Heart failure (HF) imposes an expanding global health burden, necessitating innovative approaches to education for both patients and clinicians. This review evaluates the evolving landscape of digital health tools in HF education and examines how these technologies may enhance accessibility, personalisation, and engagement in contemporary care. Emerging evidence demonstrates that digital solutions—ranging from remote educational platforms and interactive applications to AI-assisted learning and immersive reality technologies—can meaningfully improve patient self-management, support clinician knowledge acquisition, and strengthen overall care quality. These tools offer substantial advantages, including remote access to high-quality information, dynamic and interactive learning experiences, and opportunities for continuous monitoring. Nonetheless, challenges persist, particularly regarding equitable access, digital literacy, data quality, and integration into existing clinical workflows. Digital technologies hold considerable promise in optimising HF education for both patients and clinicians. When effectively implemented, they have the potential to improve patient outcomes, enhance clinical decision-making, and support more efficient healthcare delivery. Continued innovation—particularly in AI, virtual and augmented reality, and personalised learning systems—will be essential to address remaining limitations and fully realise the transformative potential of digital HF education.

Cuffless blood pressure (BP) monitoring devices represent a promising innovation in hypertension management. This scientific statement provides a comprehensive update on these emerging technologies, their specific validation requirements, their potential clinical applications, and their present and future challenges. These devices generate considerable interest by enabling non-invasive BP measurement without arterial occlusion, thereby eliminating the discomfort associated with traditional cuff-based monitoring, particularly during sleep. The technologies on which these devices are based comprise a heterogeneous group, primarily utilizing pulse wave propagation time or waveform analysis through contact or non-contact sensors. They can be categorized as continuous or intermittent, automated or manual, calibration-free or requiring cuff/demographic calibration, and wearable or stationary. This technological diversity necessitates validation protocols distinct from those used for conventional cuff-based monitors, with specific requirements for each device category. Potential clinical applications include widespread out-of-office BP monitoring, unbiased assessment of circadian BP patterns and BP variability, improved detection of nocturnal hypertension, enhanced treatment adherence and long-term BP control, and continuous monitoring in hospital settings. Additionally, their lower cost compared with conventional technologies could enhance the early detection of hypertension in resource-limited settings. However, due to insufficient accuracy validation, this scientific statement does not recommend their use in clinical decisions in spite of their potential interest, in line with international guidelines not recommending their use in hypertension management. Key challenges ahead include developing standardized validation protocols, establishing normative BP data, managing the resulting burden on clinicians in handling huge volumes of data, exploring additional haemodynamic parameters, and advancing sensor technology, mathematical models, and algorithms.

Cuffless blood pressure (BP) monitoring devices represent a promising innovation in hypertension management. This scientific statement provides a comprehensive update on these emerging technologies, their specific validation requirements, their potential clinical applications, and their present and future challenges. These devices generate considerable interest by enabling noninvasive BP measurement without arterial occlusion, thereby eliminating the discomfort associated with traditional cuff-based monitoring, particularly during sleep. The technologies on which these devices are based comprise a heterogeneous group, primarily utilizing pulse wave propagation time or waveform analysis through contact or noncontact sensors. They can be categorized as continuous or intermittent, automated or manual, calibration-free or requiring cuff/demographic calibration, and wearable or stationary. This technological diversity necessitates validation protocols distinct from those used for conventional cuff-based monitors, with specific requirements for each device category. Potential clinical applications include widespread out-of-office BP monitoring, unbiased assessment of circadian BP patterns and BP variability, improved detection of nocturnal hypertension, enhanced treatment adherence and long-term BP control, and continuous monitoring in hospital settings. Additionally, their lower cost compared with conventional technologies could enhance the early detection of hypertension in resource-limited settings. However, due to insufficient accuracy validation, this scientific statement does not still recommend their use in clinical decisions, in line with international guidelines not recommending their use in hypertension management. Key challenges ahead include developing standardized validation protocols, establishing normative BP data, manage the resulting burden on clinicians in handling huge volumes of data, exploring additional hemodynamic parameters, and advancing sensor technology, mathematical models, and algorithms.

