Digital Technologies in Cardiology: From Continuous Monitoring to Predictive Medicine

Introduction

Cardiovascular diseases (CVDs) represent the leading cause of morbidity and mortality worldwide, generating a significant burden on healthcare systems. Traditional cardiology is confronted with significant limitations, such as delayed diagnosis, intermittent monitoring, and a predominantly reactive therapeutic approach. In this context, the emergence and integration of digital health technologies mark the transition toward predictive, personalized, and prevention-oriented cardiology. The aim of this article is to analyze the transformation of cardiology through the lens of digital technologies and their impact on the prevention, diagnosis, and management of cardiovascular diseases. Although the evolution of digital technologies in cardiovascular research is relatively recent, their clinical use has demonstrated relevant progress in morbidity and mortality among patients with CVD. From a research perspective, it is essential to understand the emergence of these technologies, their development pace, current themes of interest, and the field’s temporal evolution [1].

Technological advances in the diagnosis of cardiovascular diseases also represent a major public health strategy. Integrating these solutions into clinical practice enables early detection and the initiation of personalized treatments, with the potential to significantly reduce CVD-associated morbidity and mortality. In addition, the use of telemedicine and telemonitoring contributes to resource optimization and improved access to high-quality medical care, representing an essential step in reducing the global burden of cardiovascular diseases [2]. The development of machine learning (ML) and digital health technologies is redefining the future of cardiovascular prevention. The ability of ML to extract meaningful information from complex medical datasets helps guide clinical decisions; however, this aspect must be balanced against challenges related to privacy, safety, equity, and clinical interpretability [3].

In the future era of digital health, the complex interplay among preventive medicine, primary, secondary, and tertiary prevention will be supported by genomics, artificial intelligence, bioengineering, wearable devices, and telemedicine. Combining these technologies supports a considerable potential of improving medical outcomes and the efficiency of healthcare systems [4]. Artificial intelligence in cardiology must progress beyond simple task automation and should focus on augmenting human clinical expertise, facilitating proactive cardiovascular care based on precision medicine. By leveraging computational advantages while managing its limitations, cardiology is advancing toward an era of transformative innovation beyond the limits of traditional diagnostic and therapeutic paradigms [5]. Systematic literature analyses show that current machine learning methods for diagnosing heart diseases face various challenges, for example, data imbalance, thus limiting their clinical applicability. Nevertheless, these approaches contribute to improving data-driven decision-making processes [6]. Other studies emphasize the critical role of artificial intelligence in rethinking diagnostic and treatment methods to improve patient outcomes [7], as well as emerging trends in supervised prediction algorithms that increase diagnostic accuracy and guide future research directions [8]. In the field of arrhythmia monitoring, long-term continuous ambulatory ECG monitors and external loop recorders have proven more effective than 24-hour Holter monitoring in detecting arrhythmic symptoms, with no significant differences between the two technologies [9]. Moreover, remote patient monitoring interventions can reduce the use of acute care services when designed according to patient characteristics, provider factors, and implementation context [10].

Materials and Methods

Study design

The objective of this article is to examine the digital transformation of cardiology, a process that redefines traditional paradigms of diagnosis, monitoring, and treatment through the integration of connected devices, digital biomarkers, telemedicine, and artificial intelligence. The article included studies published between 2015 and 2026 that investigated: the global burden of cardiovascular diseases; the limitations of traditional cardiology (late diagnosis, discontinuous monitoring, reactive treatment); and the emergence and impact of digital health technologies.

Data sources and search strategy

Searches were performed in databases relevant to cardiology and digital technologies applied in cardiology: PubMed, ScienceDirect, and Google Scholar. Search strategies were adapted for each database and included combinations of frequently used field-specific terms connected by Boolean operators (AND, OR): digital health, cardiology, wearable devices, digital biomarkers, artificial intelligence, predictive medicine. Examples of search expressions used: “digital health AND cardiology”, “wearable devices AND cardiovascular disease”, “artificial intelligence AND cardiac diagnosis”, “digital biomarkers AND heart disease”.

Eligibility criteria

Studies were included if they met at least one of the following criteria: clinical, observational, meta-analytical, or review studies relevant to digital health in cardiology; studies evaluating wearable devices, telemedicine, digital biomarkers, or artificial intelligence applications in the prevention, diagnosis, or management of cardiovascular diseases; articles published in English or Romanian between 2015 and 2026. Excluded were: articles without full-text availability; studies not relevant to digital cardiology; duplicate publications or studies with insufficient data.

Study selection

Study selection was conducted in two stages, i.e., screening of titles and abstracts to assess relevance, then an eligibility assessment based on full-text review. Duplicates were removed prior to full-text analysis. A total of 81 studies were ultimately included. The selected studies were analyzed and thematically organized into the main domains of digital health applied in cardiology: wearable devices and continuous monitoring; digital biomarkers; telemedicine and remote management; artificial intelligence and predictive medicine.

Results

1. Wearable devices

We analyze the role of these devices in the screening and remote diagnosis of common cardiovascular diseases, such as arrhythmias, as well as in the management of patients with existing cardiovascular conditions, for example, heart failure. Recent literature provides a comprehensive overview of wearable devices (Table 1). To date, challenges such as device accuracy, clinical validity, the lack of standardized regulatory policies, and concerns regarding patient data privacy continue to limit the widespread adoption of smart wearable technologies in clinical practice. Recommendations for addressing these challenges are presented, along with a simple and practical “ABCD”-type guide tailored to physicians’ specific needs, aimed at accelerating the integration of these devices into clinical workflows to optimize patient care [11].

This review synthesizes the characteristics of wearable devices and the associated machine learning techniques. Relevant research studies illustrating the role of these devices in the screening and management of cardiovascular conditions are described, while directions for future research are also identified. Finally, the challenges limiting the widespread use of wearable devices in cardiovascular medicine are highlighted, and short- and long-term solutions are proposed to facilitate their integration into clinical practice [12].

Wearable technology lies at the intersection of precision cardiovascular medicine, providing continuous, non-invasive, evidence-based data on patients’ health status. The convergence of AI, the Internet of Medical Things (IoMT), and real-world data integration positions wearable devices as essential tools for risk stratification and remote management. Future directions should prioritize standardized validation frameworks, strengthened cybersecurity, and equitable global access to maximize clinical and population-level impact [13]. Recent data suggest that wearable electrocardiograms perform comparably to conventional monitoring devices and may help reduce healthcare costs. However, challenges related to accessibility, data privacy, and the need to improve accuracy persist. Additional studies are required to critically evaluate existing limitations, given the significant potential of these devices to improve cardiovascular and overall health [14].

Heart failure is a progressive condition associated with increased morbidity and mortality. Early diagnosis and treatment can reduce hospitalizations and readmissions and improve quality of life. Current developments in wearable technology have transformed heart failure management, but their clinical integration requires careful evaluation of technical, clinical, and ethical challenges, including performance, regulation, and data protection [15].

The literature indicates that when integrated with telemonitoring, wearable devices can increase physical activity participation, improving peak oxygen consumption (VO₂peak) and quality of life in patients with coronary artery disease; physical function and quality of life in patients with heart failure; and walking capacity in patients with peripheral artery disease. These devices can detect atrial fibrillation, guide exercise timing, and safely monitor exercise intensity in patients with implantable cardiac devices. Real-time feedback enhances motivation and adherence, amplifying the benefits of cardiovascular rehabilitation programs [16].

Devices such as Apple Watch Series 9, Fitbit Charge 6, Garmin vívosmart 5, and Oura Ring Gen3 have proven suitable for monitoring cardiovascular function in community-dwelling adults. The systematic selection approach can also be extended to other physiological and behavioral variables [17].

