FDG signal variability and potential T cell infiltration into fibrotic area in the affected myocardium with H&E analysis. RESULTS: The difference in %ID/cc for Rag1 KO and WT mice was not significant (p = ns) indicating that the [18F]F-AraG signal in the myocardium was primarily coming from cardiomyocytes. No difference in myocardial uptake was observed between [18F]F-AraG signals in mice fed with purified diet and with purified diet supplemented with nucleotides (p = ns). The [18F]FDG signals showed wider variability at different time points. Noticeable [18F]F-AraG signals were observed in the affected MI regions. There were T cells in the fibrotic area in the H&E analysis, but they did not constitute the predominant infiltrates. CONCLUSIONS: Our preliminary preclinical data show that [18F]F-AraG accumulates in cardiomyocytes indicating that it may be suitable for cardiac imaging and to evaluate the myocardial viability after MI.
RESUMEN
Purpose: Myocardial infarction (MI) with subsequent inflammation is one of the most common heart conditions leading to progressive tissue damage. A reliable imaging marker to assess tissue viability after MI would help determine the risks and benefits of any intervention. In this study, we investigate whether a new mitochondria-targeted imaging agent, 18F-labeled 2'-deoxy-2'-18F-fluoro-9-ß-d-arabinofuranosylguanine ([18F]F-AraG), a positron emission tomography (PET) agent developed for imaging activated T cells, is suitable for cardiac imaging and to test the myocardial viability after MI. Procedure: To test whether the myocardial [18F]-F-AraG signal is coming from cardiomyocytes or immune infiltrates, we compared cardiac signal in wild-type (WT) mice with that of T cell deficient Rag1 knockout (Rag1 KO) mice. We assessed the effect of dietary nucleotides on myocardial [18F]F-AraG uptake in normal heart by comparing [18F]F-AraG signals between mice fed with purified diet and those fed with purified diet supplemented with nucleotides. The myocardial viability was investigated in rodent model by imaging rat with [18F]F-AraG and 2-deoxy-2[18F]fluoro-D-glucose ([18F]FDG) before and after MI. All PET signals were quantified in terms of the percent injected dose per cc (%ID/cc). We also explored [18F]FDG signal variability and potential T cell infiltration into fibrotic area in the affected myocardium with H&E analysis. Results: The difference in %ID/cc for Rag1 KO and WT mice was not significant (p = ns) indicating that the [18F]F-AraG signal in the myocardium was primarily coming from cardiomyocytes. No difference in myocardial uptake was observed between [18F]F-AraG signals in mice fed with purified diet and with purified diet supplemented with nucleotides (p = ns). The [18F]FDG signals showed wider variability at different time points. Noticeable [18F]F-AraG signals were observed in the affected MI regions. There were T cells in the fibrotic area in the H&E analysis, but they did not constitute the predominant infiltrates. Conclusions: Our preliminary preclinical data show that [18F]F-AraG accumulates in cardiomyocytes indicating that it may be suitable for cardiac imaging and to evaluate the myocardial viability after MI.
RESUMEN
Importance: Left atrial appendage elimination may improve catheter ablation outcomes for atrial fibrillation. Objective: To assess the safety and effectiveness of percutaneous left atrial appendage ligation adjunctive to catheter pulmonary vein isolation for nonparoxysmal atrial fibrillation. Design, Setting, and Participants: This multicenter, prospective, open-label, randomized clinical trial evaluated the safety and effectiveness of percutaneous left atrial appendage ligation adjunctive to planned pulmonary vein isolation for nonparoxysmal atrial fibrillation present for less than 3 years. Eligible patients were randomized in a 2:1 ratio to undergo left atrial appendage ligation and pulmonary vein isolation or pulmonary vein isolation alone. Use of a 2:1 randomization ratio was intended to provide more device experience and safety data. Patients were enrolled from October 2015 to December 2019 at 53 US sites, with the final follow-up visit on April 21, 2021. Interventions: Left atrial appendage ligation plus pulmonary vein isolation compared with pulmonary vein isolation alone. Main Outcomes and Measures: A bayesian adaptive analysis was used for primary end points. Primary effectiveness was