European heart journal. Digital health最新文献

Aims: Syncope remains a diagnostic challenge despite advancements in testing and treatment. Cardiac syncope is an independent predictor of mortality and can be difficult to distinguish from other causes of transient loss of consciousness (TLOC). This paper explores whether artificial intelligence (AI) can improve the evaluation and management of patients with syncope.

Methods and results: We conducted a literature review and incorporated the opinions of experts in the fields of syncope and AI. The cause of TLOC is often unclear, hospitalization criteria are ambiguous, diagnostic tests are frequently non-informative, and assessments are costly. Patients are left with unanswered questions and limited guidance. Artificial intelligence (AI) has the potential to optimize syncope evaluation by processing large data sets, detecting imperceptible patterns, and assisting clinicians. However, AI has limitations, including errors, lack of human empathy, and uncertain clinical utility. Liability issues further complicate its integration. We present three viewpoints: (i) AI is crucial for advancing syncope management; (ii) AI can enhance the patient experience; and (iii) AI in syncope care is inevitable.

Conclusion: Artificial intelligence may improve syncope diagnosis and management, particularly through machine learning-based test interpretation and wearable device data. However, it has yet to surpass human clinical judgment in complex decision-making. Current challenges include gaps in understanding syncope mechanisms, AI interpretability, generalizability, and clinical integration. Standardized diagnostic approaches, real-world validation, and curated data sets are essential for progress. Artificial intelligence may enhance efficiency and communication but raises concerns regarding confidentiality, bias, inequities, and legal implications.

The complexity and spatial relationships between vascular and cardiac structures, as well as anatomical diversity, pose a challenge for planning and performing cardiac interventions. Medical imaging, especially precise three-dimensional imaging techniques, plays a key role in the decision-making process. While traditional imaging methods like angiography, echocardiography, computed tomography, and magnetic resonance imaging remain gold standards, they have limitations in representing spatial relationships effectively. To overcome these limitations, advanced techniques such as three-dimensional printing, three-dimensional modelling, and Extended Realities are needed. Focusing on Extended Realities, their main advantages are direct spatial visualization based on medical data, interaction with objects, and immersion in cardiac anatomy. These benefits impact procedural planning and intra-procedural navigation. The following publication presents current applications, benefits, drawbacks, and limitations of Virtual, Augmented, and Mixed Reality technologies in cardiac interventions. The aim of this review is to improve understanding and utilization of the entire spectrum of these innovative tools in clinical practice.

Aims: Machine learning (ML) algorithms applied to the electrocardiography (ECG) have been successful in several cardiac diagnoses, however, rarely been used for the diagnostics of takotsubo syndrome (TTS). Our aim was to develop ML-based ECG-models to differentiate TTS from patients with myocardial infarction (MI).

Methods and results: Cross-sectional study in Stockholm. A neural network with UNet architecture was trained and validated on 507 TTS cases and 14 978 controls with suspected and verified MI, identified from the Swedish coronary angiography and angioplasty register. Cross-validation was performed. The models were compared with cardiologists using previously proposed ECG criteria. Receiver operating characteristics (ROC) area under the curve (AUC) for discriminating TTS from patients with ST-elevation and non-ST-elevation MI ROC AUC 0.88 (cross-validation: 0.85-0.92) and 0.86 (cross-validation: 0.82-0.91), respectively. ROC AUC for discriminating TTS from verified MI [non-ST-elevation MI (NSTEMI) and ST-elevation MI (STEMI)] was 0.87 (cross-validation: 0.83-0.91) with sensitivity (0.75) and specificity (0.83) with low positive predictive value (PPV) and high negative predictive value (NPV). Results for suspected MI was ROC AUC 0.85 (cross validation: 0.81-0.91) with sensitivity (0.75) and specificity (0.79) with low PPV (0.11) and high NPV (0.99). The committee of two cardiologists using a combination of ECG criteria achieved an ROC AUC of 0.71.

Conclusion: Machine learning models could discriminate TTS from MI (NSTEMI and STEMI) and suspected MI with high sensitivity and NPV, outperforming cardiologists using conventional criteria. The models require further refinement to increase PPV, precision-recall and external validation, but it holds promise for TTS screening aiding the clinician in ruling out TTS.

Aims: To identify ischaemic cardiomyopathy (ICM) patients with different phenotypes for evaluating their outcomes and heterogeneous treatment effects (HTEs) of coronary artery bypass grafting (CABG).