Algorithms based on smartwatches show a strong correlation with atrial fibrillation burden determined by implantable cardiac monitoring and high clinical sensitivity for detecting recurrences, outperforming conventional non-invasive strategies. These findings support their use as a scalable alternative for rhythm monitoring after ablation [18].

Available data indicate excellent diagnostic accuracy, suggesting that these devices may represent an appropriate and accessible option for patients [19]. They demonstrate high diagnostic performance for atrial fibrillation and ST-segment abnormalities, especially in supervised settings. However, inconclusive recordings and algorithmic limitations remain important barriers, requiring real-world validation and algorithm optimization [20].

Compared with traditional methods, smartwatches enable more efficient detection of recurrences, characterization of arrhythmic burden, symptom–rhythm correlation, and increased patient engagement. Nevertheless, limitations such as motion artifacts, false-positive alerts, dependence on adherence, and issues related to regulation, interoperability, and privacy persist. Integrating these technologies into evidence-guided care pathways could allow more proactive and personalized management of atrial fibrillation [21].

The integration of wearable technology into healthcare systems can be helpful in facilitating early diagnosis, patient engagement, and continuous monitoring of cardiac health. Despite ethical considerations and inequalities in access, the potential benefits outweigh the challenges. Increased awareness, interdisciplinary collaboration, and further research are needed to optimize accuracy and support the widespread adoption of these technologies [22].

2. Digital biomarkers

Heart rate variability (HRV) indicates autonomic regulation and has become a digital biomarker with improtant applications in both clinical care and operational performance. Recent literature provides a comprehensive overview of digital biomarkers (Table 2). Considering HRV as a dual-use tool enables the connection between the medical field and operational human performance: the same cardiac data that can anticipate clinical events in patients may also signal the risk of exhaustion or overload in high-stress professional contexts. However, optimal use of this biomarker requires continuous data collection, validated artificial intelligence algorithms, privacy protection, and clear usage guidelines. Under these conditions, HRV becomes not only a monitoring tool but also a practical and ethical support for decision-making in clinical and operational environments [23].

The coefficient of variation of heart rate variability (HRV-CV) serves as an indicator of daily cardiac autonomic fluctuations and has potential as a scalable digital biomarker for behavioral monitoring and health risk stratification. Measuring HRV-CV during sleep provides a robust estimate of daily HRV variability; an analysis of nearly two million recordings from more than 21,000 individuals demonstrated that five nights of monitoring are sufficient for reliable seven-day estimates. Higher HRV-CV values are associated with greater alcohol consumption, lower physical activity levels, reduced sleep duration and regularity, older age, and increased body mass index (BMI). These findings provide the first large-scale characterization of HRV-CV and support its utility for behavioral monitoring and risk stratification [24].

In recent years, clinical evidence regarding digital biomarkers has been systematically evaluated across a variety of populations, interventions, devices, and sensor technologies, with a predominance of physical activity measurements and cardiac monitoring. The classification of behavioral and physiological data using the World Health Organization’s ICF framework has proven applicable for organizing the wide range of identified digital biomarkers. Determining the true clinical value of these biomarkers requires systematic assessment of the quality and consistency of evidence regarding their impact on health outcomes [25].

Telemetry units are useful for providing continuous monitoring of vital signs and electrocardiographic data, parameters that function as digital signatures of physiological status and may facilitate the detection of anomalies preceding cardiac arrest. The available data suggest that dynamic changes in vital signs may contribute to the prediction of in-hospital cardiac arrest. However, there is still no consensus regarding the optimal methods for analyzing these digital biomarkers, and large prospective studies are needed to validate their predictive value in clinical practice [26].

3. Biometric sensors

Recent literature provides a comprehensive overview of biometric sensors (Table 3). CVDs are still among the leading causes of mortality worldwide, tehrefore long-term and real-time monitoring of cardiovascular parameters is essential for the early identification of abnormalities and the initiation of interventions at the optimal moment. In this context, research interest has shifted toward developing flexible, wearable, or implantable sensors capable of continuously recording relevant physiological indicators. Among the available categories, mechanical sensors can directly reflect pressure fluctuations in the heart and blood vessels, offering high sensitivity and versatility. Four major classes of mechanical sensors—capacitive, piezoresistive, piezoelectric, and triboelectric—are described as recent developments for cardiovascular monitoring. Relevant biomechanical phenomena (e.g., arterial and endocardial pressure, pulse wave, and heart rhythm) and associated monitoring methods are also presented. Finally, the usefulness of continuous monitoring in the management of vascular diseases and the barriers to its translation into clinical practice are discussed [27].

Continuous monitoring of cardiovascular parameters can facilitate early detection of clinical deterioration and timely intervention. The development of flexible wearable/implantable sensors has accelerated, and mechanical sensors have emerged due to their ability to capture pressure variations within the cardiovascular system, combining high sensitivity with adequate flexibility for prolonged use. The paper synthesizes recent advances in sensors based on capacitive, piezoresistive, piezoelectric, and triboelectric principles, as well as the physical-mechanical mechanisms that can be monitored (pulse wave, blood pressure, heart rhythm, endocardial pressure). Challenges related to clinical implementation and the importance of real-time monitoring in the treatment of cardiovascular diseases are also highlighted [28].

Continuous blood pressure (BP) monitoring is highly relevant for real-time surveillance and early prevention of cardiovascular diseases. Wearable devices intended for BP monitoring have advanced significantly through adaptations to long-term wearability and improved comfort, but their development remains constrained by challenges such as motion artifacts and insufficient dynamic response. Methods based on pulse transit time, which combine photoplethysmographic (PPG) signals with electrocardiography (ECG), have attracted attention due to their potential for high accuracy and superior dynamic response [29].

4. Telemonitoring and telemedicine platforms

Telemedicine can facilitate the timely delivery of preventive interventions, potentially reducing cardiovascular morbidity and mortality. Recent literature provides a comprehensive overview of telemonitoring and telemedicine platforms (Table 4). The virtual implementation of prevention may help reduce pressure on hospitals by decreasing the incidence of acute cardiovascular events and limiting unnecessary presentations to medical facilities. Telemedicine platforms enable periodic check-ups, monitoring, and early interventions, supporting the prevention of acute events and slowing the progression of cardiovascular diseases [30]. The use of telehealth is increasing at multiple levels of healthcare systems; however, integration into primary care remains uneven. The paper synthesizes the characteristics, approaches, and dimensions of telehealth in this context, highlighting that it can support a wide range of activities through broadly accessible communication channels. Due to the opportunistic use of existing devices and platforms, telehealth can be scaled nationally and internationally. Nevertheless, technical, organizational, and human barriers persist; in particular, digital equity (access to technology and digital health literacy) is critical for extending services to underserved populations [31].

Telemedicine, defined as the provision of clinical services at a distance through digital technologies, is an important direction of research in contemporary cardiology. Follow-up consultations conducted via health applications can improve efficiency and adherence, reducing missed appointments and facilitating monitoring. Implementation requires adequate infrastructure (high-quality audio-video, document management, and payment solutions), as well as patient engagement in transmitting relevant information. However, telemedicine complements rather than replaces the physical consultation. Its usefulness has been highlighted especially in contexts with limited access to services, including during public health crises [32]. The use of telehealth for hypertension and cardiovascular diseases has increased, particularly during the COVID-19 pandemic [33]. The analyzed interventions targeted patients with hypertension, heart failure, and stroke and frequently employed team-based care models (physicians, nurses, pharmacists, and other professionals). Results suggest that telemedicine is generally comparable to traditional face-to-face care for blood pressure control and cardiovascular disease management, functioning as an extension of care for certain patient groups. It may also support communication, engagement, and monitoring outside the clinical setting [34].