freedom from documented atrial arrythmias of greater than 30 seconds duration 12 months after undergoing pulmonary vein isolation. Rhythm was assessed by Holter monitoring at 6 and 12 months after pulmonary vein isolation, symptomatic event monitoring, or any electrocardiographic tracing obtained through 12 months after pulmonary vein isolation. Primary safety was a composite of predefined serious adverse events compared with a prespecified 10% performance goal 30 days after the procedure. Left atrial appendage closure was evaluated through 12 months after pulmonary vein isolation. Results: Overall, 404 patients were randomized to undergo left atrial appendage ligation plus pulmonary vein isolation and 206 were randomized to undergo pulmonary vein isolation alone. Primary effectiveness was 64.3% with left atrial appendage ligation and pulmonary vein isolation and 59.9% with pulmonary vein isolation only (difference, 4.3% [bayesian 95% credible interval, -4.2% to 13.2%]; posterior superiority probability, 0.835), which did not meet the statistical criterion to establish superiority (0.977). Primary safety was met, with a 30-day serious adverse event rate of 3.4% (bayesian 95% credible interval, 2.0% to 5.0%; posterior probability, 1.0) which was less than the prespecified threshold of 10%. At 12 months after pulmonary vein isolation, complete left atrial appendage closure (0 mm residual communication) was observed in 84% of patients and less than or equal to 5 mm residual communication was observed in 99% of patients. Conclusions and Relevance: Percutaneous left atrial appendage ligation adjunctive to pulmonary vein isolation did not meet prespecified efficacy criteria for freedom from atrial arrhythmias at 12 months compared with pulmonary vein isolation alone for patients with nonparoxysmal atrial fibrillation, but met prespecified safety criteria and demonstrated high rates of closure at 12 months. Trial Registration: ClinicalTrials.gov Identifier: NCT02513797.
Asunto(s)
Apéndice Atrial , Fibrilación Atrial , Compuestos Organotiofosforados , Venas Pulmonares , Humanos , Apéndice Atrial/cirugía , Fibrilación Atrial/cirugía , Teorema de Bayes , Estudios Prospectivos , Venas Pulmonares/cirugía , Ablación por Catéter , CateterismoRESUMEN
Atrial fibrillation (AF) is a growing health problem that increases morbidity and mortality, and in most patients progresses to more advanced diseases over time. Recent research has examined the underlying mechanisms, risk factors, and progression of AF, leading to updated AF disease classification schemes. Although endocardial catheter ablation is effective for early-stage paroxysmal AF, it consistently achieves suboptimal outcomes in patients with advanced AF. Identification of the factors that lead to the increased risk of treatment failure in advanced AF has spurred the development and adoption of hybrid ablation therapies and collaborative heart care teams that result in higher long-term arrhythmia-free survival. Patients with non-paroxysmal AF, atrial remodeling, comorbidities, or AF otherwise deemed difficult to treat may find hybrid treatment to be the most effective option. Future research of hybrid therapies in advanced AF patient populations, including those with dual diagnoses, may provide further evidence establishing the safety and efficacy of hybrid endo-epicardial ablation as a first line treatment.
RESUMEN
The objective of this preclinical study was to evaluate the feasibility and safety of transcatheter endocardial alginate hydrogel injection (TEAi) in a large animal model, utilizing the high-stiffness XDROP® alginate hydrogel in combination with the dedicated EndoWings® catheter-based system. All swine (n = 9) successfully underwent TEAi without complications. Acute results from a subset of animals (n = 5) demonstrated the ability of the catheter to access a wide range of endomyocardial areas and achieve consecutive circumferential hydrogel distribution patterns within the mid-left ventricular wall. Histological examinations at 6 months (n = 4) demonstrated that the XDROP® remained localized within the cardiac tissue. In addition, serial echocardiographic imaging showed that XDROP® had no adverse impacts on LV systolic and diastolic functions. In conclusion, this innovative combination technology has the potential to overcome the translational barriers related to alginate hydrogel delivery to the myocardium.