Accurate 3D representations of cardiac structures allow quantitative analysis of anatomy and function. In this work, we propose a method for reconstructing complete 3D cardiac shapes from segmentations of sparse planes in CT angiography (CTA) for application in 2D transthoracic echocardiography (TTE). Our method uses a neural implicit function to reconstruct the 3D shape of the cardiac chambers and left-ventricle myocardium from sparse CTA planes. To investigate the feasibility of achieving 3D reconstruction from 2D TTE, we select planes that mimic the standard apical 2D TTE views. During training, a multi-layer perceptron learns shape priors from 3D segmentations of the target structures in CTA. At test time, the network reconstructs 3D cardiac shapes from segmentations of TTE-mimicking CTA planes by jointly optimizing the latent code and the rigid transforms that map the observed planes into 3D space. For each heart, we simulate four realistic apical views, and we compare reconstructed multi-class volumes with the reference CTA volumes. On a held-out set of CTA segmentations, our approach achieves an average Dice coefficient of 0.86 +/- 0.04 across all structures. Our method also achieves markedly lower volume errors than the clinical standard, Simpson ' s biplane rule: 4.88 +/- 4.26 mL vs. 8.14 +/- 6.04 mL, respectively, for the left ventricle; and 6.40 +/- 7.37 mL vs. 37.76 +/- 22.96 mL, respectively, for the left atrium. This suggests that our approach offers a viable route to more accurate 3D chamber quantification in 2D transthoracic echocardiography.

This review synthesizes recent progress in applications of artificial intelligence to heart failure care, including phenotyping, risk stratification, imaging interpretation, and point-of-care decision support, and delineates barriers that currently limit safe and equitable clinical translation. Clinical datasets remain heterogeneous and incomplete; fragmentation across electronic records, telemetry, and imaging repositories constrains generalizability and external validity. Underrepresentation of key subgroups and outcome misclassification introduce systematic error that can widen disparities. Performance drifts as therapies and workflows evolve, yet monitoring after deployment is uncommon. Model opacity hinders error analysis and clinician trust. Regulatory and data-sharing frameworks are evolving and inconsistent, complicating multisite validation and ongoing surveillance. Mitigation strategies with the strongest support include rigorous cohort curation; transparent reporting; geographic and temporal external validation; prospective pilots with prespecified safety checks; bias auditing with equity metrics; concise documentation such as model cards and factsheets; continuous monitoring with clear contingency and rollback plans; and human oversight embedded throughout governance. Embedding safeguards into development and implementation can enable AI to deliver measurable value in heart failure care while protecting patient safety and equity. Immediate priorities are robust evaluation, routine surveillance for drift and harm, and alignment with outcomes that matter to patients.

AIM:Transesophageal echocardiography (TEE) is the modality of choice for mitral valve (MV) interventional planning. However, computed tomography (CT) has been proposed as a standard screening tool for MV interventions to assess the risk of injury to the left circumflex artery. We aimed to develop a pipeline to fuse CT and MV modalities and create three-dimensional (3D) printable models of the MV apparatus to enhance interventional planning and assessed its usability among clinicians. METHODS AND RESULTS:The design, production, and assessment of the 3D-printed personalized models were based on TEE enriched with data from CT. The digital pipeline consisted of fusion with a mutual information algorithm using 3D Slicer (Slicer) and Elastix toolboxes. Flexible 3D printing was performed using Agilus 30 Clear. The pipeline was feasible for achieving semiautomatic fusion of anatomical structures related to MV interventional planning. Visualization of fused synergistic information for 3D planning could be provided in three distinct cases of MV regurgitation (secondary MR with tenting, flail leaflet, and prolapse). The 3D printing resulted in a flexibility in line with actual tissue allowing for tactile modification. An average System Usability Score of 71 indicates a moderately good usability among imaging cardiologists, intervention cardiologists, and cardiac surgeons. CONCLUSION:The presented pipeline with digital planning and personalized 3D printing has reached the technology readiness level for application in mitral valve interventions, and prospective clinical trials with endpoints of surgical effectiveness. Comprehensive and efficient interactions between clinicians and technical staff are essential to establish well-designed patient-specific interventions.