Heart failure remains a major public health issue, and remote monitoring and telemedicine can support personalized interventions, including through the integration of artificial intelligence and machine learning. The need for continuous innovation, interdisciplinary collaboration, and strategic investment is emphasized to harness the transformative potential of these solutions toward patient-centered care and efficient resource use [35].

Evidence from randomized trials and meta-analyses indicates that telemedicine can improve the implementation of guideline-directed therapy, reduce hospitalizations, increase patient engagement, and, in some contexts, reduce mortality. Remote monitoring of vital signs, symptoms, and treatment adherence can enable early detection of clinical deterioration and intervention before decompensation, but barriers must also be considered, e.g., technological limitations, reimbursement challenges, gaps in digital literacy, and integration into clinical workflows. Future directions in this field must be focused on standardized guidelines, patient-centered design, and hybrid models (virtual plus face-to-face) [36]. Internet-based remote monitoring systems can facilitate rapid responses to emergencies, reduce resource utilization, and improve clinical outcomes in the management of chronic diseases. Strategies that combine automated data collection, patient self-reporting, and personalized communication are recommended to overcome obstacles to sustained behavioral change and quality-of-life improvement [37].

Analyses indicate improvements in outcomes, access, and patient satisfaction—especially in chronic disease management—through reduced geographic barriers and increased engagement, and, similarly, comprehensive evaluations show a favorable impact on clinical outcomes, cost savings, and higher satisfaction levels, suggesting transformative potential for healthcare delivery [38,39]. Telemedicine may be able to improve the accessibility of specialized cardiology care, including in rural and underserved areas, facilitating cardiac rehabilitation and reducing health disparities [40]. As technology advances, the role of telemedicine in cardiology is expected to grow, influencing efficiency, costs, and patient management; at the same time, implementation and regulatory challenges remain relevant [40]. Digital health tools can improve access to care and outcomes in rural populations through teleconsultations, remote monitoring, mobile applications, and wearable devices. Major barriers remain limited connectivity and low familiarity with digital technologies—issues that must be addressed to ensure equitable access and sustainable implementation [41].

5. Artificial Intelligence

Artificial intelligence and ML are increasingly influencing cardiovascular medicine by providing tools for predictive modeling, diagnosis, risk stratification, and decision support (Table 5). Relevant concepts in cardiology are discussed (e.g., feature selection and common methodological errors), along with supervised learning algorithms and their current applications, as well as the role of deep learning and unsupervised methods in analyzing complex data. Overall, AI is capable of contributing to precision cardiology and improved clinical outcomes, although integration into routine practice remains limited [42]. Despite advances in diagnosis and treatment, cardiovascular diseases remain a leading cause of morbidity and mortality. AI has the potential to transform cardiology practice, particularly in medical imaging and the interpretation of complex datasets, by supporting clinical decision-making and extracting clinically relevant information. Integration with digital communication technologies may enable home-based care models for elderly and chronically ill patients, reducing hospitalizations and improving quality of life. Reviews highlight the potential of AI in both imaging and clinical practice, as well as the need to address limitations and ethical considerations [43].

AI can support the prediction of cardiovascular outcomes, the noninvasive diagnosis of coronary artery disease, the detection of arrhythmias via wearable devices, and the optimization of heart failure management. The development of IoT and precision medicine is accelerating their integration. However, ethical and real-world implementation concerns remain, requiring robust governance frameworks and clinical validation [44]. AI is integrated into clinical decision support systems (CDSS) using either rule-based approaches or data-derived ML models. Techniques such as artificial neural networks and support vector machines have evolved, and increased computational power has enabled the development of deep neural networks (DNNs). Despite their promise, the current impact on clinical practice is still moderate; however, the rapid expansion of the literature suggests an increasingly important role in the field [45]. Methodological reviews describe AI workflows, common algorithms for regression and classification, and performance metrics. The role of explainable artificial intelligence (XAI) in enhancing model transparency and trust is emphasized. Applications in cardiology involving supervised learning, unsupervised learning, reinforcement learning, and natural language processing are reviewed, highlighting the need for legal, ethical, and methodological requirements for clinical implementation [46].

AI and ML can improve diagnostic accuracy, risk prediction, workflow efficiency, and resource utilization. Applications in imaging, major categories of cardiovascular diseases, clinical research, and outcome prediction are summarized, along with discussions of the algorithms and methodologies used. Nevertheless, limitations persist regarding generalizability, data quality, bias, interpretability, and integration into clinical processes [47]. In cardiovascular medicine, the main objectives of AI include optimizing care, increasing efficiency, and improving clinical outcomes in the context of expanding data sources and therapeutic advances. Editorials highlight research priorities and the need for concrete steps toward responsible clinical implementation [48].

Narrative syntheses show that AI models have been widely applied to ECG and imaging data (echocardiography, coronary angiography, cardiac CT, and cardiac MRI), targeting diagnosis and risk stratification for multiple pathologies (e.g., coronary artery disease, cardiomyopathies, arrhythmias, and valvular diseases). Overall, the integration of AI promises significant advances in diagnosis and treatment, provided that clinical validation and ethical implementation are ensured [49].

Discussion

1. Continuous digital cardiovascular monitoring

The transition from episodic monitoring toward continuous, discreet surveillance is integrated into everyday life.

The digitalization of cardiovascular monitoring has accelerated a shift in the clinical paradigm—from point-in-time (“snapshot”) assessments to longitudinal monitoring capable of capturing rare, intermittent, or asymptomatic events. In this context, wearable and implantable devices, along with contactless solutions, are shaping an “invisible” clinical surveillance infrastructure with the potential for early detection, dynamic risk stratification, and timely intervention.

Wearable devices and portable sensors

Electrocardiography (ECG) remains the reference tool for evaluating cardiac electrical activity, and the 12-lead ECG is the diagnostic standard for multiple non-arrhythmic pathologies. However, the technical complexity of acquisition and reliance on trained personnel limit its use outside medical settings. Portable ECG devices and remote monitoring solutions have sought to reduce this gap through simplified acquisition (typically single-lead), facilitating self-monitoring and extending surveillance into ambulatory environments.

An analysis of studies conducted on commercially available devices validated in adult populations and approved by the FDA indicates that reduced-lead ECG devices have significant potential for long-term monitoring, especially when combined with real-time alert mechanisms. Their clinical utility is particularly relevant for identifying abnormal rhythms, with evidence suggesting that certain remote devices may surpass conventional ECG in diagnosing specific arrhythmias, such as atrial fibrillation. Despite these advantages, limitations persist regarding signal quality, device reliability, and the relatively small number of robust clinical studies evaluating their impact on therapeutic decision-making and clinical outcomes [50].

In parallel, smartwatches have evolved into multifunctional platforms with medical applications that can be grouped into three domains: monitoring, nudging, and prediction. Monitoring refers to the integration of data into medical management; nudging involves individual use aimed at behavior change; and prediction leverages aggregated data to train machine-learning algorithms to anticipate health outcomes. The literature highlights the potential of these devices within value-based medicine, while also emphasizing the need for more nuanced discussions regarding validation, clinical use, and the ethical implications of predictions generated from population-level data [51].

Implantable devices and ECG patches

Wireless transmission and ECG digitalization have facilitated the implementation of continuous monitoring strategies, with a major impact on the diagnosis and management of dysrhythmias. Implantable loop recorders (ILRs) represent a technologically mature option for long-term monitoring, with increasingly well-defined indications (e.g., unexplained syncope, suspected paroxysmal arrhythmias, post-event monitoring). Recent analyses highlight device progress and development directions, including optimization of detection algorithms and integration into clinical telemonitoring workflows [52].