RESUMEN
Atrial fibrillation (AF) is a common cardiac arrhythmia with serious health consequences if not detected and treated early. Detecting AF using wearable devices with photoplethysmography (PPG) sensors and deep neural networks has demonstrated some success using proprietary algorithms in commercial solutions. However, to improve continuous AF detection in ambulatory settings towards a population-wide screening use case, we face several challenges, one of which is the lack of large-scale labeled training data. To address this challenge, we propose to leverage AF alarms from bedside patient monitors to label concurrent PPG signals, resulting in the largest PPG-AF dataset so far (8.5 M 30-second records from 24,100 patients) and demonstrating a practical approach to build large labeled PPG datasets. Furthermore, we recognize that the AF labels thus obtained contain errors because of false AF alarms generated from imperfect built-in algorithms from bedside monitors. Dealing with label noise with unknown distribution characteristics in this case requires advanced algorithms. We, therefore, introduce and open-source a novel loss design, the cluster membership consistency (CMC) loss, to mitigate label errors. By comparing CMC with state-of-the-art methods selected from a noisy label competition, we demonstrate its superiority in handling label noise in PPG data, resilience to poor-quality signals, and computational efficiency.
Asunto(s)
Algoritmos , Fibrilación Atrial , Fotopletismografía , Procesamiento de Señales Asistido por Computador , Humanos , Fotopletismografía/métodos , Fibrilación Atrial/fisiopatología , Fibrilación Atrial/diagnóstico , Alarmas Clínicas , Aprendizaje Automático , Dispositivos Electrónicos VestiblesRESUMEN
BACKGROUND: Alcohol consumption is associated with a higher increased risk of atrial fibrillation (AF), but the acute effects on cardiac electrophysiology in humans remain poorly understood. The HOw ALcohol InDuces Atrial TachYarrhythmias (HOLIDAY) Trial revealed that alcohol shortened pulmonary vein atrial effective refractory periods, but more global electrophysiologic changes gleaned from the surface ECG have not yet been reported. METHODS: This was a secondary analysis of the HOLIDAY Trial. During AF ablation procedures, 100 adults were randomized to intravenous alcohol titrated to 0.08% blood alcohol concentration versus a volume and osmolarity-matched, masked, placebo. Intervals measured from 12lead ECGs were compared between pre infusion and at infusion steady state (20 min). RESULTS: The average age was 60 years and 11% were female. No significant differences in the P-wave duration, PR, QRS or QT intervals, were present between alcohol and placebo arms. However, infusion of alcohol was associated with a statistically significant relative shortening of the JT interval (r: -14.73, p = 0.048) after multivariable adjustment. CONCLUSION: Acute exposure to alcohol was associated with a relative reduction in the JT interval, reflecting shortening of ventricular repolarization. These acute changes may reflect a more global shortening of refractoriness, suggesting immediate proarrhythmic effects pertinent to the atria and ventricles.
Asunto(s)
Fibrilación Atrial , Electrocardiografía , Adulto , Femenino , Humanos , Masculino , Persona de Mediana Edad , Nivel de Alcohol en Sangre , Atrios Cardíacos , Ensayos Clínicos Controlados Aleatorios como AsuntoRESUMEN
Left atrial appendage occlusion affects systemic coagulation parameters, leading to additional patient-related benefits. The aim of this study was to investigate the differences in coagulation factor changes 6 months after epicardial left atrial appendage occlusion in patients with different LAA morphometries. This is the first study to analyze these relationships in detail. A prospective study of 22 consecutive patients was performed. Plasminogen, fibrinogen, tPA concentration, PAI-1, TAFI and computed tomography angiograms were performed. Patients were divided into subgroups based on left atrial appendage body and orifice diameter enlargement. The results of blood tests at baseline and six-month follow-up were compared. In a population with normal LAA body size and normal orifice diameter size, a significant decrease in analyzed clotting factors was observed between baseline and follow-up for all parameters except plasminogen. A significant decrease between baseline and follow-up was observed with enlarged LAA body size in all parameters except TAFI, in which it was insignificant and plasminogen, in which a significant increase was observed. Occlusion of the left atrial appendage is beneficial for systemic coagulation. Patients with a small LAA may benefit more from LAA closure in terms of stabilizing their coagulation factors associated with potential thromboembolic events in the future.
RESUMEN
Abstract We report the case of a 60-year-old patient who underwent orthotopic heart transplant 14 years earlier. Routine echocardiography showed giant masses in the left atrium. There were no symptoms or thromboembolic events in the past. Magnetic resonance imaging study revealed very enlarged left atrium (8.7 × 10.6 cm) occupied by irregular smooth mass (7 × 5 × 6.1 cm) with a stalk that was attached to the posterior left atrial wall in the area of graft suture lines. Intraoperative examination revealed a massive thrombus (12 × 10 cm) that filled almost the entire left atrial area.