Search

BACKGROUND: Inadequate representation of women and racial minorities in heart failure (HF) clinical trials continues to limit the generalizability of the results. This could create a disparity in treatment for future heart failure therapies and devices. The study aims to assess the representation of women and racial minorities in recent heart failure studies involving sodium-glucose cotransporter-2 (SGLT-2) inhibitors. METHODS: PubMed was used to search randomized controlled trials (RCTs) looking at SGLT-2 inhibitors and heart failure, which were published from inception to August 2024. RESULTS: A total of 43 RCTs with 27,703 participants were identified. The studies were published between 2018 and 2024. Seven studies (41 %) were multi-country, with 45 countries represented. The overall proportion of women enrolled in the studies was 35.6 %. The proportion of women was 24.06 % in studies that recruited only patients with HFrEF, 44.33 % in those that recruited only patients with HFpEF, and 41.4 % in those that recruited both HFrEF and HFpEF. Data on race was partially reported in 25 studies (58 %). 76 % of the pharmaceutical industry-funded studies reported race data. However, only 33.3 % of the unfunded or non-industry-funded studies reported race data. In the studies that reported race data, 72.91 % were Caucasians, 15.48 % were Asians, 5.62 % were African-American and 4.1 % were mixed race or others.In the bivariate analysis, race was more likely to be reported in studies done in the US (p

BACKGROUND: Heart failure with reduced ejection fraction (HFrEF) and heart failure with preserved ejection fraction (HFpEF) are challenging conditions to treat due to complex pathophysiology and associated comorbidities. However, recent trials have demonstrated improved outcomes with guideline-directed medical therapy (GDMT) for each subtype of heart failure. OBJECTIVE: We investigated the relationship of determinants of health and risk factors with GDMT use for HFrEF and HFpEF in a large, diverse US cohort. METHODS: Using the NIH-sponsored All of Us Program, we compared demographics, risk factors (e.g., hypertension, diabetes, smoking), and SDOH measures between HFrEF and HFpEF in US adults aged 18 years and older. We examined the proportions of HFrEF patients receiving fewer than four or all four GDMTs. HFpEF patients receiving two medications were compared with those receiving less than two recommended medications. Multiple logistic regression was used for data analysis. RESULT: Of 6049 HFrEF patients, 5838 (97 %) received fewer than four GDMTs, and 210 (3 %) received quadruple therapy. Of 3774 HFpEF patients, 162 (4 %) were on 2/3 GDMT, and only 38 (1 %) were on all three recommended medications. Patients with ASCVD and diabetes had higher odds of being on more than half of the recommended GDMT for both HFrEF and HFpEF. Additionally, females had higher odds of being on 2/3 GDMT for HFpEF (1.46 [1.08, 2.00]). Race, income, education, and health insurance types did not predict GDMT optimization. CONCLUSION: HFrEF and HFpEF GDMT remain underutilized. Future efforts to address comorbidities and system-wide healthcare interventions may improve heart failure GDMT.