In populations at risk of developing atrial fibrillation after specific interventions, ILR may overcome the limitations of prolonged external monitoring, which is often impractical. For example, in patients with atrial flutter undergoing cavotricuspid isthmus ablation, long-term ECG monitoring may reveal the onset of new atrial fibrillation, frequently within the first months after the procedure; ILR thus becomes a realistic solution for continuous surveillance, with implications for thromboembolic event prevention and therapy adjustment [53].

In cryptogenic stroke, underdiagnosed atrial fibrillation remains a major clinical issue. Evidence indicates that extended monitoring can increase detection rates, yet many studies present significant “gaps” in monitoring intervals, especially immediately after the index event. In addition to ILR, noninvasive strategies such as external loop recorders (ELR) and mobile cardiac outpatient telemetry (MCOT) are used; however, the relative role of wearable devices and “smart” monitoring in prevention remains insufficiently clarified. A synthesis of the evidence underscores the need for more precise recommendations regarding patient selection for each technology and for studies that reduce existing methodological gaps [54].

Contactless monitoring

Contactless monitoring, particularly during sleep, addresses a clinical and operational need: reducing the intrusiveness of polysomnography (PSG) and extending evaluation into non-hospital environments. A systematic review of contactless technologies describes a variety of sensors and systems (e.g., radar, temperature sensors, motion sensors, video cameras) capable of estimating cardiorespiratory parameters with minimal patient impact. Additionally, advantages and limitations related to accuracy, robustness to artifacts, and implementation conditions in clinical or home environments are identified [55].

Radars for vital sign detection offer distinct benefits: elimination of electrodes, freedom of movement, reduction of skin irritation, and facilitated patient access (particularly relevant in children and older adults). However, broad clinical acceptance depends on overcoming technical and validation barriers, especially regarding signal reliability under real-world conditions [56]. In the same direction, the use of IR-UWB radar for measuring multiscale cardiac motion proposes a contactless alternative for rapid and potentially accurate assessment, with promising applications in online monitoring and home care [57].

Video photoplethysmography (vPPG/rPPG/iPPG) represents another emerging direction. However, blood pressure estimation via vPPG is limited by low signal-to-noise ratio and variability in the correlation between pulse transit time and blood pressure, with performance dependent on method and analyzed region of interest (e.g., facial regions vs. hand) [58]. By comparison, evaluation of pulse frequency characteristics and variability through iPPG indicates that certain methods (such as POS and CHROM) may be more robust to motion and illumination artifacts, supporting the clinical potential of these systems for assessing autonomic nervous system dynamics, including through derived indicators (e.g., Poincaré maps) [59].

Continuous cardiovascular monitoring is emerging as a next-generation clinical infrastructure, but its large-scale implementation requires standardization, real-world validation, interoperability, and responsible integration into clinical workflows.

2. Artificial Intelligence in Cardiology

Cardiology is becoming anticipatory, personalized, and decision-oriented, not merely diagnostic.

AI is transforming cardiology through its ability to integrate large volumes of data (ECG, imaging, clinical data, sensors) and generate inferences that support clinical decisions. Beyond algorithmic performance, the critical challenges remain interpretability, generalization across diverse populations, bias control, and evaluation of real clinical impact.

ECG analysis through Deep Learning

Advances from 2017–2023 show a substantial increase in performance in arrhythmia detection and classification, with deep learning models frequently outperforming classical ML approaches. Various architectures are used (CNNs, RNNs, transformers, hybrid models), and the literature highlights both improved accuracy and the need for methodological guidelines regarding comparability, dataset selection, and external validation [60–62].

Recent directions include computationally efficient models adapted to resource-limited devices such as wearable monitors. For example, a lightweight 1D architecture based on ConvNeXtV2 demonstrated high performance in detecting atrial fibrillation and atrial flutter from single-lead ECG, while maintaining low computational cost and offering interpretability elements through Grad-CAM visualizations (attention to P-wave morphology and RR irregularities) [63].

AI in cardiac imaging

AI is increasingly applied in cardiovascular CT and MRI, with reported benefits for workflow (acquisition/post-processing time), image quality, and diagnostic accuracy. Applications include automated calcium scoring, stenosis quantification, plaque analysis, segmentation, and volumetric quantification, as well as myocardial tissue characterization [64,65].

In low- and middle-income countries, AI may facilitate task-shifting to less experienced operators; however, implementation depends on dataset diversity, infrastructure, governance, and ethical frameworks. Available reviews emphasize the need for multicenter data sharing, training, and interoperability standards [66]. A complementary direction is explainable AI (XAI), necessary to increase trust and clinical integration; however, XAI evaluation remains predominantly qualitative and insufficiently standardized [67].

Fusion modeling (clinical data + imaging) indicates prognostic improvements compared with traditional scores, but requires automated feature extraction from electronic health records and images—using CNNs and NLP—to become feasible in practice [68].

Clinical decision support systems

AI-based clinical decision support systems (CDSS) are considered a major direction for improving decision quality and patient outcomes. The literature highlights both applications (assisted diagnosis, personalized therapeutic recommendations, risk prediction, clinical documentation) and barriers: interpretability, bias, workflow integration, accountability, and medico-legal aspects [69].

Proof-of-concept studies show the possibility of predicting ischemic events over short time windows with accuracies >80% and potential for proactive intervention; however, translation into clinical implementation requires external validation, assessment of clinical benefit, and error analysis [70]. An important conceptual shift is the transition from “prediction” to patient-centered decision intelligence through multimodal integration (clinical notes, wearables, social determinants, environmental factors) and the provision of actionable, explainable, and context-sensitive recommendations [71].

3. From digital medicine to predictive medicine

Cardiology is evolving toward an anticipatory and personalized model based on dynamic risk and multimodal data.

Personalized risk models

Risk models increasingly guide clinical decisions, including in heart failure and cardiomyopathies. For example, in heart failure with preserved ejection fraction, a model using widely available variables can identify patients at high risk of sudden cardiac death, supporting stratification and differentiated monitoring [72].

In primary cardiomyopathies, risk assessment requires a multiparametric, stepwise approach that integrates clinical evaluation, ECG monitoring, multimodal imaging, genetics, and electroanatomical mapping, with implications for ablation and ICD indication [73,74]. In addition, the limitations of static models and surrogate criteria (e.g., appropriate ICD therapy), which may overestimate “true” risk and lead to unnecessary interventions, are emphasized; thus, dynamic models and disease-specific endpoints are needed [74,75]. The integration of machine learning in predicting mode of death and risk stratification, including in advanced imaging contexts, supports the shift toward individualized assessment; however, robustness, transparency, and clinical validation remain essential conditions [74,76].

Digital biomarkers and precision cardiology

Digital biomarkers (derived from sensors, wearables, and implantable devices) extend clinical observation beyond the hospital and may support therapeutic decisions. A synthesis of meta-analyses indicates evidence of variable quality: some interventions based on digital biomarkers are associated with meaningful improvements (including arrhythmia detection and reduced stroke incidence in certain contexts), yet reporting quality is often low. Rigorous use of AMSTAR-2 and GRADE tools is recommended to strengthen the evidence base [77].

Scoping reviews show rapid expansion of the field but also a lack of uniform operational definitions and standards for integrating digital biomarkers into practice, highlighting the need to map evidence across clinical domains and identify gaps [25]. Heart rate variability (HRV) is an example of a digital biomarker with clinical and operational utility, but effective implementation depends on standardized acquisition, context-dependent interpretation, and environment-specific validation [23].

The cardiovascular digital twin

The concept of the cardiac digital twin promises a personalized in silico representation, dynamically updated with clinical and monitoring data, capable of simulating disease progression and treatment response. In precision cardiology, cardiac digital twins are explored, especially in rhythm disorders, with potential support for procedural planning and individualized predictions [78].

