Artificial intelligence (AI) is rapidly transforming healthcare through applications in clinical decision support, diagnostic imaging, population health management, and workflow optimization. Despite these advances, real-world deployment continues to expose critical challenges related to safety, bias, transparency, and integration into clinical workflows. Algorithmic bias can exacerbate health disparities, limited explainability may undermine clinician trust, and insufficient validation and post-deployment monitoring can compromise patient safety. Although the World Health Organization (WHO) has established six ethical principles for AI in health, including autonomy, well-being and safety, transparency, accountability, equity, and sustainability, translating these high-level principles into practical and enforceable governance mechanisms remains a persistent challenge. This narrative review synthesizes insights from bioethics, health policy, computer science, and clinical medicine to identify gaps in current AI governance approaches and proposes a lifecycle-aligned governance-by-design framework that operationalizes WHO ethical principles across key stages of the healthcare AI lifecycle, including data collection, model development, validation, deployment, and post-deployment monitoring. The framework integrates concrete governance mechanisms such as consent governance, fairness evaluation, external validation, explainability, clinician oversight, and continuous performance monitoring. Overall, this work advances a practical, lifecycle-integrated approach to AI governance and provides a structured foundation for developing safe, equitable, and trustworthy AI systems in healthcare.

Animal-vehicle collisions (AVCs) pose a significant threat to road safety, wildlife conservation, and transportation systems worldwide. Advances in artificial intelligence (AI) and computer vision have enabled intelligent detection and mitigation systems aimed at reducing such collisions. This review synthesizes the current state of AI-powered AVC prevention systems, examining deep learning architectures, multimodal sensor technologies, real-time processing frameworks, and system-level integration strategies. We analyze the transition from traditional computer vision methods to modern deep neural networks, evaluate sensor fusion approaches, and assess existing wildlife detection datasets and benchmarking practices. Key technical challenges are identified, including environmental variability, long-range detection constraints, dataset scarcity, cross-species generalization limitations, and real-time safety requirements. Rather than framing AVC prevention solely as an object detection task, this review conceptualizes it as a safety-critical perception and risk assessment pipeline operating under strict latency and deployment constraints. Persistent gaps in wildlife-specific detection, standardized evaluation protocols, and scalable edge deployment are discussed. To organize these insights, we present WildSafe-Edge as a conceptual reference architecture derived from the literature, synthesizing system-level design considerations and highlighting open research directions. Future research directions include transfer learning, synthetic data augmentation, vehicle-to-everything (V2X) integration, and edge-centric architectures to enable robust, real-world collision mitigation systems.

Background/Objectives: Glucagon-like peptide-1 receptor agonists (GLP-1RAs) have emerged as a promising therapeutic option for women with polycystic ovary syndrome (PCOS). Clinical trials and data demonstrate significant improvements in body weight, insulin resistance, hyperandrogenism, and, in some studies, menstrual regularity and reproductive outcomes. However, the current evidence base remains disproportionately focused on short-term metabolic and anthropometric endpoints, while outcomes most relevant to patients—including treatment satisfaction, gastrointestinal tolerability, psychological well-being, body image, fertility planning, financial burden, and long-term adherence—remain inadequately characterized. Methods: We searched PubMed and Google Scholar for English-language literature published between 2021 and 2026, using structured keyword searches. This narrative review evaluates the literature on GLP-1RA use in PCOS beyond weight-focused outcomes, examining mechanisms of action, comparative tolerability across agents, and patient-centered domains including quality of life, eating behavior, and reproductive planning. Results: The published literature reveals a substantial gap between trial-reported completion rates and treatment success, and actual persistence and patient satisfaction. This discrepancy is particularly consequential in PCOS, where treatment decisions intersect with high baseline rates of depression, anxiety, and body image disturbance, and where ovulatory benefits must be weighed against mandatory discontinuation before conception. Conclusions: We identify a systematic absence of validated patient-reported outcome measures, standardized core outcome sets, and long-term follow-up data after treatment withdrawal. This review proposes a research agenda prioritizing patient-centered endpoints as co-primary outcomes, structured assessment of acceptability and persistence, qualitative and mixed-methods approaches, and a dedicated study of fertility planning and treatment interruption.