BACKGROUND: Worsening renal function (WRF) is common in hospitalized patients being treated for acute heart failure. However, discriminating clinically significant WRF remains challenging. In patients hospitalized with acute heart failure, we evaluated if blood and urine biomarkers of cardiac and kidney dysfunction were associated with adverse outcomes. METHODS: We identified 175 of 927 participants in the AKINESIS study (Acute Kidney Neutrophil Gelatinase-Associated Lipocalin Evaluation of Symptomatic Heart Failure Study) who met criteria for stage 1 or 2 Kidney Disease: Improvement Global Outcomes acute kidney injury during the first 3 days of hospitalization. We measured 24 blood and urine biomarkers from specimens collected within 24 hours of meeting acute kidney injury criteria. The primary composite outcome consisted of worsening WRF (higher acute kidney injury stage), need for dialysis, or death at 30 days. Biomarkers association with the composite outcome was assessed with logistic regression by tertiles and area under the curve (AUC). RESULTS: Of the 175 participants, 32 (18%) developed the primary composite outcome. Only history of chronic kidney disease was significantly different between those with and without the composite outcome. The highest tertile of plasma Gal-3 (galectin-3) and urine epidermal growth factor were associated with increased odds of the composite outcome compared with the lowest tertile in unadjusted analyses. After adjusting for serum creatinine, systolic blood pressure, and blood urea nitrogen, only the highest tertile of Gal-3 was associated with greater odds of the composite outcome (odds ratio, 4.6 [95% CI, 1.4-16.0). Gal-3 had the highest AUC (0.70 [95% CI, 0.58-0.82]), while epidermal growth factor had a lower AUC (0.63 [95% CI, 0.53-0.74]). Notably, urine biomarkers of kidney tubule injury were not associated with the composite outcome. CONCLUSIONS: Tubular injury does not occur in most patients with acute heart failure experiencing WRF, consistent with the functional mechanisms of WRF in this patient population. REGISTRATION: URL: https://www.clinicaltrials.gov/study/NCT01291836?term=NCT01291836&rank=1; Unique identifier: NCT01291836.

Glycoprotein nonmetastatic melanoma protein B (GPNMB) is a type I transmembrane protein initially identified in nonmetastatic melanomas and has been associated with human heart failure; however, its role in cardiac injury and function remains unclear. Here we show that GPNMB expression is elevated in failing human and mouse hearts after myocardial infarction (MI). Lineage tracing and bone-marrow transplantation reveal that bone-marrow-derived macrophages are the main source of GPNMB in injured hearts. Using genetic loss-of-function models, we demonstrate that GPNMB deficiency leads to increased mortality, cardiac rupture and rapid post-MI left ventricular dysfunction. Conversely, increasing circulating GPNMB levels through viral delivery improves heart function after MI. Single-cell transcriptomics show that GPNMB enhances myocyte contraction and reduces fibroblast activation. Additionally, we identified GPR39 as a receptor for circulating GPNMB, with its absence negating the beneficial effects. These findings highlight a pivotal role of macrophage-derived GPNMBs in post-MI cardiac repair through GPR39 signaling.

Explainability of convolutional neural networks (CNNs) is integral for their adoption into radiological practice. Commonly used attribution methods localize image areas important for CNN prediction but do not characterize relevant imaging features underlying these areas, acting as a barrier to the adoption of CNNs for clinical use. We therefore propose Semantic Exploration and Explainability using a Style-based Generative Adversarial Autoencoder Network (SEE-GAAN), an explainability framework that uses latent space manipulation to generate a sequence of synthetic images that semantically visualizes how clinical and CNN features manifest within medical images. Visual analysis of changes in these sequences then facilitates the interpretation of features, thereby improving explainability. SEE-GAAN was first developed on a cohort of 26,664 chest radiographs across 15,409 patients from our institution. SEE-GAAN sequences were then generated across several clinical features and CNN predictions of NT-pro B-type natriuretic peptide (BNPP) as a proxy for acute heart failure. Radiological interpretations indicated SEE-GAAN sequences captured relevant changes in anatomical and pathological morphology associated with clinical and CNN predictions and clarified ambiguous areas highlighted by commonly used attribution methods. Our study demonstrates SEE-GAAN can facilitate our understanding of clinical features for imaging biomarker exploration and improve CNN transparency over commonly used explainability methods.