Integration of multimodal data into mechanistic and statistical models, amplified by the development of AI (including generative AI), may enable more dynamic simulations and real-time recommendations. However, major challenges remain regarding model personalization, clinical validation, computational resources, interoperability, and ethical governance [79,80].

In atrial fibrillation, atrial digital twins (particularly of the left atrium) can integrate structural, electrophysiological, and hemodynamic data to simulate arrhythmia behavior, therapeutic response, and thromboembolic risk. Applications include stroke risk prediction through computational fluid dynamics, in silico testing of antiarrhythmics, and virtual ablation planning. Nevertheless, scalability and prospective validation remain prerequisites for clinical translation [81]. Along the same line, virtual testing of amiodarone guided by a digital twin suggests the possibility of pre-estimating efficacy in high-risk post-ablation patients, opening a promising direction for precision therapy [82].

Overall, the discussed data support a convergent transition toward predictive cardiology, in which continuous monitoring (wearable, implantable, contactless), digital biomarkers, and AI are integrated into secure clinical ecosystems. However, large-scale translation depends on: (1) prospective validation in real-world conditions, (2) methodological standardization, (3) interoperability and integration into clinical workflows, (4) data explainability and ethical governance, and (5) digital equity, ensuring that benefits are distributed without amplifying disparities.

Clinical benefits and impact on the healthcare system

The integration of digital technologies in cardiology generates significant clinical benefits, with a direct impact on patient outcomes and the organization of healthcare systems. Continuous monitoring of physiological parameters enables early diagnosis and timely identification of clinical deterioration, facilitating rapid intervention and reducing the risk of severe complications. At the same time, longitudinal analysis of individual data supports personalized prevention through dynamic risk stratification and adaptation of therapeutic interventions to each patient’s profile. The implementation of remote monitoring and early warning systems contributes to the reduction of hospitalizations and readmissions, particularly in heart failure, where early interventions can prevent decompensation. Moreover, telemedicine and remote care expand access to specialized services, improve continuity of care, and optimize interdisciplinary coordination. From a systemic perspective, these transformations may lead to economic efficiency by decreasing costs associated with avoidable hospital admissions and reallocating resources toward high-risk patients.

4. Limitations, risks, and ethical challenges

Despite its transformative potential, digital cardiology faces important limitations. A major concern is the insufficient clinical validation of some artificial intelligence algorithms, often developed on limited or non-representative datasets, which raises questions about the generalizability of results. At the same time, algorithmic bias may amplify existing inequalities among different population groups, highlighting the need for explicit equity strategies and performance auditing. Data protection and cybersecurity become essential in a context characterized by the continuous collection of sensitive information. Massive data flows may also generate informational overload for clinicians, increasing the risk of alarm fatigue and reducing decision-making efficiency. At the institutional level, regulatory and clinical responsibility challenges persist, including approval processes by authorities such as the FDA and EMA. Finally, patient acceptance—shaped by digital literacy, trust, and privacy concerns—remains a critical determinant of real-world implementation.

5. Future directions

The evolution of digital cardiology indicates a transition toward deeply integrated and predictive models of care. The development of continuous AI-guided cardiovascular prevention is emerging, based on dynamic, real-time risk assessment. In parallel, the integration of the digital twin concept promises personalized simulation of disease progression and treatment response, opening new perspectives for precision medicine. Another emerging field is real-time algorithm-guided therapies supported by continuous monitoring and adaptive predictive models. In interventional cardiology, augmented reality may improve procedural precision and the planning of complex interventions. At the macro-systemic level, the future belongs to integrated digital ecosystems linking patient–hospital–home, characterized by interoperability, data continuity, and hybrid models of care.

Conclusion

Digital cardiology is undergoing a profound transformation driven by the convergence of connected devices, digital biomarkers, telemedicine, and artificial intelligence. This evolution marks the shift from episodic monitoring to predictive and personalized medicine, with major potential to improve early diagnosis, prevention, and the efficiency of healthcare systems. However, sustainable implementation requires rigorous clinical validation, clear regulatory frameworks, ethical data governance, and true integration into clinical workflows. In this context, technology does not replace medical judgment but becomes the central infrastructure of the cardiology of the future—an anticipatory, connected, and deeply patient-centered cardiology.

Conflicts of interest and sources of funding

The authors declare no conflict of interest. This research received no external funding.

Authors’ contribution

Conceptualization, S.S.T, I.D.F.; methodology, I.D.F., C.N.D.; resources, B-V.V., C.N.D.; writing—original draft preparation, S.S.T, I.D.F., B-V.V.; writing—review and editing, S.I.D., A.E.M.; supervision, S.I.D., A.E.M.. All authors have read and agreed to the published version of the manuscript.

Acknowledgments

Generative AI was used for grammar revision and stylistic polishing, as the authors are non-native English speakers.

Ethics approval and consent to participate

Not applicable.