This work presents a novel approach to achieving temporally consistent mitral annulus landmark localization in echocardiography videos using sparse annotations. Our method introduces a self-supervised loss term that enforces temporal consistency between neighboring frames, which smooths the position of landmarks and enhances measurement accuracy over time. Additionally, we incorporate realistic field-of-view augmentations to improve the recognition of missing anatomical landmarks. We evaluate our approach on both a public and private dataset, and demonstrate significant improvements in Mitral Annular Plane Systolic Excursion (MAPSE) calculations and overall landmark tracking stability. The method achieves a mean absolute MAPSE error of 1.81 +/- 0.14 mm, an annulus size error of 2.46 +/- 0.31 mm, and a landmark localization error of 2.48 +/- 0.07 mm. Finally, it achieves a 0.99 ROC-AUC for recognition of missing landmarks.

Background: Deep learning applications may assist in automatically detecting coronary arteries on invasive coronary angiography (ICA). Objectives: The authors aimed to train deep learning models for the segmentation of coronary arteries and the detection of significant stenoses on ICA, conduct external validation, and compare the performance with expert variabilities. Methods: ICA studies from Amsterdam University Medical Centers (center 1) and Emory University Hospital (center 2) were retrospectively collected. Contours of the main coronary arteries and their ≥50% stenoses were manually segmented using dedicated software. Deep learning–based models were created using data from center 1, center 2, and both centers. The performance of the models was assessed on unseen data and compared to expert variability. Results: A total of 10,573 ICA images were used to train models: 9,065 from center 1 (n = 2,624) and 1,508 (n = 456) from center 2. Validation was done on 186 center 1 images and 123 center 2 images. The segmentation model trained on data sets from both centers had the highest median Dice coefficient (0.86; IQR: 0.81-0.88). The stenoses detection algorithm trained on both centers achieved a detection rate of 0.67 (95% CI: 0.63-0.71), similar to expert agreement (0.65; 95% CI: 0.63-0.68). The model trained on the data with the most stenoses yielded the highest stenosis detection rate (0.67; 95% CI: 0.64-0.71). When matched for data set size and proportion of stenoses, the models trained on both centers performed similarly. Conclusions: The models achieved performance levels on par with experts in coronary artery segmentation and detection of significant stenoses in the main arteries.

AIMS:To understand prognostic differences between sexes in (subtypes of) secondary mitral valve regurgitation (SMR) and to identify avenues for improvement. METHOD AND RESULTS:In this retrospective study, all consecutive patients diagnosed with moderate or severe SMR by echocardiographic assessment between January 1, 2014, and June 1, 2021 were included. Sex-specific analyses were performed using Cox proportional hazards analysis, adjusted for significant covariates. A total of 1245 patients with SMR (43% female) were included. Females more often had atrial SMR (233 (29%) females vs. 200 (21%) males, p < 0.01), males more often ischemic SMR (100 females (12%) vs. 245 males (25%), p < 0.01), and there were no significant differences between sexes in the proportion of non-ischemic SMR (199 (25%) females vs. 268 (28%) males, p = 0.99). The estimated 5-year survival was 70% (CI = 68%, 73%). Median follow-up was 4.3 years [2.7-6.2], 236 males and 128 females died during follow-up. Females had a better survival than males in a multivariable Cox model (HR = 0.67, p < 0.01). CONCLUSION:Overall survival in patients with SMR was low with an estimated 5-year survival of 70%. Females had a better survival in patients with SMR than males. The lower survival in males with SMR might be due to a larger proportion of atrial SMR in females, fewer patients with ischemic SMR, and lower ejection fractions in males with non-ischemic SMR. The current focus on rapid heart failure medication optimization may improve the prognosis of the most vulnerable group; future studies can be directed to see whether this will be the case.

