European heart journal. Digital health最新文献

Aims: Patients with abdominal aortic aneurysms and peripheral arterial disease (arterial vascular diseases) carry a high disease burden and are likely to experience cardiovascular events. Novel strategies using artificial intelligence could identify which patients with arterial vascular diseases are at high risk of cardiovascular disease progression. Structured data dictionaries are needed to ensure high-quality, unbiased, and ethically sound data input for artificial intelligence models. The aim of this study was to obtain expert consensus-based data dictionaries that adhere to applicable ethical guidelines to support research on arterial vascular diseases.

Methods and results: The data dictionaries were created through a modified Delphi approach to achieve consensus among key opinion leaders in the cardiovascular field. First, data requirements were defined and variable longlists were created per disease through a literature review. Secondly, written feedback rounds were held. Lastly, face-to-face meetings were held to establish consensus on the final data dictionaries. During the whole process, ethical and legal experts on trustworthy artificial intelligence were involved to ensure adherence to corresponding guidelines and laws. The aneurysm data dictionary contains 312 variables, and the peripheral arterial disease data dictionary contains 325 variables. A total of 16 clinical experts were involved in the creation, including 12 vascular surgeons, two vascular medicine specialists, one cardiologist, and one gastroenterology surgeon and digital health expert.

Conclusion: Two expert consensus-based data dictionaries for use in clinical and artificial intelligence research on arterial vascular diseases were created, developed for application in research on predicting disease progression and cardiovascular risk.

Aims: Early detection of the need for coronary revascularization and timely intervention may reduce fatal events, but limited screening tools often leads to underdiagnosis. The aim of this study is to use a deep learning model (DLM) that utilizes electrocardiography (ECG) and the eXtreme Gradient Boosting (XGBoost) model to predict risk of coronary revascularization in the general population.

Methods and results: This study included patients with at least one ECG per patient. The development set comprised 113 451 patients for training a DLM. After excluding patients with elevated troponin I levels and those without follow-up records, the internal validation set consisted of 66 680 patients. The external validation was conducted using data from a community hospital. XGBoost predicted events based on demographic data and ECG features. The primary endpoint was coronary revascularization within 1 year. Model performance was evaluated using the C-index. The DLM stratified patients by risk of coronary revascularization within 1 year. The study included 51% males with a mean age of 53 years, 10% with diabetes, and a revascularization rate of 2.6%. High-risk patients had a hazard ratio of 9.77 (95% CI: 7.63-12.51) compared with low-risk patients. The C-index was 0.825 (95% CI: 0.81-0.84). Combining demographic and AI-ECG data, XGBoost achieved a C-index of 0.884 (95% CI: 0.87-0.89). Comparative C-index analysis revealed significantly different discriminative performance between models (P = 1.110223e-15).

Conclusions: The DLM demonstrates ECG's potential as a screening tool for coronary revascularization, enabling opportunistic detection and prompting further evaluation of high-risk patients.

Aims: The shift in mitral stenosis (MS) aetiology from rheumatic to calcific valve disease complicates distinguishing valve-related from myocardial-driven haemodynamic abnormalities. This study examines how left-heart myopathy influences flow velocity-based echocardiographic MS severity assessment and evaluates haemodynamic changes following mitral valve (MV) intervention at rest and during exercise.

Methods and results: The CircAdapt biophysical model was used to create a virtual cohort with varying MS severity, left ventricular (LV) compliance, and left atrial (LA) function. Mean gradient (MG) was evaluated alongside left-heart pressures at rest and during exercise. To study acute haemodynamic effects of MV intervention, the mitral valve's effective orifice area was restored to 5.9 cm². MG showed variation of 1 mmHg attributable to left-heart myopathy. Following virtual MV intervention for clinically significant MS, mean left atrial pressure (mLAP) decreased by 50% in patients with preserved myocardial function but remained elevated in those with LV and LA dysfunction due to persistently elevated LV end-diastolic pressure, resulting in persistently impaired exercise capacity.