References

1. Zwack CC, Haghani M, Hollings M, Zhang L, Gauci S, Gallagher R, Redfern J. The evolution of digital health technologies in cardiovascular disease research. NPJ Digit Med. 2023;6(1):1. doi:10.1038/s41746-022-00734-2.
2. Restrepo Tique M, Araque O, Sánchez-Echeverri LA. Technological Advances in the Diagnosis of Cardiovascular Disease: A Public Health Strategy. Int J Environ Res Public Health. 2024;21(8):1083. doi: 10.3390/ijerph21081083.
3. Javaid A, Zghyer F, Kim C, Spaulding EM, Isakadze N, Ding J, Kargillis D, Gao Y, Rahman F, Brown DE, Saria S, Martin SS, Kramer CM, Blumenthal RS, Marvel FA. Medicine 2032: The future of cardiovascular disease prevention with machine learning and digital health technology. Am J Prev Cardiol. 2022;12:100379. doi: 10.1016/j.ajpc.2022.
4. De la Torre K, Min S, Lee H, Kang D. The Application of Preventive Medicine in the Future Digital Health Era. J Med Internet Res. 2025;27:e59165. doi: 10.2196/59165.
5. Pantelidis P, Dilaveris P, Ruipérez-Campillo S, Goliopoulou A, Giannakodimos A, Theofilis P, De Lucia R, Katsarou O, Zisimos K, Kalogeras K, Oikonomou E, Siasos G. Hearts, Data, and Artificial Intelligence Wizardry: From Imitation to Innovation in Cardiovascular Care. Biomedicines. 2025;13(5):1019. doi: 10.3390/biomedicines13051019.
6. Ahsan MM, Siddique Z. Machine learning-based heart disease diagnosis: A systematic literature review. Artif Intell Med. 2022;128:102289. doi: 10.1016/j.artmed.2022.102289.
7. Gunjal A, Judgi T. A comprehensive survey of artificial intelligence methods for cardiovascular disease detection: Recent advances and future challenges. MethodsX. 2025;15:103678. doi: 10.1016/j.mex.2025.103678.
8. Mao Y, Jimma BL, Mihretie TB. Machine learning algorithms for heart disease diagnosis: A systematic review. Curr Probl Cardiol. 2025;50(8):103082. doi: 10.1016/j.cpcardiol.2025.103082.
9. Health Quality Ontario. Long-Term Continuous Ambulatory ECG Monitors and External Cardiac Loop Recorders for Cardiac Arrhythmia: A Health Technology Assessment. Ont Health Technol Assess Ser. 2017;17(1):1-56.
10. Thomas EE, Taylor ML, Banbury A, Snoswell CL, Haydon HM, Gallegos Rejas VM, Smith AC, Caffery LJ. Factors influencing the effectiveness of remote patient monitoring interventions: a realist review. BMJ Open. 2021;11(8):e051844. doi: 10.1136/bmjopen-2021-051844.
11. Bayoumy K, Gaber M, Elshafeey A, Mhaimeed O, Dineen EH, Marvel FA, Martin SS, Muse ED, Turakhia MP, Tarakji KG, Elshazly MB. Smart wearable devices in cardiovascular care: where we are and how to move forward. Nat Rev Cardiol. 2021;18(8):581-599. doi: 10.1038/s41569-021-00522-7.
12. Hughes A, Shandhi MMH, Master H, Dunn J, Brittain E. Wearable Devices in Cardiovascular Medicine. Circ Res. 2023;132(5):652-670. doi: 10.1161/CIRCRESAHA.122.322389.
13. Nazir A, Nazir A, Shah Wali Jamal M, Sadiq SUR, Aman S, Mustapha MJ, Lawal SO, AbdulKareem MO, Bamigbola MF. Wearable Technology and Its Potential Role in Cardiovascular Health Monitoring and Disease Management. Health Sci Rep. 2025;8(11):e71486. doi: 10.1002/hsr2.71486.
14. Jena N, Singh P, Chandramohan D, Garapati HN, Gummadi J, Mylavarapu M, Shaik BF, Nanjundappa A, Apala DR, Toquica C, Lapsiwala B, Simhadri PK. Wearable Technology in Cardiology: Advancements, Applications, and Future Prospects. Rev Cardiovasc Med. 2025;26(6):39025. doi: 10.31083/RCM39025.
15. Odeh VA, Chen Y, Wang W, Ding X. Recent Advances in the Wearable Devices for Monitoring and Management of Heart Failure. Rev Cardiovasc Med. 2024;25(10):386. doi: 10.31083/j.rcm2510386.
16. Terada T, Hausen M, Way KL, O’Neill CD, Marçal IR, Dorian P, Reed JL. Wearable Devices for Exercise Prescription and Physical Activity Monitoring in Patients with Various Cardiovascular Conditions. CJC Open. 2025;7(5):695-706. doi: 10.1016/j.cjco.2025.02.017.
17. Lu JK, Wang W, Goh J, Maier AB. Selecting Wearable Devices to Measure Cardiovascular Functions in Community-Dwelling Adults: Application of a Practical Guide for Device Selection. Mayo Clin Proc Digit Health. 2025;3(2):100202. doi: 10.1016/j.mcpdig.2025.100202.
18. Aguilar M, Macle L, Chamieh R, Khairy P, Deyell MW, Bennett RG, Andrade JG. Wearable Smartwatches for Atrial Fibrillation Detection and Burden Estimation After Ablation: Comparison With Continuous Monitoring. Europace. 2025:euaf280. doi: 10.1093/europace/euaf280.
19. Barrera N, Solorzano M, Jimenez Y, Kushnir Y, Gallegos-Koyner F, Dagostin de Carvalho G. Accuracy of Smartwatches in the Detection of Atrial Fibrillation: A Systematic Review and Diagnostic Meta-Analysis. JACC Adv. 2025;4(11 Pt 1):102133. doi: 10.1016/j.jacadv.2025.
20. Sîngeap MS, Corneanu LE, Prodaniuc A, Şova IA, Coşovanu EO, Petriș OR. Diagnostic Accuracy of Wearable ECG Devices for Atrial Fibrillation and ST-Segment Changes: A Systematic Review. Diagnostics (Basel). 2025;15(24):3162. doi: 10.3390/diagnostics15243162.
21. Stachteas P, Bantidos MG, Papoutsidakis N, Nasoufidou A, Karakasis P, Sidiropoulos G, Kofos C, Patoulias D, Ediaroglou V, Stavropoulos G, Karagiannidis E, Fyntanidou B, Tsalikakis D, Smyrnakis E, Kassimis G, Papadopoulos CE, Fragakis N. Monitoring Atrial Fibrillation Using Wearable Digital Technologies: The Emerging Role of Smartwatches. J Clin Med. 2025;15(1):14. doi: 10.3390/jcm15010014.
22. Vyas R, Jain S, Thakre A, Thotamgari SR, Raina S, Brar V, Sengupta P, Agrawal P. Smart watch applications in atrial fibrillation detection: Current state and future directions. J Cardiovasc Electrophysiol. 2024;35(12):2474-2482. doi: 10.1111/jce.16451.
23. Burlacu A, Brinza C, Geman O, Karppa M, Hemanth DJ. Heart rate variability as a dual-use digital biomarker: integrating clinical, AI, and operational perspectives on human performance and resilience. BMC Cardiovasc Disord. 2026;26(1):87. doi: 10.1186/s12872-026-05543-z.
24. Grosicki GJ, Carter JR, Laursen PB, Plews DJ, Altini M, Galpin AJ, Fielding F, Hippel WV, Chapman C, Jasinski SR, Beattie UK, Holmes KE. Heart rate variability coefficient of variation during sleep as a digital biomarker that reflects behavior and varies by age and sex. Am J Physiol Heart Circ Physiol. 2026;330(1):H187-H199. doi: 10.1152/ajpheart.00738.2025.
25. Motahari-Nezhad H, Fgaier M, Mahdi Abid M, Péntek M, Gulácsi L, Zrubka Z. Digital Biomarker-Based Studies: Scoping Review of Systematic Reviews. JMIR Mhealth Uhealth. 2022;10(10):e35722. doi: 10.2196/35722.
26. De Sario Velasquez GD, Forte AJ, McLeod CJ, Bruce CJ, Pacheco-Spann LM, Maita KC, Avila FR, Torres-Guzman RA, Garcia JP, Borna S, Felton CL, Carter RE, Haider CR. Predicting Cardiopulmonary Arrest with Digital Biomarkers: A Systematic Review. J Clin Med. 2023;12(23):7430. doi: 10.3390/jcm12237430.