Accurate segmentation of the mitral valve in transthoracic echocardiography (TTE) enables the extraction of various anatomical parameters that are important for guiding clinical management. However, manual mitral valve segmentation is time-consuming and prone to interobserver variability. To support robust automatic analysis of mitral valve anatomy, we propose a novel AI-based method for mitral valve segmentation and anatomical measurement extraction. We retrospectively collected a set of echocardiographic exams from 1756 consecutive patients with suspected coronary artery disease. For these patients, we retrieved expert-defined scores for mitral regurgitation (MR) severity and follow-up characteristics. PLAX-view videos were automatically identified, and the inside border of the mitral valve leaflets were manually segmented in 182 patients. To automatically segment mitral valve leaflets, we designed a deep neural network that takes a video frame and outputs a distance- and classification-map for each leaflet, supervised by manual segmentations. From the resulting automatic segmentations, we extracted leaflet length, annulus diameter, tenting area, and coaptation length. To demonstrate the clinical relevance of these automatically extracted measurements, we performed univariable and multivariable Cox Regression survival analysis, with the clinical endpoint defined as heart-failure hospitalization or all-cause mortality. We trained the segmentation model on annotated frames of 111 patients, and tested segmentation performance on a set of 71 patients. For the survival analysis, we included 1,117 patients (mean age 64.1 ± 12.4 years, 58% male, median follow-up 3.3 years). The trained model achieved an average surface distance of 0.89 mm, a Hausdorff distance of 3.34 mm, and a temporal consistency score of 97%. Additionally, leaflet coaptation was accurately detected in 93% of annotated frames. In univariable Cox regression, automated annulus diameter (>35 mm, hazard ratio (HR) = 2.38, p<0.001), tenting area (>2.4 cm2, HR = 2.48, p<0.001), tenting height (>10 mm, HR = 1.91, p<0.001), and coaptation length (>3 mm, HR = 1.53, p = 0.007) were significantly associated with the defined clinical endpoint. For reference, significant MR by expert assessment resulted in an HR of 2.31 (p<0.001). In multivariable Cox Regression analysis, automated annulus diameter and coaptation length predicted the defined endpoint as independent parameters (p = 0.03 and p = 0.05, respectively). Our method allows accurate segmentation of the mitral valve in TTE, and enables fully automated quantification of key measurements describing mitral valve anatomy. This has the potential to improve risk stratification for cardiac patients.

This review examines the potential benefits of non-invasive remote monitoring in patients with heart failure (HF), focusing on early detection of clinical deterioration and reducing hospitalizations. Key questions addressed include: Can remote monitoring prevent hospitalisations in patients with HF? Does it improve quality of life and promote self-care? Is it cost-effective? Can artificial intelligence (AI) facilitate its implementation? Monitoring with non-wearable and wearable devices reduces hospitalizations by detecting early signs of deterioration and enhancing self-care behaviour. While the initial investment can be high, the long-term cost-effectiveness is supported by reduced hospitalisations. AI is increasingly integrated into monitoring systems, enhancing predictive accuracy and personalized care. Remote monitoring reduces mortality and hospitalisations in patients with HF, with benefits in cost-effectiveness, and the potential to optimize care delivery by integrating AI. Future research should focus on identifying monitoring strategies for specific HF populations, such as patients with advanced HF.

Aims Home telemonitoring systems (hTMS) have demonstrated positive effects on hospitalizations and mortality for patients with heart failure (HF). However, there is a high degree of heterogeneity in the development and integration of hTMS. This limits the potential for large-scale impact and equitable access to high-quality remote care. Therefore, this manuscript describes a detailed protocol of a scalable high-volume hTMS system which has been standardized and implemented across seven large teaching hospitals in The Netherlands (Graphical Abstract). Methods A multicentre, qualitative, stakeholder-inclusive approach was applied from the early stages of the hTMS protocol development. In January 2023, a HF-core team was established, comprising cardiologists, HF nurse specialists, and experts in implementation and process optimization, from all hospitals. The team developed unified protocols for remote monitoring of vital signs (blood pressure, heart rate, weight), including standardized cut-off values to generate automated alerts. In addition, protocols were established on how to rapidly titrate HF medication with the use of hTMS. A new department, the Medical Service Centre was established in each site to monitor these alerts and contact patients. Conclusion This manuscript describes the development of the hybrid care pathway and the operational protocol of the hTMS. Future publications will elaborate on outcomes related to implementation success, clinical endpoints, and cost-effectiveness, which are currently being collected and evaluated as part of the programmes prospective design.