Background: Electrical and dielectric properties of the myocardium depend on its composition, fibrosis, edema, ischemia, and heat damage, and hence may play an important role in defining the electrophysiologic substrate. Local impedance and other impedance-based methods give information about these parameters that is available to clinicians, but not direct or substitutable for intrinsic conductivity and permittivity of the tissue. The use of artificial intelligence has been thoroughly studied for the ECGs, electrograms, images, and computational data analysis, but not for dielectric or impedance measurements. Objective: The study aims to review the scientific basis of dielectric properties of heart muscle critically in cardiology and electrophysiology, to differentiate between existing clinical and conceptual applications of myocardial dielectrics, and to estimate current and potential contributions of artificial intelligence to their interpretation. Data Sources and Study Selection: The current work represents a structured narrative review in PubMed, Scopus, and Google Scholar databases from inception until May 2026 based on various combinations of keywords that refer to myocardial impedance, dielectric properties, conductivity, permittivity, local impedance, dielectric imaging, cardiac electrophysiology, catheter ablation, machine learning, and artificial intelligence. This review included experimental, ex vivo, animal, computational, and human studies related to myocardial dielectric properties and their use in electrophysiology. Evidence was classified according to four categories: direct human clinical evidence; preclinical/translation evidence; indirect evidence from related techniques; and extrapolation concept. As a result of heterogeneity between studies, sensing technologies, and outcomes, the results have been analyzed narratively. Key Findings: Evidence regarding the usage of AI algorithms, which have been primarily trained on myocardial dielectric or catheter-based local impedance data, is extremely scarce and mostly consists of preclinical or ex vivo data. On the contrary, the majority of clinically used AI algorithms in the field of electrophysiology make use of ECG data, intracardiac electrogram data, image processing, or computational modeling without any inputs related to dielectrics or local impedance. Conclusions and Implications for Practice: Dielectric sensing is an attractive supplement to traditional methods of voltage mapping and imaging, although the clinical readiness of dielectric sensing greatly varies depending on the application. At the present time, the existing data provide a basis for utilizing the local impedance measurement in the ablation procedure and evaluation of the myocardium properties, while the combination of artificial intelligence and dielectric sensing is still experimental. Before being introduced into the clinical electrophysiology practice, signal acquisition standardization and prospective multicenter trials are needed.

Photoplethysmography (PPG) is a non-invasive optical technique commonly used to measure heart rate and oxygen saturation, but its waveform contains additional physiological information that can be analyzed using artificial intelligence (AI). This narrative review summarizes the emerging applications of AI-based PPG in cardiovascular, respiratory, sleep, hemodynamic, pregnancy-related, and portal-hypertension assessment, with the aim of evaluating its potential beyond conventional monitoring and identifying barriers to clinical translation. The literature search was conducted using PubMed, Google Scholar, IEEE Xplore, ScienceDirect, and SpringerLink. Additional relevant studies were identified through screening the reference lists of included articles. Studies published between 2002 and 2026 were identified to capture the development of PPG from conventional monitoring to newer AI-based applications. Human studies were prioritized, while relevant computational, simulated, synthetic, ex vivo, and technical studies were also included. Studies unrelated to PPG, duplicates, and studies with limited relevance were excluded. A total of 96 references were included, covering AI approaches such as convolutional and deep neural networks, ensemble methods, transfer learning, U-Net, generative adversarial networks, and Transformer-based models. Overall, the reviewed evidence suggests that AI-based PPG may support blood pressure estimation, atrial fibrillation detection, sleep and respiratory monitoring, vascular aging assessment, pulmonary hypertension screening, preeclampsia assessment, volume-status and compensatory-reserve assessment, and exploratory assessment related to portal hypertension. However, clinical translation remains limited by motion artifacts, sensor and measurement-site variability, skin-pigmentation-related bias, physiological and environmental influences, heterogeneous methods, limited external validation, and inconsistent clinical and regulatory standards.

Cardiorenal syndrome (CRS) encompasses a spectrum of disorders arising from bidirectional interactions between the heart and kidneys and is associated with substantial morbidity, mortality, and healthcare burden. Early recognition remains challenging because conventional biomarkers and imaging modalities may inadequately detect subclinical disease or distinguish functional changes from true organ injury. This narrative review examines the epidemiology, classification, pathophysiology, diagnostic approaches, and contemporary management of CRS, with particular emphasis on the emerging role of artificial intelligence (AI). Relevant evidence regarding established and emerging diagnostic and therapeutic approaches was reviewed, including biomarkers, imaging, guideline-directed medical therapy, ultrafiltration, cardiac devices, transplantation, and AI-based applications. Current evidence demonstrates the multifactorial nature of CRS and highlights the importance of early diagnosis and individualized management. Machine learning and deep learning approaches have shown potential to integrate electronic health records, biomarkers, imaging, physiological signals, and multi-omics data to support early detection, risk stratification, outcome prediction, and therapeutic decision-making. AI-assisted approaches may complement conventional diagnostic and management strategies and facilitate more precise and proactive CRS care. However, limitations related to data quality, model interpretability, external validation, and clinical implementation must be addressed before widespread clinical adoption.