Methods and results: We applied a machine learning-based consensus, K-Medoids clustering analysis to the Surgical Treatment for Ischemic Heart Failure trial. We compared the risk of all-cause mortality and cardiovascular mortality among different phenotypes. The survival benefits of CABG compared with medical therapy alone were assessed in the identified phenotypes for evaluating HTEs. The consensus clustering analysis identified three distinct clinical phenotypes among 1212 ICM patients based on 19 variables. Specifically, phenotype 1 (n = 371) was characterized by younger ages, higher left ventricular ejection fraction (LVEF), and lower left ventricular end-systolic volume index (n = 371). Phenotype 2 had higher angina grades and more left main/left anterior descending artery stenosis (n = 520). Phenotype 3 had lower LVEF, higher New York Heart Association (NYHA) grades, more diabetes, and less hypertension (n = 321). After a median of 9.8 follow-up years, phenotype 3 had the highest risk of all-cause mortality [hazard ratio (HR), 1.96; 95% confidence intervals (CI), 1.62-2.37] and cardiovascular mortality (HR, 2.46; 95% CI, 1.95-3.10) compared to phenotype 1. Among phenotype 3, CABG provided significant survival benefits in all-cause mortality (HR, 0.75; 95% CI, 0.58-0.96) and cardiovascular mortality (HR, 0.67; 95% CI, 0.50-0.90) compared with medical therapy alone.

Conclusion: We identified three phenotypes with distinct outcomes and HTEs among ICM patients. Patients with lower LVEF, higher NYHA grades, and diabetes had the poorest clinical outcomes but were more likely to derive greater survival benefits from CABG.

Aims: Paravalvular regurgitation (PVR) is frequently observed following Transcatheter Aortic Valve Replacement (TAVR). Periprocedural monitoring of invasive hemodynamics has shown promise for diagnosis of PVR, but automated software options are lacking. We aimed to develop a rule-based algorithm for automated assessment of hemodynamic indices of PVR, and evaluate its construct validity and discriminatory value for cardiac magnetic resonance (CMR)-derived relevant PVR compared to standard manual hemodynamic assessment.

Methods and results: Left ventricular and aortic pressures were invasively measured during TAVR using fluid-filled pigtail catheters. To evaluate construct validity of automated vs. manual assessment of invasive hemodynamics, we compared (i) proportion of cardiac cycles affected by arrhythmias/noise, (ii) pressure gradients, and (iii) PVR indices. Additionally, we compared the discriminatory value of automatically and manually determined PVR indices for CMR-determined relevant PVR at 30-days. In total, 77 patients were enrolled (664 cardiac cycles). Automated filtering of cardiac cycles affected by arrhythmias/noise had a high sensitivity (95.2%) and specificity (86.4%). In addition, excellent agreement was observed between automated and manual computation of mean gradients pre- and post-TAVR [39.3 ± 12.1 vs. 37.5 ± 11.9 mmHg, intra-class correlation coefficient (ICC): 0.916; 1.92 ± 5.87 vs. 1.14 ± 5.89, ICC: 0.957, respectively], and PVR indices [diastolic delta (DD): 41.7 ± 12.4 vs. 40.6 ± 12.3 mmHg, ICC: 0.982, respectively]. Automated and manual assessment of DD showed comparable discriminatory value for relevant PVR [area under the curve (AUC): 0.81 vs. 0.80, respectively].

Conclusion: Rule-based, automated assessment of hemodynamic indices of PVR showed excellent construct validity and discriminatory value for CMR-determined relevant PVR, supporting its use for real-time evaluation and risk stratification in TAVR patients.

Aims: Smartphone-based digital screening was shown to increase the detection rate of atrial fibrillation (AF) requiring oral anticoagulation (OAC) compared with usual care. In this pre-specified subgroup analysis of the eBRAVE-AF trial, we explored sex-specific differences in digital AF-screening.

Methods and results: In eBRAVE-AF (NCT04250220), participating policyholders of a German health insurance company were randomly assigned to a 6-month digital or conventional AF-screening strategy. For digital screening, participants used smartphone-based photoplethysmography (PPG) to detect pulse wave irregularities, which were confirmed using 14-day external ECG-recorders. The primary endpoint was newly diagnosed AF treated with OAC. After 6 months, participants were assigned to a second, cross-over study-phase. The efficacy of AF-screening in women and men was assessed by Cox-regression analysis. 5551 (31% females; 55% ≥ 65 years) of 67 488 invited policyholders free of AF participated in the study and were randomly assigned to digital screening (n = 2860) or usual care (n = 2691). Participation rate was significantly higher among men than women (8.7% vs. 7.3%; P < 0.001). Male sex was a significant predictor for reaching the primary endpoint (HR 1.74; 95% CI: 1.08-2.82, P = 0.023), which was pronounced in patients undergoing digital screening (HR 2.48; 95% CI: 1.52-4.05, P < 0.001). Digital screening did not significantly increase the detection rate of AF requiring OAC in women (HR 1.83; 95% CI: 0.74-4.54; P = 0.193; P-interaction = 0.563).

Conclusion: Men showed higher willingness to participate in this digital study and digital AF-screening was effective for them. While digital screening increased the detection rate of AF with OAC in women, the effect was not statistically significant, likely due to limited power.

Extended reality (XR) is an emerging technology currently finding its way into various medical fields. This systematic review aimed to compile a comprehensive overview of the current data on XR in cardiovascular medicine. To identify the currently available evidence of the applications of XR in cardiology, we searched PubMed and Web of Science until 31 July 2024 using predefined keywords. After screening, a total of 164 studies were included. Overall, the publications were characterized by very heterogeneous study designs. From the published data, it can already be deduced that XR can support every area of cardiology, from education (n = 31) and training (n = 36) to peri-procedural care (n = 78) and rehabilitation (n = 16). Extended reality offers a wide range of applications, and the aim of using these technologies is to optimize the clinical practice. However, these technologies are still in development, and randomized controlled trials are urgently needed to identify their benefits and limitations.