Guideline-directed medical therapy (GDMT) has clear benefits on morbidity and mortality in patients with heart failure; however, GDMT use remains low. In the multicenter, open-label, investigator-initiated ADMINISTER trial, patients (n = 150) diagnosed with heart failure and reduced ejection fraction (HFrEF) were randomized (1:1) to receive usual care or a strategy using digital consults (DCs). DCs contained (1) digital data sharing from patient to clinician (pharmacotherapy use, home-measured vital signs and Kansas City Cardiomyopathy Questionnaires); (2) patient education via a text-based e-learning; and (3) guideline recommendations to all treating clinicians. All remotely gathered information was processed into a digital summary that was available to clinicians in the electronic health record before every consult. All patient interactions were standardly conducted remotely. The primary endpoint was change in GDMT score over 12 weeks (ΔGDMT); this GDMT score directly incorporated all non-conditional class 1 indications for HFrEF therapy with equal weights. The ADMINISTER trial met its primary outcome of achieving a higher GDMT in the DC group after a follow-up of 12 weeks (ΔGDMT score in the DC group: median 1.19, interquartile range (0.25, 2.3) arbitrary units versus 0.08 (0.00, 1.00) in usual care; P < 0.001). To our knowledge, this is the first multicenter randomized controlled trial that proves a DC strategy is effective to achieve GDMT optimization. ClinicalTrials.gov registration: NCT05413447 .

Purpose:Interpreting echocardiographic exams requires substantial manual interaction as videos lack scan-plane information and have inconsistent image quality, ranging from clinically relevant to unrecognizable. Thus, a manual prerequisite step for analysis is to select the appropriate views that showcase both the target anatomy and optimal image quality. To automate this selection process, we present a method for automatic classification of routine views, recognition of unknown views, and quality assessment of detected views. Approach:We train a neural network for view classification and employ the logit activations from the neural network for unknown view recognition. Subsequently, we train a linear regression algorithm that uses feature embeddings from the neural network to predict view quality scores. We evaluate the method on a clinical test set of 2466 echocardiography videos with expert-annotated view labels and a subset of 438 videos with expert-rated view quality scores. A second observer annotated a subset of 894 videos, including all quality-rated videos. Results:The proposed method achieved an accuracy of 84.9 % ± 0.67 for the joint objective of routine view classification and unknown view recognition, whereas a second observer reached an accuracy of 87.6%. For view quality assessment, the method achieved a Spearman's rank correlation coefficient of 0.71, whereas a second observer reached a correlation coefficient of 0.62. Conclusion:The proposed method approaches expert-level performance, enabling fully automatic selection of the most appropriate views for manual or automatic downstream analysis.

The European Society of Cardiology guidelines for the management of adult congenital heart disease patients recommend screening for arrhythmias and bradycardias in symptomatic patients, often being done by means of an ambulatory 24-48 -hour Holter or implantable loop recorder (ILR). However, nowadays non-invasive instruments, such as patches, smartwatches and smartphones based on single -lead ECGs that perform extended monitoring, are also available. The aim of this narrative review was to assess whether these instruments, when they detect arrhythmias and bradycardias in patients with adult congenital heart disease, will lead to meaningful changes in clinical care. Clinically meaningful changes include adjustment of medication, cardioversion, electrophysiology study, ablation or implantation of a cardiovascular implantable electronic device. The following monitoring instruments are discussed: cumulative Holter, 2 -week continuous monitor, smartwatchand smartphone-based single -lead ECG, and ILR. The diagnostic yield of extended rhythm monitoring is high, and varies between 18% (smartphone-based single -lead ECG) and 41% with ILR. In conclusion, contemporary arrhythmia screening includes various new non-invasive technologies that are promising new tools as an alternative to Holter monitoring or ILR. However, the optimal mode of detection is still unclear due to the lack of head -to -head comparisons.

