Search

BACKGROUND: In January 2021, vericiguat, a soluble guanylate cyclase stimulator, was approved by the U.S. Food and Drug Administration (FDA) to reduce the risk of cardiovascular death and heart failure (HF) hospitalization among patients with a recent worsening HF event based on the VICTORIA (VerICiguaT Global Study in Subjects with Heart Failure with Reduced Ejection Fraction) trial. OBJECTIVES: This study sought to leverage a contemporary U.S. registry of patients hospitalized for heart failure (HF) to characterize patients who may be candidates for vericiguat based on FDA label and the VICTORIA trial eligibility criteria. METHODS: The authors studied patients hospitalized for HF with ejection fraction (EF)

BackgroundHeart failure (HF) is highly prevalent in the United States. Approximately one-third to one-half of HF cases are categorized as HF with reduced ejection fraction (HFrEF). Patients with HFrEF are at risk of worsening HF, have a high risk of adverse outcomes, and experience higher health care use and costs. Therefore, it is crucial to identify patients with HFrEF who are at high risk of subsequent events after HF hospitalization.ObjectiveMachine learning (ML) has been used to predict HF-related outcomes. The objective of this study was to compare different ML prediction models and feature construction methods to predict 30-, 90-, and 365-day hospital readmissions and worsening HF events (WHFEs).MethodsWe used the Veradigm PINNACLE outpatient registry linked to Symphony Health's Integrated Dataverse data from July 1, 2013, to September 30, 2017. Adults with a confirmed diagnosis of HFrEF and HF-related hospitalization were included. WHFEs were defined as HF-related hospitalizations or outpatient intravenous diuretic use within 1 year of the first HF hospitalization. We used different approaches to construct ML features from clinical codes, including frequencies of clinical classification software (CCS) categories, Bidirectional Encoder Representations From Transformers (BERT) trained with CCS sequences (BERT + CCS), BERT trained on raw clinical codes (BERT + raw), and prespecified features based on clinical knowledge. A multilayer perceptron neural network, extreme gradient boosting (XGBoost), random forest, and logistic regression prediction models were applied and compared.ResultsA total of 30,687 adult patients with HFrEF were included in the analysis; 11.41% (3184/27,917) of adults experienced a hospital readmission within 30 days of their first HF hospitalization, and nearly half (9231/21,562, 42.81%) of the patients experienced at least 1 WHFE within 1 year after HF hospitalization. The prediction models and feature combinations with the best area under the receiver operating characteristic curve (AUC) for each outcome were XGBoost with CCS frequency (AUC=0.595) for 30-day readmission, random forest with CCS frequency (AUC=0.630) for 90-day readmission, XGBoost with CCS frequency (AUC=0.649) for 365-day readmission, and XGBoost with CCS frequency (AUC=0.640) for WHFEs. Our ML models could discriminate between readmission and WHFE among patients with HFrEF. Our model performance was mediocre, especially for the 30-day readmission events, most likely owing to limitations of the data, including an imbalance between positive and negative cases and high missing rates of many clinical variables and outcome definitions.ConclusionsWe predicted readmissions and WHFEs after HF hospitalizations in patients with HFrEF. Features identified by data-driven approaches may be comparable with those identified by clinical domain knowledge. Future work may be warranted to validate and improve the models using more longitudinal electronic health records that are complete, are comprehensive, and have a longer follow-up time.

Aims: Patients with HFrEF and worsening HF events (WHFE) are at particularly high risk and urgently need disease‐modifying therapy. CHART‐HF assessed treatment patterns and reasons for medication decisions among HFrEF patients with and without WHFE. Methods and results: CHART‐HF collected retrospective electronic medical records of outpatients with HF and EF < 45% between 2017–2019 from a nationwide panel of 238 cardiologists (458 patients) and the Geisinger Health System (GHS) medical record (1000 patients). The index visit in the WHFE cohort was the first outpatient cardiologist visit ≤6 months following the WHFE, and in the reference cohort was the last visit in a calendar year without WHFE. Demographic characteristics were similar between patients with and without WHFE in both the nationwide panel and GHS. In the nationwide panel, the proportion of patients with versus without WHFE receiving ≥50% of guideline‐recommended dose on index visit was 35% versus 40% for beta blocker, 74% versus 83% for ACEI/ARB/ARNI, and 48% versus 49% for MRA. The proportion of patients receiving ≥50% of guideline‐recommended dose was lower in the GHS: 29% versus 34% for beta‐blocker, 16% versus 31% for ACEI/ARB/ARNI, and 18% versus 22% for MRA. For patients with and without WHFE, triple therapy on index date was 42% and 44% of patients from the nationwide panel, and 14% and 17% in the GHS. Comparing end of index clinic visit with 12‐month follow‐up in the GHS, the proportion of patients on no GDMT increased from 14% to 28% in the WHFE cohort and from 14 to 21% in the non‐WHFE group. Conclusions: Major gaps in use of GDMT, particularly combination therapy, remain among US HFrEF patients. These gaps persist during longitudinal follow‐up and are particularly large among patients with recent WHFE. [ABSTRACT FROM AUTHOR]