27. Owida HA. Biomechanical Sensing Systems for Cardiac Activity Monitoring. Int J Biomater. 2022;2022:8312564. doi: 10.1155/2022/8312564.
28. Tang C, Liu Z, Li L. Mechanical Sensors for Cardiovascular Monitoring: From Battery-Powered to Self-Powered. Biosensors (Basel). 2022;12(8):651. doi: 10.3390/bios12080651.
29. Zhou ZB, Cui TR, Li D, Jian JM, Li Z, Ji SR, Li X, Xu JD, Liu HF, Yang Y, Ren TL. Wearable Continuous Blood Pressure Monitoring Devices Based on Pulse Wave Transit Time and Pulse Arrival Time: A Review. Materials (Basel). 2023;16(6):2133. doi: 10.3390/ma16062133.
30. Battineni G, Sagaro GG, Chintalapudi N, Amenta F. The Benefits of Telemedicine in Personalized Prevention of Cardiovascular Diseases (CVD): A Systematic Review. J Pers Med. 2021;11(7):658. doi: 10.3390/jpm11070658.
31. Beheshti L, Kalankesh LR, Doshmangir L, Farahbakhsh M. Telehealth in Primary Health Care: A Scoping Review of the Literature. Perspect Health Inf Manag. 2022;19(1):1n.
32. Haleem A, Javaid M, Singh RP, Suman R. Telemedicine for healthcare: Capabilities, features, barriers, and applications. Sens Int. 2021;2:100117. doi: 10.1016/j.sintl.2021.100117.
33. Chivu CD, Crăciun MD, Pițigoi D, Aramă V, Luminos ML, Jugulete G, et al. The Dynamic Risk of COVID-19-Related Events in Vaccinated Healthcare Workers (HCWs) from a Tertiary Hospital in Bucharest, Romania: A Study Based on Active Surveillance Data. Vaccines (Basel). 2024;12(2):182. doi: 10.3390/vaccines12020182.
34. Jackson TN, Sreedhara M, Bostic M, Spafford M, Popat S, Lowe Beasley K, Jordan J, Ahn R. Telehealth Use to Address Cardiovascular Disease and Hypertension in the United States: A Systematic Review and Meta-Analysis, 2011-2021. Telemed Rep. 2023;4(1):67-86. doi: 10.1089/tmr.2023.0011.
35. Liu JC, Cheng CY, Cheng TH, Liu CN, Chen JJ, Hao WR. Unveiling the Potential: Remote Monitoring and Telemedicine in Shaping the Future of Heart Failure Management. Life (Basel). 2024;14(8):936. doi: 10.3390/life14080936.
36. Choi DJ. The role and prospects of telemedicine in the treatment of heart failure patients: a narrative review. Ewha Med J. 2025;48(2):e26. doi: 10.12771/emj.2025.00360.
37. Emaliyawati E, Ibrahim K, Kurniawan T, Fitria N, Songwathana P. A Systematic Review of Internet-Based Remote Patient Monitoring Systems for Chronic Disease Management in Asian. Patient Prefer Adherence. 2025;19:2985-3000. doi: 10.2147/PPA.S544351.
38. Ezeamii VC, Okobi OE, Wambai-Sani H, Perera GS, Zaynieva S, Okonkwo CC, Ohaiba MM, William-Enemali PC, Obodo OR, Obiefuna NG. Revolutionizing Healthcare: How Telemedicine Is Improving Patient Outcomes and Expanding Access to Care. Cureus. 2024;16(7):e63881. doi: 10.7759/cureus.63881.
39. Vudathaneni VKP, Lanke RB, Mudaliyar MC, Movva KV, Mounika Kalluri L, Boyapati R. The Impact of Telemedicine and Remote Patient Monitoring on Healthcare Delivery: A Comprehensive Evaluation. Cureus. 2024 Mar 4;16(3):e55534. doi: 10.7759/cureus.55534.
40. Tolu-Akinnawo O, Ezekwueme F, Awoyemi T. Telemedicine in Cardiology: Enhancing Access to Care and Improving Patient Outcomes. Cureus. 2024;16(6):e62852. doi: 10.7759/cureus.62852.
41. Maita KC, Maniaci MJ, Haider CR, Avila FR, Torres-Guzman RA, Borna S, Lunde JJ, Coffey JD, Demaerschalk BM, Forte AJ. The Impact of Digital Health Solutions on Bridging the Health Care Gap in Rural Areas: A Scoping Review. Perm J. 2024;28(3):130-143. doi: 10.7812/TPP/23.134.
42. Johnson KW, Torres Soto J, Glicksberg BS, Shameer K, Miotto R, Ali M, Ashley E, Dudley JT. Artificial Intelligence in Cardiology. J Am Coll Cardiol. 2018;71(23):2668-2679. doi: 10.1016/j.jacc.2018.03.521.
43. Romiti S, Vinciguerra M, Saade W, Anso Cortajarena I, Greco E. Artificial Intelligence (AI) and Cardiovascular Diseases: An Unexpected Alliance. Cardiol Res Pract. 2020;2020:4972346. doi: 10.1155/2020/4972346.
44. Karatzia L, Aung N, Aksentijevic D. Artificial intelligence in cardiology: Hope for the future and power for the present. Front Cardiovasc Med. 2022;9:945726. doi: 10.3389/fcvm.2022.945726.
45. Koulaouzidis G, Jadczyk T, Iakovidis DK, Koulaouzidis A, Bisnaire M, Charisopoulou D. Artificial Intelligence in Cardiology-A Narrative Review of Current Status. J Clin Med. 2022;11(13):3910. doi: 10.3390/jcm11133910.
46. Ledziński Ł, Grześk G. Artificial Intelligence Technologies in Cardiology. J Cardiovasc Dev Dis. 2023;10(5):202. doi: 10.3390/jcdd10050202.
47. Chowdhury MA, Rizk R, Chiu C, Zhang JJ, Scholl JL, Bosch TJ, Singh A, Baugh LA, McGough JS, Santosh KC, Chen WCW. The Heart of Transformation: Exploring Artificial Intelligence in Cardiovascular Disease. Biomedicines. 2025;13(2):427. doi: 10.3390/biomedicines13020427.
48. Vidal-Perez R, Vazquez-Rodriguez JM. Role of artificial intelligence in cardiology. World J Cardiol. 2023;15(4):116-118. doi: 10.4330/wjc.v15.i4.116.
49. Patrascanu OS, Tutunaru D, Musat CL, Dragostin OM, Fulga A, Nechita L, Ciubara AB, Piraianu AI, Stamate E, Poalelungi DG, Dragostin I, Iancu DC, Ciubara A, Fulga I. Future Horizons: The Potential Role of Artificial Intelligence in Cardiology. J Pers Med. 2024;14(6):656. doi: 10.3390/jpm14060656.
50. Bouzid Z, Al-Zaiti SS, Bond R, Sejdić E. Remote and wearable ECG devices with diagnostic abilities in adults: A state-of-the-science scoping review. Heart Rhythm. 2022;19(7):1192-1201. doi: 10.1016/j.hrthm.2022.02.030.
51. Köhler C, Bartschke A, Fürstenau D, Schaaf T, Salgado-Baez E. The Value of Smartwatches in the Health Care Sector for Monitoring, Nudging, and Predicting: Viewpoint on 25 Years of Research. J Med Internet Res. 2024;26:e58936. doi: 10.2196/58936.
52. Akella K, Murtaza G, Della Rocca DG, Kodwani N, Gopinathannair R, Natale A, Lakkireddy D. Implantable loop recorders for cardiac dysrhythmia monitoring. Future Cardiol. 2020;16(6):725-733. doi: 10.2217/fca-2020-0035.
53. Mittal S, Pokushalov E, Romanov A, Ferrara M, Arshad A, Musat D, Preminger M, Sichrovsky T, Steinberg JS. Long-term ECG monitoring using an implantable loop recorder for the detection of atrial fibrillation after cavotricuspid isthmus ablation in patients with atrial flutter. Heart Rhythm. 2013;10(11):1598-604. doi: 10.1016/j.hrthm.2013.07.044.
54. Pezawas T. ECG Smart Monitoring versus Implantable Loop Recorders for Atrial Fibrillation Detection after Cryptogenic Stroke-An Overview for Decision Making. J Cardiovasc Dev Dis. 2023;10(7):306. doi: 10.3390/jcdd10070306.
55. Boiko A, Martínez Madrid N, Seepold R. Contactless Technologies, Sensors, and Systems for Cardiac and Respiratory Measurement during Sleep: A Systematic Review. Sensors (Basel). 2023;23(11):5038. doi: 10.3390/s23115038.