Conclusion: Virtual patient cohorts suggest that MV intervention reduces MG but may not normalize mLAP in patients with impaired LV and LA function. Persistent myocardial dysfunction may limit both symptomatic and exercise capacity improvement, despite successful intervention. As percutaneous treatment options expand, distinguishing myocardial from valve-driven abnormalities is essential for accurate assessment, patient selection, and optimizing outcomes.

Aims: Cardiovascular diseases are the leading global cause of mortality, with ischaemic heart disease contributing significantly to the burden. Primary and secondary prevention strategies are essential to reducing the incidence and recurrence of acute myocardial infarction. Healthcare professionals are no longer the sole source of health education; the Internet, including tools powered by artificial intelligence, is also widely utilized. This study evaluates the accuracy and the readability of large language model (LLM)-generated information on cardiovascular primary and secondary prevention.

Methods and results: An observational study assessed LLM's responses to two tailored questions about acute myocardial infarction risk prevention. The LLM used was ChatGPT (4o version). Expert cardiologists evaluated the accuracy of each response using a Likert scale, while readability was assessed with the Flesch Reading Ease Score (FRES). ChatGPT-4o provided comprehensive and accurate responses for 15 out of 20 (75%) of the items. Readability scores were low, with median FRES indicating that both primary and secondary prevention content were difficult to understand. Specialized clinical topics exhibited lower accuracy and readability compared to the other topics.

Conclusion: The current study demonstrated that ChatGPT-4o provided accurate information on primary and secondary prevention, although its readability was assessed as difficult. However, clinical oversight still remains critical to bridge gaps in accuracy and readability and ensure optimal patient outcomes.

Aims: Quality of life (QoL) improvement is a primary driver for atrial fibrillation (AF) catheter ablation (CA), yet its determinants remain unclear. We aimed to identify patient phenotypes with distinct post-ablation QoL trajectories, determine their key predictors, and clarify their association with arrhythmia recurrence and reintervention.

Methods and results: We prospectively followed 213 patients (median age 60 years, 31% female) undergoing AF CA at a tertiary hospital for 2.2 years [interquartile range (IQR): 1.6-2.6]. A digital health application collected real-time electronic patient-reported outcomes (PROs), including the AF Effect on QoL (AFEQT) questionnaire. Reference charts were generated from QoL trajectories of recurrence-free patients. Machine learning (ML) identified subgroups with distinct QoL trajectories, and explainable artificial intelligence (AI) highlighted key predictors. Quality of life improved by +26 AFEQT points [95% confidence interval (CI): 18-33] within 3 months post-ablation and remained stable thereafter, despite significant heterogeneity in individual responses. Patients with AF recurrence showed significantly lower QoL gains (P = 0.010). Machine learning identified three phenotypes: a younger cluster with the largest QoL improvements, an emotive cluster with higher recurrence rates and minimal QoL benefits despite additional antiarrhythmic reinterventions, and an older cluster with established cardiovascular risk factors. Anxiety, age, and AF duration emerged as key discriminators.

Conclusion: ML defined three clinically coherent phenotypes, each exhibiting distinct QoL trajectories and ablation outcomes. Explainable AI clarified how individual psychological and biological traits interact to shape these outcomes, highlighting the potential for tailored multidisciplinary care beyond individualized rhythm control strategies.

Aims: Spontaneous cardioversion (SCV) is commonly observed in patients presenting to emergency departments (EDs) with primary atrial fibrillation (AF). Predicting SCV could facilitate timely discharge and avoid costly admissions. We sought to evaluate whether SCV could be predicted using artificial intelligence-enabled electrocardiograms (AI-ECGs) and whether this could produce cost savings.