This retrospective study was conducted to evaluate all‐cause healthcare resource utilization (HCRU) and costs in commercially insured patients living with pulmonary arterial hypertension (PAH) and explore end‐of‐life (EOL)‐related HCRU and costs. Data from the IQVIA PharMetrics® Plus database (October 2014 to May 2020) were analyzed to identify adults (≥18 years) with PAH (PAH cohort) and those without PH (non‐PH cohort). Patients were required to have data for ≥12 months before (baseline) and ≥6 months after (follow‐up) the first observed PH diagnosis (index date) for PAH cohort or pseudo index date for non‐PH cohort. A PAH EOL cohort was similarly constructed using a broader data window (October 2014 to March 2022) and ≥1 month of follow‐up. Annualized all‐cause HCRU and costs during follow‐up were compared between PAH and non‐PH cohorts after 1:1 matching on propensity scores derived from patient characteristics. EOL‐related HCRU and costs were explored within 30 days and 6 months before the death date and estimated by a claims‐based algorithm in PAH EOL cohort. The annual all‐cause total ($183,616 vs. $20,212) and pharmacy ($115,926 vs. $7862; both p < 0.001) costs were 8 and 14 times higher, respectively, in the PAH cohort versus matched non‐PH cohort (N = 386 for each). In PAH EOL cohort (N = 28), the mean EOL‐related costs were $48,846 and $167,524 per patient within 30 days and 6 months before the estimated death, respectively. Hospitalizations contributed 58.8%–70.8% of the EOL‐related costs. The study findings indicate substantial HCRU and costs for PAH. While pharmacy costs were one of the major sources, hospitalization was the primary driver for EOL‐related costs. [ABSTRACT FROM AUTHOR]

Aims: In patients with heart failure (HF), we aimed to assess (i) the time trends in N‐terminal pro‐B‐type natriuretic peptide (NT‐proBNP) testing; (ii) patient characteristics associated with NT‐proBNP testing; (iii) distribution of NT‐proBNP levels, focusing on the subgroups with (WHFE) vs. without (NWHFE) a worsening HF event, defined as an HF hospitalization; and (iv) changes of NT‐proBNP levels over time. Methods and results: NT‐proBNP testing and levels were investigated in HF patients enrolled in the Swedish Heart Failure Registry (SwedeHF) linked with the Stockholm CREAtinine Measurements project from January 2011 to December 2018. Index date was the first registration in SwedeHF. Patterns of change in NT‐proBNP levels before (in the previous 6 ± 3 months) and after (in the following 6 ± 3 months) the index date were categorized as follows: (i) <3000 ng/L at both measurements = stable low; (ii) <3000 ng/L at the first measurement and ≥3000 ng/L at the second measurement = increased; (iii) ≥3000 ng/L at the first measurement and <3000 ng/L at the second measurement = decreased; and (iv) ≥3000 ng/L at both measurements = stable high. Univariable and multivariable logistic regression models, expressed as odds ratios (ORs) and 95% confidence intervals (95% CIs), were performed to assess the associations between (i) clinical characteristics and NT‐proBNP testing and (ii) changes in NT‐proBNP from 6 months prior to the index date and the index date and a WHFE. Consistency analyses were performed in HF with reduced ejection fraction (HFrEF) alone. A total of 4424 HF patients were included (median age 74 years, women 34%, HFrEF 53%), 33% with a WHFE. NT‐proBNP testing increased over time, up to 55% in 2018, and was almost two‐fold as frequent, and time to testing was less than half, in patients with WHFE vs. NWHFE. Independent predictors of testing were WHFE, higher heart rate, diuretic use, and preserved ejection fraction. Median NT‐proBNP was 3070 ng/L (Q1–Q3: 1220–7395), approximately three‐fold higher in WHFE vs. NWHFE. Compared with stable low NT‐proBNP levels, increased (OR 4.27, 95% CI 2.47–7.37) and stable high levels (OR 2.48, 95% CI 1.58–3.88) were independently associated with a higher risk of WHFE. Results were consistent in the HFrEF population. Conclusions: NT‐proBNP testing increased over time but still was only performed in half of the patients. Testing was associated with a WHFE, with features of more severe HF and for differential diagnosis purposes. Increased and stable high levels were associated with a WHFE. Overall, our data highlight the potential benefits of carrying further implementation of NT‐proBNP testing in clinical practice. [ABSTRACT FROM AUTHOR]