Wong, Yee W

ABSTRACT Background Acute heart failure (AHF) exhibits marked heterogeneity in diastolic hemodynamics, yet comprehensive echocardiographic assessment of diastolic function (DF) and filling pressure (FP) is often infeasible. We evaluated whether artificial intelligence–enabled electrocardiography (AI-ECG) could provide scalable DF grading and FP estimation in hospitalized AHF patients. Methods We retrospectively studied adults hospitalized for AHF across Mayo Clinic sites (2013–2023) who received ≥1 dose of intravenous loop diuretic and had paired 12-lead ECG and TTE. The previously validated AI-ECG DF model was applied without retraining to generate four DF grades and a continuous FP probability. Clinical outcomes were all-cause mortality and heart failure rehospitalization. Associations with clinical severity markers and echocardiographic indices were examined. Kaplan–Meier survival analysis and adjusted multivariable Cox proportional hazards models were performed. Exploratory analyses examine the kinetics of change in FP probability and impact on mortality. Results Among 11,513 patients (median age 75 years, 39% female), AI-ECG DF grading was feasible in 100%, whereas echocardiographic DF was indeterminate in 44% of clinically eligible patients. In 2,582 patients with determinate echocardiographic DF, AI-ECG FP probability discriminated TTE Grade 2–3 dysfunction with AUC 0.85 (95% CI 0.83 – 0.86). Higher AI-ECG DF grades were associated with higher comorbidity burden, worse NYHA class, elevated NT-proBNP, higher MAGGIC scores, elevated PCWP, and more advanced structural remodeling. After multivariable adjustment, AI-ECG DF remained independently associated with mortality (hazard ratio [HR] 1.25, 95% CI 1.16–1.35 for Grade 2; HR 1.44, 95% CI 1.33–1.56 for Grade 3 versus Normal/Grade 1). Combining AI-ECG DF with MAGGIC scores yielded ordered risk gradients, with highest mortality in patients with both high MAGGIC and Grade 2–3 DF. Among patients with serial ECGs, improvement in FP probability was independently associated with lower mortality (HR 0.85, 95% CI 0.79–0.91), whereas worsening did not show a consistent adverse gradient beyond baseline DF. Conclusions In a large, geographically diverse AHF cohort, AI-ECG DF grading was universally feasible, correlated with established hemodynamic severity markers, and provided independent prognostic information beyond established risk factors, supporting its role as a pragmatic, scalable diastolic biomarker in AHF. CLINICAL PERSPECTIVE What Is New? In 11,513 hospitalized acute heart failure (HF) patients, artificial intelligence-enabled electrocardiography provided diastolic function grading in 100% of patients from a single 12-lead ECG without requiring additional clinical variables, compared with 56% feasibility for guideline-based echocardiography grading. AI-ECG diastolic function grades correlated with established marker of severity (NYHA functional class, NT-proBNP, MAGGIC risk scores, and pulmonary capillary wedge pressure) and remained independently associated with both mortality and HF rehospitalization after multivariable adjustment. Serial AI-ECG measurements identified post-discharge filling pressure trajectories, with improvement independently associated with 15% lower mortality, a first demonstration that longitudinal ECG assessment can track post-discharge hemodynamic recovery. What Are the Clinical Implications? AI-ECG transforms the universally obtained 12-lead ECG into an actionable hemodynamic biomarker that addresses the critical gap when echocardiographic diastolic function assessment is indeterminate or unavailable in acute HF patients. Despite markedly different hemodynamic severity and long-term outcomes across AI-ECG diastolic function grades, hospitalization length of stay did not differ, suggesting advanced diastolic dysfunction represents occult risk not easily recognized during routine acute care and highlighting the need for improved post-discharge risk stratification. The continuous filling pressure probability metric enables longitudinal monitoring of post-discharge hemodynamic status using serial routine ECGs, potentially identifying patients requiring intensified follow-up or specialist referral.

Abstract Aims Ferric carboxymaltose (FCM) is guideline-recommended for iron deficiency (ID) in heart failure with reduced ejection fraction (HFrEF). Despite a well-established safety profile, the magnitude and clinical significance of FCM-induced hypophosphataemia in HFrEF remains unclear. This pre-specified substudy of HEART-FID evaluated serum phosphate, 1,25-dihydroxyvitamin D, and plasma parathyroid hormone (PTH) subsequent to FCM. Methods and results HEART-FID was a randomized, double-blind, placebo-controlled trial of ambulatory patients with HFrEF and ID randomized to FCM versus placebo. This substudy assessed mean change from baseline across eight visits over 6 months for the following endpoints: serum phosphate, 25-hydroxyvitamin D, 1,25-dihydroxyvitamin D, and PTH, in addition to the clinical severity of potential hypophosphataemia. Overall, 133 patients (n = 62 FCM, n = 71 placebo) were prospectively enrolled. Mean age was 68 ± 11 years, 55 (41.4%) were women, and 29 (21.8%) had chronic kidney disease. Phosphate levels decreased in 34 (57.6%) patients in the FCM group compared with 7 (10.3%) in the placebo group. Mean change in phosphate levels reached a nadir at day 21 (−0.36 ± 0.27 mmol/L) subsequent to FCM infusion with 28 (51%) having moderate-to-severe hypophosphataemia. Reductions in 1,25-dihydroxyvitamin D were also observed, whilst PTH increased. These biochemical changes returned to baseline levels by day 91. Serum levels of 25-hydroxyvitamin D remained stable throughout the study. No serious adverse events associated with hypophosphataemia were reported. Conclusions Transient moderate-to-severe hypophosphataemia was frequent subsequent to FCM infusion, accompanied by 1,25-dihydroxyvitamin D decrease and PTH increase. Serum levels of 25-hydroxyvitamin D remained stable. No evidence of symptomatic hypophosphataemia was reported, collectively indicating FCM-related hypophosphataemia to be clinically benign and transient in HFrEF.

BACKGROUND: Clinical trials in heart failure (HF) traditionally use time-to-event analyses focusing on death and hospitalization for HF. These time-to-first event analyses may have more limited abilities to assess the probability of benefiting from a therapy, especially if that benefit manifests as improved functional status rather than reduced risk of death or HF hospitalization. Hierarchical end points including clinical outcomes and patient status measures allow for ranked evaluation of outcomes in 1 metric assessing whether patients randomized to intervention or control are more likely to derive an overall benefit while also allowing more patients to contribute to the primary outcome. METHODS: We review the rationale for using hierarchical end points in HF trials, provide examples of HF trials that used this type of end point, and discuss its use in the HEART-FID trial (Randomized Placebo-Controlled Trial of Ferric Carboxymaltose as Treatment for Heart Failure With Iron Deficiency), the largest HF trial to date implementing a hierarchical end point analysis for the primary outcome. RESULTS: Using a hierarchical end point as the primary outcome allows for the inclusion of different types of outcomes in 1 ranked end point, making it possible to more holistically assess the potential utility of a new therapy on patient well-being and outcomes. CONCLUSIONS: Hierarchical end points assess the potential utility of a new therapy on patient well-being and outcome more holistically than time-to-first event analysis. Trials that would not have been feasible due to decreasing rates of death and hospitalization in the HF population can use hierarchical end points to successfully power studies to identify promising HF therapies. The HEART-FID trial used hierarchical end points to better determine the role of intravenous ferric carboxymaltose in patients with HF. REGISTRATION: URL: https://www.clinicaltrials.gov ; Unique identifier: NCT03037931.