Publications by authors named "Sounok Sen"

Article Synopsis
  • AI-ECG can effectively detect hypertrophic cardiomyopathy (HCM) and track treatment responses using 12-lead ECGs.
  • The study analyzed data from patients undergoing surgical reduction and those receiving mavacamten at multiple healthcare centers, finding no improvement in HCM scores after surgery, but a significant decrease in scores among patients taking mavacamten.
  • This highlights AI-ECG's potential for ongoing monitoring of heart condition improvements following medication rather than surgical interventions.
View Article and Find Full Text PDF

Background: The lack of automated tools for measuring care quality limits the implementation of a national program to assess guideline-directed care in heart failure with reduced ejection fraction (HFrEF).

Objectives: The authors aimed to automate the identification of patients with HFrEF at hospital discharge, an opportunity to evaluate and improve the quality of care.

Methods: The authors developed a novel deep-learning language model for identifying patients with HFrEF from discharge summaries of hospitalizations with heart failure at Yale New Haven Hospital during 2015 to 2019.

View Article and Find Full Text PDF
Article Synopsis
  • The study investigates the link between cognitive function and cardiovascular disease (CVD) in older adults, focusing on how different types of CVD and aging affect this relationship.
  • An analysis of over 3,100 adults aged 60 and older revealed that those with CVD had significantly lower scores on various cognitive tests compared to those without CVD, indicating impaired cognitive performance.
  • Specifically, older adults with congestive heart failure and those aged 80 and above demonstrated the most notable cognitive deficits, especially on the Digit Symbol Substitution Test (DSST).
View Article and Find Full Text PDF

Background: Observational data suggest that the subset of patients with heart failure related CS (HF-CS) now predominate critical care admissions for CS. There are no dedicated HF-CS randomised control trials completed to date which reliably inform clinical practice or clinical guidelines. We sought to identify aspects of HF-CS care where both consensus and uncertainty may exist to guide clinical practice and future clinical trial design, with a specific focus on HF-CS due to acute decompensated chronic HF.

View Article and Find Full Text PDF
Article Synopsis
  • - The study aims to assess the effectiveness of an AI-based algorithm in detecting structural heart disease (SHD) using portable ECG devices, focusing on its real-world application compared to established echocardiogram methods.
  • - It will involve enrolling 585 patients who will undergo a single-lead ECG with both an Apple Watch and another portable device during their echocardiogram routine visits, linking their ECG data to electronic health records for analysis.
  • - Ethical considerations include secure access to patient data and maintaining confidentiality, ensuring that the study adheres to strict guidelines for handling protected health information.
View Article and Find Full Text PDF

There is a critical need for biomarkers of acute cellular rejection (ACR) in organ transplantation. We hypothesized that ACR leads to changes in donor-reactive T cell small extracellular vesicle (sEV) profiles in transplant recipient circulation that match the kinetics of alloreactive T cell activation. In rodent heart transplantation, circulating T cell sEV quantities (P < .

View Article and Find Full Text PDF
Article Synopsis
  • Artificial intelligence-enhanced electrocardiography (AI-ECG) can detect hypertrophic cardiomyopathy (HCM) and monitor treatment responses through ECGs, presenting a modern alternative to surgical options like septal reduction therapy (SRT) and oral treatments like mavacamten.
  • A study involving patients from multiple health systems showed no significant change in AI-ECG HCM scores after SRT, indicating that this surgical method may not effectively improve HCM scores.
  • In contrast, patients on mavacamten therapy showed a significant decrease in their AI-ECG scores over a median follow-up period, suggesting that AI-ECG could be useful for regularly tracking improvements in HCM
View Article and Find Full Text PDF
Article Synopsis
  • Hypertrophic cardiomyopathy (HCM) affects 1 in 200 people and is a major cause of sudden cardiac death in young adults, but current detection methods using ECG data can be limited due to accessibility issues.
  • A new deep learning model has been developed to detect HCM using images of 12-lead ECGs, validated with large datasets from clinical settings and the UK Biobank for effectiveness.
  • The model showed very high accuracy (AUROC of 0.96 for internal and 0.94 for external validation) and can significantly increase the odds of confirming HCM diagnosis, marking it as a promising avenue for automated and efficient HCM screening.
View Article and Find Full Text PDF

Background: Although clinical studies have demonstrated the association between a single N-terminal pro-B-type natriuretic peptide (NT-proBNP) measurement and clinical outcomes in chronic heart failure, the biomarker is frequently measured serially in clinical practice.

Objectives: The aim of this study was to determine the added prognostic value of repeated NT-proBNP measurements compared with single measurements alone for chronic heart failure patients.

Methods: In the GUIDE-IT (Guiding Evidence Based Therapy Using Biomarker Intensified Treatment in Heart Failure) study, 894 study participants with chronic heart failure with reduced ejection fraction were enrolled at 45 outpatient sites in the United States and Canada.