Existing risk prediction models for hospitalized heart failure patients are limited. We identified patients hospitalized with a diagnosis of heart failure between 7 May 2013 and 26 April 2022 from a large academic, quaternary care medical centre (training cohort). Demographics, medical comorbidities, vitals, and labs were collected and were used to construct random forest machine learning models to predict in-hospital mortality. Models were compared with logistic regression, and to commonly used heart failure risk scores. The models were subsequently validated in patients hospitalized with a diagnosis of heart failure from a second academic, community medical centre (validation cohort). The entire cohort comprised 21 802 patients, of which 14 539 were in the training cohort and 7263 were in the validation cohort. The median age (25th-75th percentile) was 70 (58-82) for the entire cohort, 43.2% were female, and 6.7% experienced inpatient mortality. In the overall cohort, 7621 (35.0%) patients had heart failure with reduced ejection fraction (EF ≤ 40%), 1271 (5.8%) had heart failure with mildly reduced EF (EF 41-49%), and 12 910 (59.2%) had heart failure with preserved EF (EF ≥ 50%). Random forest models in the validation cohort demonstrated a c-statistic (95% confidence interval) of 0.96 (0.95-0.97), sensitivity (SN) of 87.3%, and specificity (SP) of 90.6% for the prediction of in-hospital mortality. Models for those with HFrEF demonstrated a c-statistic of 0.96 (0.94-0.98), SN 88.2%, and SP 91.0%, and those for patients with HFpEF showed a c-statistic of 0.95 (0.93-0.97), SN 87.4%, and SP 89.5% for predicting in-hospital mortality. The random forest model significantly outperformed logistic regression (c-statistic 0.87, SN 75.9%, and SP 86.9%), and current existing risk scores including the Acute Decompensated Heart Failure National Registry risk score (c-statistic of 0.70, SN 69%, and SP 62%), and the Get With the Guidelines-Heart Failure risk score (c-statistic 0.69, SN 67%, and SP 63%); P

AIMS: Heart failure (HF) is a clinical syndrome with no definitive diagnostic tests. HF registries are often based on manual reviews of medical records of hospitalized HF patients identified using International Classification of Diseases (ICD) codes. However, most HF patients are not hospitalized, and manual review of big electronic health record (EHR) data is not practical. The US Department of Veterans Affairs (VA) has the largest integrated healthcare system in the nation, and an estimated 1.5 million patients have ICD codes for HF (HF ICD-code universe) in their VA EHR. The objective of our study was to develop artificial intelligence (AI) models to phenotype HF in these patients. METHODS AND RESULTS: The model development cohort (n = 20 000: training, 16 000; validation 2000; testing, 2000) included 10 000 patients with HF and 10 000 without HF who were matched by age, sex, race, inpatient/outpatient status, hospital, and encounter date (within 60 days). HF status was ascertained by manual chart reviews in VAs External Peer Review Program for HF (EPRP-HF) and non-HF status was ascertained by the absence of ICD codes for HF in VA EHR. Two clinicians annotated 1000 random snippets with HF-related keywords and labelled 436 as HF, which was then used to train and test a natural language processing (NLP) model to classify HF (positive predictive value or PPV, 0.81; sensitivity, 0.77). A machine learning (ML) model using linear support vector machine architecture was trained and tested to classify HF using EPRP-HF as cases (PPV, 0.86; sensitivity, 0.86). From the HF ICD-code universe, we randomly selected 200 patients (gold standard cohort) and two clinicians manually adjudicated HF (gold standard HF) in 145 of those patients by chart reviews. We calculated NLP, ML, and NLP + ML scores and used weighted F scores to derive their optimal threshold values for HF classification, which resulted in PPVs of 0.83, 0.77, and 0.85 and sensitivities of 0.86, 0.88, and 0.83, respectively. HF patients classified by the NLP + ML model were characteristically and prognostically similar to those with gold standard HF. All three models performed better than ICD code approaches: one principal hospital discharge diagnosis code for HF (PPV, 0.97; sensitivity, 0.21) or two primary outpatient encounter diagnosis codes for HF (PPV, 0.88; sensitivity, 0.54). CONCLUSIONS: These findings suggest that NLP and ML models are efficient AI tools to phenotype HF in big EHR data to create contemporary HF registries for clinical studies of effectiveness, quality improvement, and hypothesis generation.