AIMS:To describe the clinical practice and educational preparation of heart failure (HF) nurses across Europe and determine the key differences between countries. METHODS AND RESULTS:A survey tool was developed, in English, by the Heart Failure Association Patient Care committee of the European Society of Cardiology (ESC). It was translated into eight languages, before electronically disseminated by nurse ambassadors, presidents of HF national societies and through social media. A total of 837 nurses involved in the daily care of patients with HF from 15 countries completed the survey. Most nurses, 78% (n = 395) worked within a hospital outpatient setting, and 51% (n = 431) had access to a specialized HF multidisciplinary team. Nurses performed a range of activities including patient education to promote self-care, virtual and in-person symptom monitoring. A third had more than 5-year experience in cardiac care and 22% (n = 182) prescribed HF medications. There was a significant correlation between HF nurses that prescribed HF medications and access to a specialist multidisciplinary team (p = 0.04). A small number of nurses, mainly from Belgium, supported invasive monitoring (n = 68, 8%) with 14% (n = 120) of mostly Danish nurses supporting exercise programmes. The majority of nurses surveyed were committed to further academic professional development, with 41% (n = 343) having completed a HF course. CONCLUSION:The role of the HF nurse varies across Europe, however involvement in patient education, symptom monitoring and follow-up remain core to their practice. In specific activities including the prescribing of HF medications and involvement in invasive monitoring, practice has advanced with collaboration in the multidisciplinary team. Consequently, harmonization of education, training and career pathways are required to standardize HF care aligned with expert guidelines across Europe.

Purposeof Review Guideline-directed medical therapy (GDMT) underuse is common in heart failure (HF) patients. Digital solutions have the potential to support medical professionals to optimize GDMT prescriptions in a growing HF population. We aimed to review current literature on the effectiveness of digital solutions on optimization of GDMT prescriptions in patients with HF. Recent Findings We report on the efficacy, characteristics of the study, and population of published digital solutions for GDMT optimization. The following digital solutions are discussed: teleconsultation, telemonitoring, cardiac implantable electronic devices, clinical decision support embedded within electronic health records, and multifaceted interventions. Effect of digital solutions is reported in dedicated studies, retrospective studies, or larger studies with another focus that also commented on GDMT use. Overall, we see more studies on digital solutions that report a significant increase in GDMT use. However, there is a large heterogeneity in study design, outcomes used, and populations studied, which hampers comparison of the different digital solutions. Barriers, facilitators, study designs, and future directions are discussed. Summary There remains a need for well-designed evaluation studies to determine safety and effectiveness of digital solutions for GDMT optimization in patients with HF. Based on this review, measuring and controlling vital signs in telemedicine studies should be encouraged, professionals should be actively alerted about suboptimal GDMT, the researchers should consider employing multifaceted digital solutions to optimize effectiveness, and use study designs that fit the unique sociotechnical aspects of digital solutions. Future directions are expected to include artificial intelligence solutions to handle larger datasets and relieve medical professional’s workload.

Aims The European Society of Cardiology guidelines recommend risk stratification with limited clinical parameters such as left ventricular (LV) function in patients with chronic coronary syndrome (CCS). Machine learning (ML) methods enable an analysis of complex datasets including transthoracic echocardiography (TTE) studies. We aimed to evaluate the accuracy of ML using clinical and TTE data to predict all-cause 5-year mortality in patients with CCS and to compare its performance with traditional risk stratification scores.Methods and results Data of consecutive patients with CCS were retrospectively collected if they attended the outpatient clinic of Amsterdam UMC location AMC between 2015 and 2017 and had a TTE assessment of the LV function. An eXtreme Gradient Boosting (XGBoost) model was trained to predict all-cause 5-year mortality. The performance of this ML model was evaluated using data from the Amsterdam UMC location VUmc and compared with the reference standard of traditional risk scores. A total of 1253 patients (775 training set and 478 testing set) were included, of which 176 patients (105 training set and 71 testing set) died during the 5-year follow-up period. The ML model demonstrated a superior performance [area under the receiver operating characteristic curve (AUC) 0.79] compared with traditional risk stratification tools (AUC 0.62-0.76) and showed good external performance. The most important TTE risk predictors included in the ML model were LV dysfunction and significant tricuspid regurgitation.Conclusion This study demonstrates that an explainable ML model using TTE and clinical data can accurately identify high-risk CCS patients, with a prognostic value superior to traditional risk scores. Graphical Abstract CCS, chronic coronary syndrome; eGFR, estimated glomerular filtration rate; LV, left ventricular; TTE, transthoracic echocardiography.