View Article and Find Full Text PDF
Article Synopsis
  • The study addresses the challenge of assessing care quality for heart failure patients, specifically those with reduced ejection fraction (HFrEF), due to a lack of automated measurement tools at hospital discharge.
  • Researchers developed a deep learning language model that identifies HFrEF patients from discharge summaries using a semi-supervised approach, validated with hospital data from Yale New Haven Hospital and external institutions.
  • The model demonstrated high performance, achieving AUROC values of up to 0.97 in detecting HFrEF, effectively improving the identification of these patients and potentially enhancing care quality.
View Article and Find Full Text PDF

Heart failure (HF) imposes a large and growing burden on the population, with a prevalence that is projected to increase to more than 8 million adults by 2030. The high risk of morbidity and mortality associated with HF is further exacerbated by the frequent presence of comorbidities. The coexistence of HF and comorbid conditions can result in emergency department visits and hospitalizations that not only affect patients and their families but also pose a growing economic burden on health care systems.

View Article and Find Full Text PDF
Article Synopsis
  • * Conducted as a randomized clinical trial, the results showed that while there was no significant overall increase in GDMT prescriptions, patients receiving alerts were more likely to be prescribed mineralocorticoid receptor antagonists (MRAs).
  • * Only 11.2% of patients were prescribed all four main types of GDMT at discharge, suggesting that improvements in the alert system and other strategies may be needed to increase overall prescription rates.
View Article and Find Full Text PDF
Article Synopsis
  • Heart transplant recipients with previous cytomegalovirus exposure were analyzed to determine the effectiveness of two CMV prevention strategies: universal prophylaxis (UP) and preemptive therapy (PET).
  • A study of 563 CMV R+ heart transplant recipients revealed that PET significantly increased the risk of CMV infection and related hospitalizations compared to UP, along with a higher incidence of acute cellular rejection.
  • Although UP led to more cases of leukopenia, it was associated with better overall outcomes for graft health and reduced risks related to CMV compared to PET in these patients.
View Article and Find Full Text PDF

There is limited large, national data investigating the prevalence, characteristics, and outcomes of cardiac arrest (CA) in patients hospitalized for heart failure (HF). The goal of this study was to examine the characteristics, trends, and outcomes of HF hospitalizations complicated by in-hospital CA. We used the National Inpatient Sample to identify all primary HF admissions from 2016 to 2019.

View Article and Find Full Text PDF

Background: T2D is an increasingly common disease that is associated with worse outcomes in patients with heart failure. Despite this, no contemporary study has assessed its impact on heart transplantation outcomes. This paper examines the demographics and outcomes of patients with type 2 diabetes (T2D) undergoing heart transplantation.

View Article and Find Full Text PDF

Acute Heart failure (AHF) is among the most frequent causes of hospitalization in the United States, contributing to substantial health care costs, morbidity, and mortality. Inpatient initiation of guideline-directed medical therapy (GDMT) is recommended for patients with heart failure with reduced ejection fraction (HFrEF) to reduce the risk of cardiovascular death or HF hospitalization. However, underutilization of GDMT prior to discharge is pervasive, representing a valuable missed opportunity to optimize evidence-based care.

View Article and Find Full Text PDF

The superiority of angiotensin receptor-neprilysin inhibitor (ARNI) over angiotensin-converting enzyme inhibitor (ACE-I) and angiotensin receptor blocker (ARB) has not been reassessed after the publication of recent trials that did not find clinical benefits. Therefore, we performed an updated network meta-analysis comparing the efficacy and safety of ARNI, ACE-I, ARB, and placebo in heart failure with reduced ejection fraction. We included randomized clinical trials that compared ARNI, ARB, ACE-I, and placebo in heart failure with reduced ejection fraction.

View Article and Find Full Text PDF

Background Patients with obesity and advanced heart failure face unique challenges on the path to heart transplantation. There are limited data on waitlist and transplantation outcomes in this population. We aimed to evaluate the impact of obesity on heart transplantation outcomes, and to investigate the effects of the new organ procurement and transplantation network allocation system in this population.

View Article and Find Full Text PDF

Background Because of discrepancies between donor supply and recipient demand, the cardiac transplantation process aims to prioritize the most medically urgent patients. It remains unknown how recipients with the lowest medical urgency compare to others in the allocation process. We aimed to examine differences in clinical characteristics, organ allocation patterns, and outcomes between cardiac transplantation candidates with the lowest and highest medical urgency.

View Article and Find Full Text PDF

Background Racial and ethnic disparities contribute to differences in access and outcomes for patients undergoing heart transplantation. We evaluated contemporary outcomes for heart transplantation stratified by race and ethnicity as well as the new 2018 allocation system. Methods and Results Adult heart recipients from 2011 to 2020 were identified in the United Network for Organ Sharing database and stratified into 3 groups: Black, Hispanic, and White.

View Article and Find Full Text PDF

Aims: The impact of mechanical ventilation (MV) at the time of heart transplantation is not well understood. In addition, MV was recently removed as a criterion from the new US heart transplantation allocation system. We sought to assess for the association between MV at transplantation and 1-year mortality.

View Article and Find Full Text PDF