56. Kebe M, Gadhafi R, Mohammad B, Sanduleanu M, Saleh H, Al-Qutayri M. Human Vital Signs Detection Methods and Potential Using Radars: A Review. Sensors (Basel). 2020;20(5):1454. doi: 10.3390/s20051454.
57. Qiao JH, Qi FG, Liang FL, Ma J, Lv H, Yu X, Xue HJ, An Q, Yan KD, Shi D, Qiao YH, Wang JQ, Zhang Y. Contactless multiscale measurement of cardiac motion using biomedical radar sensor. Front Cardiovasc Med. 2022;9:1057195. doi: 10.3389/fcvm.2022.1057195.
58. Shirbani F, Moriarty A, Hui N, Cox J, Tan I, Avolio AP, Butlin M. Contactless video-based photoplethysmography technique comparison investigating pulse transit time estimation of arterial blood pressure. Annu Int Conf IEEE Eng Med Biol Soc. 2021;2021:5650-5653. doi: 10.1109/EMBC46164.2021.9629489.
59. van Es VAA, Lopata RGP, Scilingo EP, Nardelli M. Contactless Cardiovascular Assessment by Imaging Photoplethysmography: A Comparison with Wearable Monitoring. Sensors (Basel). 2023;23(3):1505. doi: 10.3390/s23031505.
60. Ansari Y, Mourad O, Qaraqe K, Serpedin E. Deep learning for ECG Arrhythmia detection and classification: an overview of progress for period 2017-2023. Front Physiol. 2023;14:1246746. doi: 10.3389/fphys.2023.1246746.
61. Katal N, Gupta S, Verma P, Sharma B. Deep-Learning-Based Arrhythmia Detection Using ECG Signals: A Comparative Study and Performance Evaluation. Diagnostics (Basel). 2023;13(24):3605. doi: 10.3390/diagnostics13243605.
62. Reshad AI, Nino V, Valero M. Deep Learning-Based Detection of Arrhythmia Using ECG Signals – A Comprehensive Review. Vasc Health Risk Manag. 2025;21:685-703. doi: 10.2147/VHRM.S508620.
63. Kraft D, Rumm P. Atrial Fibrillation and Atrial Flutter Detection Using Deep Learning. Sensors (Basel). 2025;25(13):4109. doi: 10.3390/s25134109.
64. Lanzafame LRM, Bucolo GM, Muscogiuri G, Sironi S, Gaeta M, Ascenti G, Booz C, Vogl TJ, Blandino A, Mazziotti S, D’Angelo T. Artificial Intelligence in Cardiovascular CT and MR Imaging. Life (Basel). 2023;13(2):507. doi: 10.3390/life13020507.
65. Tolu-Akinnawo OZ, Ezekwueme F, Omolayo O, Batheja S, Awoyemi T. Advancements in Artificial Intelligence in Noninvasive Cardiac Imaging: A Comprehensive Review. Clin Cardiol. 2025;48(1):e70087. doi: 10.1002/clc.70087.
66. Marey A, Mehrtabar S, Afify A, Pal B, Trvalik A, Adeleke S, Umair M. From Echocardiography to CT/MRI: Lessons for AI Implementation in Cardiovascular Imaging in LMICs-A Systematic Review and Narrative Synthesis. Bioengineering (Basel). 2025;12(10):1038. doi: 10.3390/bioengineering12101038.
67. Haupt M, Maurer MH, Thomas RP. Explainable Artificial Intelligence in Radiological Cardiovascular Imaging-A Systematic Review. Diagnostics (Basel). 2025;15(11):1399. doi: 10.3390/diagnostics15111399.
68. van Assen M, Tariq A, Razavi AC, Yang C, Banerjee I, De Cecco CN. Fusion Modeling: Combining Clinical and Imaging Data to Advance Cardiac Care. Circ Cardiovasc Imaging. 2023;16(12):e014533. doi: 10.1161/CIRCIMAGING.122.014533.
69. Elhaddad M, Hamam S. AI-Driven Clinical Decision Support Systems: An Ongoing Pursuit of Potential. Cureus. 2024;16(4):e57728. doi: 10.7759/cureus.57728.
70. Elvas LB, Nunes M, Ferreira JC, Dias MS, Rosário LB. AI-Driven Decision Support for Early Detection of Cardiac Events: Unveiling Patterns and Predicting Myocardial Ischemia. J Pers Med. 2023;13(9):1421. doi: 10.3390/jpm13091421.
71. Subudhi G, Subudhi S, Garg S, Mehandru D. Artificial Intelligence in Medicine: Moving From “Prediction” to “Patient-Centric Decision Intelligence”. Cureus. 2025;17(12):e100323. doi: 10.7759/cureus.100323.
72. Adabag S, Langsetmo L. Sudden cardiac death risk prediction in heart failure with preserved ejection fraction. Heart Rhythm. 2020;17(3):358-364. doi: 10.1016/j.hrthm.2019.12.009.
73. Lazzeroni D, Crocamo A, Ziveri V, Notarangelo MF, Rizzello D, Spoladori M, Donelli D, Cacciola G, Ardissino D, Niccoli G, Peretto G. Personalized Management of Sudden Death Risk in Primary Cardiomyopathies: From Clinical Evaluation and Multimodality Imaging to Ablation and Cardioverter-Defibrillator Implant. J Pers Med. 2023;13(5):877. doi: 10.3390/jpm13050877.
74. Werner RA, Derlin T, Bengel FM. Personalized prediction of mode of cardiac death in heart failure using supervised machine learning in the context of cardiac innervation imaging. J Nucl Cardiol. 2022;29(1):202-203. doi: 10.1007/s12350-020-02215-z.
75. van der Heide MYC, Verstraelen TE, Wilde AAM. Personalized sudden cardiac death risk prediction in genetic heart diseases: Beyond one-size-fits-all. Heart Rhythm. 2026;23(1):e62-e74. doi: 10.1016/j.hrthm.2025.07.041.
76. Singh M, Kumar A, Khanna NN, Laird JR, Nicolaides A, Faa G, Johri AM, Mantella LE, Fernandes JFE, Teji JS, Singh N, Fouda MM, Singh R, Sharma A, Kitas G, Rathore V, Singh IM, Tadepalli K, Al-Maini M, Isenovic ER, Chaturvedi S, Garg D, Paraskevas KI, Mikhailidis DP, Viswanathan V, Kalra MK, Ruzsa Z, Saba L, Laine AF, Bhatt DL, Suri JS. Artificial intelligence for cardiovascular disease risk assessment in personalised framework: a scoping review. EClinicalMedicine. 2024;73:102660. doi: 10.1016/j.eclinm.2024.102660.
77. Motahari-Nezhad H, Al-Abdulkarim H, Fgaier M, Abid MM, Péntek M, Gulácsi L, Zrubka Z. Digital Biomarker-Based Interventions: Systematic Review of Systematic Reviews. J Med Internet Res. 2022;24(12):e41042. doi: 10.2196/41042.
78. Trayanova NA, Prakosa A. Up digital and personal: How heart digital twins can transform heart patient care. Heart Rhythm. 2024;21(1):89-99. doi: 10.1016/j.hrthm.2023.10.019.
79. Thangaraj PM, Benson SH, Oikonomou EK, Asselbergs FW, Khera R. Cardiovascular care with digital twin technology in the era of generative artificial intelligence. Eur Heart J. 2024;45(45):4808-4821. doi: 10.1093/eurheartj/ehae619.
80. Skalidis I, Stalikas N, Collet C, Chatzizisis YS, Samant S, Apostolos A, Tsigkas G, Iglesias JF, Arroyo D, Garin D, Cook S, Salihu A, Meier D, Fournier S, Hovasse T, De Backer O, Garot P, Akodad M. Digital twins and simulations in transcatheter coronary and structural heart interventions. Eur Heart J Digit Health. 2025;7(2):ztaf129. doi: 10.1093/ehjdh/ztaf129.
81. Karakasis P, Antoniadis AP, Theofilis P, Vlachakis PK, Milaras N, Patoulias D, Karamitsos T, Fragakis N. Digital Twin Models in Atrial Fibrillation: Charting the Future of Precision Therapy? J Pers Med. 2025;15(6):256. doi: 10.3390/jpm15060256.
82. Hwang T, Lim B, Kwon OS, Kim MH, Kim D, Park JW, Yu HT, Kim TH, Uhm JS, Joung B, Lee MH, Hwang C, Pak HN. Clinical usefulness of digital twin guided virtual amiodarone test in patients with atrial fibrillation ablation. NPJ Digit Med. 2024;7(1):297. doi: 10.1038/s41746-024-01298-z.