Hindricks, Gerhard

Abstract Background Effective fluid status monitoring in chronic heart failure (HF) patients is critical for preventing decompensation and hospitalization. Conventional methods, such as daily weight tracking, often fail to detect early, pre-symptomatic fluid retention. As fluid accumulation affects the vocal tract, subtle voice alterations can serve as a biomarker for congestion. In this work, we present preliminary results from the first 55 patients enrolled at the German Heart Center at Charité (DHZC) within the multicenter VAMP-HF study, assessing the performance of AI-driven voice analysis for non-invasive fluid status monitoring. Methods The study design incorporated a run-in period for the first 20 patients to refine the recording setup and ensure sufficient audio quality for subsequent data collection. An additional three patients were excluded due to clinical deterioration or in-hospital mortality. Participants provided daily voice recordings (sustained vowels, standardized text, and varying sentences) alongside clinical measurements such as NT-proBNP, daily weight, and left-ventricular ejection fraction. A speaker-independent XGBoost classifier was trained on acoustic features to classify patient states (admission, discharge, and intermediate states). Performance was evaluated using a nested leave-one-patient-out approach, ensuring strict training and validation data separation. Results The final analysis included 32 patients (mean age 76.12 ± 12.65 years). At admission, patients had a mean NT-proBNP of 9575.55 ± 8202.87 pg/mL and a mean weight loss of 4.2 ± 4.29 kg until discharge. The trained machine learning model achieved an F1-score of 0.75 (Fig. 1b), demonstrating its ability to distinguish between admission and discharge states, based solely on voice samples. An exemplary prediction for a test patient is shown in Fig. 1a. Notably, the model was also able to detect subtle vocal changes even in patients with <2 kg weight loss. Conclusion Our findings suggest that AI-driven voice analysis is a feasible biomarker for detecting heart failure decompensation. While not directly compared with conventional early warning thresholds, these results support the hypothesis that voice-based biomarkers may serve as an early indicator of fluid congestion. Further validation in larger cohorts is needed to confirm these findings and enable integration into remote HF monitoring programs.

Abstract Atrial fibrillation (AF) is increasingly diagnosed early, close to its first occurrence due to: (i) increased public awareness with self-screening; (ii) health care initiatives including population screening and opportunistic case finding; and (iii) increased use and surveillance of implantable cardiac devices. At its onset, AF is often low burden, and cardiovascular co-morbidities may be absent or at an early stage. Thus, the management of recent-onset AF has become an issue of growing importance. Professional guidelines have traditionally focused on anticoagulant thromboprophylaxis, generally recommending a cautious approach to rhythm control, and priority has been given to rate control to alleviate symptoms. In recent guidelines, the importance of managing lifestyle and co-morbidities has increased. The AF-SCREEN collaboration proposes that a vigorous approach to active management of recent-onset AF may be warranted. This includes addressing co-morbidities and promoting healthy lifestyles to prevent the emergence or progression of AF and associated cardiovascular disease, as well as the initiation of active rhythm control ± anticoagulation to prevent AF-related morbidity and mortality, including stroke and heart failure (HF). Intuitively, intervention early after AF onset would be beneficial since lifestyle and co-morbidity management, plus rhythm control and anticoagulation, are important contributors to improved outcomes in patients with established AF, but robust evidence is lacking for recent-onset AF. There is a delicate balance between achieving favourable outcomes such as preventing strokes, HF and AF progression vs the complications and potential adverse effects of interventions. Given the serious long-term consequences, innovative approaches are necessary to determine the value and risks of initiating active therapy very early in the course of AF. More data are needed to guide the best management of recent-onset AF, bearing AF burden in mind. Long-term studies using large national databases linked to electronic medical records and rhythm monitoring devices offer excellent opportunities. Shorter-term studies focusing on reducing AF burden to slow AF progression and studies focusing on outcomes such as HF could be used in both randomized clinical trials and observational cohort studies.

Abstract Aims Artificial intelligence (AI) has the potential to transform cardiac electrophysiology (EP), particularly in arrhythmia detection, procedural optimization, and patient outcome prediction. However, a standardized approach to reporting and understanding AI-related research in EP is lacking. This scientific statement aims to develop and apply a checklist for AI-related research reporting in EP to enhance transparency, reproducibility, and understandability in the field. Methods and results An AI checklist specific to EP was developed with expert input from the writing group and voted on using a modified Delphi process, leading to the development of a 29-item checklist. The checklist was subsequently applied to assess reporting practices to identify areas where improvements could be made and provide an overview of the state of the art in AI-related EP research in three domains from May 2021 until May 2024: atrial fibrillation (AF) management, sudden cardiac death (SCD), and EP lab applications. The EHRA AI checklist was applied to 31 studies in AF management, 18 studies in SCD, and 6 studies in EP lab applications. Results differed between the different domains, but in no domain reporting of a specific item exceeded 55% of included papers. Key areas such as trial registration, participant details, data handling, and training performance were underreported (<20%). The checklist application highlighted areas where reporting practices could be improved to promote clearer, more comprehensive AI research in EP. Conclusion The EHRA AI checklist provides a structured framework for reporting AI research in EP. Its use can improve understanding but also enhance the reproducibility and transparency of AI studies, fostering more robust and reliable integration of AI into clinical EP practice.