Methods and results: We recruited patients presenting to EDs with primary AF throughout 2022-23. Patients were excluded if the outcome of their AF episode was unclear, or the ECG was not accessible. Spontaneous cardioversion prediction was attempted using ResNet50, EfficientNet, and DenseNet convolutional neural network (CNN) architectures and subsequently an ensemble learning model. We then performed a cost-minimization analysis to estimate the cost effect of a prediction-guided 'wait-and-see' protocol. There were 1159 presentations to the ED, of which 502 had sufficient data for inclusion. The median age was 74.0 years and 54.0% were women. Spontaneous cardioversion occurred in 227 (45.2%) patients and was more frequent in younger patients (P < 0.001). The ensemble learning model outperformed individual CNNs, achieving an accuracy of 69.7% (SD 5.91) and a receiver operating characteristic area under the curve (ROC AUC) of 0.742 (SD 0.037) with a sensitivity and specificity of 0.736 (SD 0.068) and 0.657 (SD 0.150), respectively. The per patient cost was $4681 if all patients were admitted, which reduced to $3398 with a prediction-guided 'wait-and-see' protocol with a 33.3% reduction in overall hospitalization.

Conclusion: Artificial intelligence-enabled electrocardiogram can predict SCV in patients presenting to EDs with primary AF, and a prediction-guided 'wait-and-see' protocol utilizing AI-ECG could lead to substantial cost savings and reduced hospitalization.

Aims: This study aims to investigate the ownership of wearable health devices across different demographic groups and usage patterns among Chinese adults.

Methods and results: This was a cross-sectional study, with all data originating from the Huawei Blood Pressure Health Study, a real-world study aimed at exploring blood pressure management through wearable devices in China. Data were remotely collected using mobile phones and Huawei Watch D from 23 February 2022 to 31 March 2024. The system utilized artificial intelligence algorithms to assess participants' risk of hypertension and provided risk alarm feedback via mobile phones and watches. A total of 75 918 participants from 31 provinces were included, with an average age of 47 years. Most of the participants were concentrated in the economically developed South China and East China regions. Among the participants, 73.8% used the Watch D for blood pressure monitoring, and 10.5% received risk alerts. The rate of blood pressure monitoring on the day they received the alert was 78%. However, the rate significantly decreased between 6 months and 1 year (Mann-Kendall test, Z = -2.85, P < 0.05). For hypertensive patients, the blood pressure monitoring rate was 84% on the day they joined the study and decreased over time (Mann-Kendall test, Z = -3.09, P < 0.05). However, it remained above 50% within 6 months.

Conclusion: This study provides evidence of the digital health divide in the utilization of wearable devices among the Chinese population. Additionally, it proposes a potentially follow-up interval for employing wearable devices for maintaining compliance with blood pressure monitoring.

Study registration: URL: https://www.chictr.org.cn/.

Unique identifier for huawei-bphs: ChiCTR2200057354.

Aims: Recurrent congestive episodes are a primary cause of hospitalizations in patients with heart failure. Hitherto, outpatient management adopts a reactive approach, assessing patients clinically through frequent follow-up visits to detect congestion early. This study aims to assess the capabilities of a self-supervised contrastive learning-derived risk index to detect episodes of acute decompensated heart failure (ADHF) in patients using continuously recorded wearable time-series data.

Methods and results: This is the protocol for a single-arm, prospective cohort pilot study that will include 290 patients with ADHF. Acute decompensated heart failure is diagnosed by clinical signs and symptoms, as well as additional diagnostics (e.g. NT-proBNP). Patients will receive standard-of-care treatment, supplemented by continuous wearable-based monitoring of vital signs and physical activity, and are followed for 90 days. During follow-up, study visits will be conducted and presentations without clinical ADHF will be referred to as 'regular' and data from these episodes will be presented to a deep neural network that is trained by a self-supervised contrastive learning objective to extract features from the time-series that are typical in regular periods. The model is used to calculate a risk index measuring the dissimilarity of observed features from those of regular periods. The primary outcome of this study will be the risk index's accuracy in detecting episodes with ADHF. As secondary outcome data integrity and the score in the validated questionnaire System Usability Scale will be evaluated.

Conclusion: Demonstrating reliable congestion detection through continuous monitoring with a wearable and self-supervised contrastive learning could assist in pre-emptive heart failure management in clinical care.

Clinical trial registration: The study was registered in the German clinical trials register (DRKS00034502).