Ribeiro, Antonio Luiz

Abstract Background Ventricular systolic dysfunction (LVSD) is the main predictor of mortality in Chagas disease (ChD). Although LVSD can be treated with affordable medications that enhance both symptoms and survival, its diagnosis necessitates advanced imaging tests, which are often unavailable in resource-limited settings. Recently, artificial intelligence (AI) models applied to an electrocardiogram (ECG) have shown promise in detecting LVSD and assessing disease progression, acting as digital biomarkers and offering the potential for screening tools. Purpose This study aims to evaluate the performance of an AI-ECG model in detecting LVSD and predicting mortality in patients with ChD. Specifically, we will fine-tune the AI-ECG model to improve LVSD identification and update the previously published mortality score (JAHA) by replacing NT-proBNP with AI-ECG to assess mortality risk. Methods This study was conducted with patients from the SaMi-Trop project, a prospective cohort of individuals seropositive for ChD from 21 municipalities in Minas Gerais, an endemic region of Brazil. The baseline assessment occurred in 2013–2014, with follow-ups in 2015–2016 (FU1) and 2022–2023 (FU2). The AI-ECG model was fine-tuned using a dataset with an 8% low ejection fraction prevalence. The model was trained with a binary cross-entropy loss function, a batch size of 128, and an Adam optimizer with a learning rate of 0.001. The area under the curve (AUC) was calculated for validation. The fine-tuned model, parsed into 2-second ECG windows, was applied to two waves of the SaMi-Trop cohort: Baseline (4,701 ECGs from 1,906 patients) and FU1 (2,324 ECGs from 1,059 patients). The association between AI-detected LVSD (AI-LVSD) and mortality was assessed using Cox proportional hazard models. Results The fine-tuned AI-LVSD model achieved an AUC of 0.88 (95% CI: 0.78–0.97) in detecting LVSD. When updating the JAHA mortality score, AI-LVSD replaced NT-proBNP with a stronger association with mortality risk, yielding hazard ratios (HR) of 4.5 (95% CI: 3,0–6.8) for two-year mortality and 4.3 (95% CI: 3.4–5.5) for overall mortality. Additionally, when incorporated into a simplified hazard model alongside age and NYHA class, AI-LVSD emerged as a strong biomarker for mortality risk, with hazard ratios of 5.4 (95% CI: 3.7–7.8) for two-year mortality and 4.9 (95% CI: 4.0–6.1) for overall mortality (Figure 1). Conclusion The AI-ECG model accurately identified LVSD for screening purposes and effectively replaced NT-proBNP in a simplified mortality risk model for Chagas disease. This tool can potentially enhance early detection and risk stratification, particularly in remote areas with limited access to advanced diagnostic resources.Figure 01.Cox proportional hazard model

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.