Background: Pulsed field ablation uses electrical pulses to cause nonthermal irreversible electroporation and induce cardiac cell death. Pulsed field ablation may have effectiveness comparable to traditional catheter ablation while preventing thermally mediated complications. Methods: The PULSED AF pivotal study (Pulsed Field Ablation to Irreversibly Electroporate Tissue and Treat AF) was a prospective, global, multicenter, nonrandomized, paired single-arm study in which patients with paroxysmal (n=150) or persistent (n=150) symptomatic atrial fibrillation (AF) refractory to class I or III antiarrhythmic drugs were treated with pulsed field ablation. All patients were monitored for 1 year using weekly and symptomatic transtelephonic monitoring; 3-, 6-, and 12-month ECGs; and 6- and 12-month 24-hour Holter monitoring. The primary effectiveness end point was freedom from a composite of acute procedural failure, arrhythmia recurrence, or antiarrhythmic escalation through 12 months, excluding a 3-month blanking period to allow recovery from the procedure. The primary safety end point was freedom from a composite of serious procedure- and device-related adverse events. Kaplan-Meier methods were used to evaluate the primary end points. Results: Pulsed field ablation was shown to be effective at 1 year in 66.2% (95% CI, 57.9 to 73.2) of patients with paroxysmal AF and 55.1% (95% CI, 46.7 to 62.7) of patients with persistent AF. The primary safety end point occurred in 1 patient (0.7%; 95% CI, 0.1 to 4.6) in both the paroxysmal and persistent AF cohorts. Conclusions: PULSED AF demonstrated a low rate of primary safety adverse events (0.7%) and provided effectiveness consistent with established ablation technologies using a novel irreversible electroporation energy to treat patients with AF. Registration: URL: https://www.clinicaltrials.gov ; Unique identifier: NCT04198701.

Abstract Aims To develop quality indicators (QIs) that may be used to evaluate the quality of care and outcomes for adults with atrial fibrillation (AF). Methods and results We followed the ESC methodology for QI development. This methodology involved (i) the identification of the domains of AF care for the diagnosis and management of AF (by a group of experts including members of the ESC Clinical Practice Guidelines Task Force for AF); (ii) the construction of candidate QIs (including a systematic review of the literature); and (iii) the selection of the final set of QIs (using a modified Delphi method). Six domains of care for the diagnosis and management of AF were identified: (i) Patient assessment (baseline and follow-up), (ii) Anticoagulation therapy, (iii) Rate control strategy, (iv) Rhythm control strategy, (v) Risk factor management, and (vi) Outcomes measures, including patient-reported outcome measures (PROMs). In total, 17 main and 17 secondary QIs, which covered all six domains of care for the diagnosis and management of AF, were selected. The outcome domain included measures on the consequences and treatment of AF, as well as PROMs. Conclusion This document defines six domains of AF care (patient assessment, anticoagulation, rate control, rhythm control, risk factor management, and outcomes), and provides 17 main and 17 secondary QIs for the diagnosis and management of AF. It is anticipated that implementation of these QIs will improve the quality of AF care.

Background: Coupling between the ablation catheter and myocardium is critical to resistively heat tissue with radiofrequency ablation. The objective of this study was to evaluate whether a novel local impedance (LI) measurement on an ablation catheter identifies catheter–tissue coupling and is predictive of lesion formation. Methods and Results: LI was studied in explanted hearts (n=10 swine) and in vivo (n=10; 50–70 kg swine) using an investigational electroanatomic mapping system that measures impedance from an ablation catheter with mini-electrodes incorporated in the distal electrode (Rhythmia and IntellaNav MiFi OI, Boston Scientific). Explanted tissue was placed in a warmed (37 °C) saline bath mounted on a scale, and LI was measured 15 mm away from tissue to 5 mm of catheter–tissue compression at multiple catheter angles. Lesions were created with 31 and 50 W for 5 to 45 seconds (n=90). During in vivo evaluation of LI, measurements of myocardium (n=90) and blood pool (n=30) were guided by intracardiac ultrasound while operators were blinded to LI data. Lesions were created with 31 and 50 W for 45 seconds in the ventricles (n=72). LI of myocardium (119.7 Ω) was significantly greater than that of blood pool (67.6 Ω; P <0.01). Models that incorporate LI drop (ΔLI) to predict lesion size had better performance than models that incorporate force-time integral ( R 2 =0.75 versus R 2 =0.54) and generator impedance drop ( R 2 =0.82 versus R 2 =0.58). Steam pops displayed a significantly higher starting LI and larger ΔLI compared with successful radiofrequency applications ( P <0.01). Conclusions: LI recorded from miniature electrodes provides a valuable measure of catheter–tissue coupling, and ΔLI is predictive of lesion formation during radiofrequency ablation.