Aims: Large language models (LLMs) have shown potential in clinical decision support, but the influence of prompt design on their performance, particularly in complex cardiology decision-making, is not well understood.

Methods and results: We retrospectively reviewed 231 patients evaluated by our Heart Team for severe aortic stenosis, with treatment options including surgical aortic valve replacement, transcatheter aortic valve implantation, or medical therapy. We tested multiple prompt-design strategies using zero-shot (0-shot), Chain-of-Thought (CoT), and Tree-of-Thought (ToT) prompting, combined with few-shot prompting, free/guided-thinking, and self-consistency. Patient data were condensed into standardized vignettes and queried using GPT4-o (version 2024-05-13, OpenAI) 40 times per patient under each prompt (147 840 total queries). Primary endpoint was mean accuracy; secondary endpoints included sensitivity, specificity, area under the curve (AUC), and treatment invasiveness. Guided-thinking-ToT achieved the highest accuracy (94.04%, 95% CI 90.87-97.21), significantly outperforming few-shot-ToT (87.16%, 95% CI 82.68-91.63) and few-shot-CoT (85.32%, 95% CI 80.59-90.06; P < 0.0001). Zero-shot prompting showed the lowest accuracy (73.39%, 95% CI 67.48-79.31). Guided-thinking-ToT yielded the highest AUC values (up to 0.97) and was the only prompt whose invasiveness did not differ significantly from Heart Team decisions (P = 0.078). An inverted quadratic relationship emerged between few-shot examples and accuracy, with nine examples optimal (P < 0.0001). Self-consistency improved overall accuracy, particularly for ToT-derived prompts (P < 0.001).

Conclusion: Prompt design significantly impacts LLM performance in clinical decision-making for severe aortic stenosis. Tree-of-Thought prompting markedly improved accuracy and aligned recommendations with expert decisions, though LLMs tended toward conservative treatment approaches.

Aims: The recurrence rate of ventricular tachycardia (VT) after ablation remains high due to the difficulty in locating VT critical sites. This study proposes a machine learning approach for improved identification of ablation targets based on intracardiac electrograms (EGMs) features derived from standard substrate mapping in a chronic myocardial infarction (MI) porcine model.

Methods and results: Thirteen pigs with chronic MI underwent invasive electrophysiological studies using multipolar catheters (Advisor™ HD grid, EnSite Precision™). Fifty-six substrate maps and 35 068 EGMs were collected during sinus rhythm and pacing from multiple sites, including left, right, and biventricular pacing. Ventricular tachycardia was induced in all pigs, and a total of 36 VTs were localized and mapped with early, mid-, and late diastolic components of the circuit. Mapping sites within 6 mm from these critical sites were considered as potential ablation targets. Forty-six signal features representing functional, spatial, spectral, and time-frequency properties were computed from each bipolar and unipolar EGM. Several machine learning models were developed to automatically localize ablation targets, and logistic regressions were used to investigate the association between signal features and VT critical sites. Random forest provided the best accuracy based on unipolar signals from sinus rhythm map, provided an area under the curve of 0.821 with sensitivity and specificity of 81.4% and 71.4%, respectively.

Conclusion: This study demonstrates for the first time that machine learning approaches based on EGM features may support clinicians in localizing targets for VT ablation using substrate mapping. This could lead to the development of similar approaches in VT patients.

Aims: Heart failure (HF) is associated with high mortality and reduced quality of life (QoL). Interventions encouraging a healthy lifestyle and self-care can reduce morbidity and HF-related hospitalizations. We conducted a randomized controlled trial (RCT) to assess the impact of a digital health programme on QoL and clinical outcomes of patients. The programme included remote patient monitoring (RPM), self-care, HF education, and empowered positive lifestyle changes.

Methods and results: Patients (n = 175) received standard-of-care (SoC) at a HF outpatient clinic (control, n = 89) or SoC plus a digital health programme (intervention, n = 86) for 6 months, followed by a 6-month maintenance period. Compliance with RPM was 93% at 6 months. No significant between-group difference was found in the primary endpoint (health-related QoL), except in an exploratory subgroup of New York Heart Association class III patients, where the intervention group had a significantly smaller QoL decline (P = 0.023). For secondary endpoints, the intervention group had significantly greater improvements in self-care at 6 months (P < 0.001) and 12 months (P = 0.003), and in disease-specific knowledge at 12 months (P = 0.001). Several exploratory endpoints favoured the intervention, with significant improvements in triglycerides (P = 0.012), HbA1c (P = 0.014), and fasting glucose (P = 0.010). The TG/HDL cholesterol ratio and TG/glucose index improved significantly at both 6 and 12 months in between-group comparisons.

Conclusion: Although the digital programme did not improve health-related QoL, it led to benefits in other important outcomes such as self-care, disease-specific knowledge, and several key metabolic parameters.