Large language models (LLMs), Generative AI (GAI), and Generative Vision Models (GVMs) have become transformative technologies in healthcare, offering new landscapes for diagnostics, patient communication, and research innovation. To map the applications of GAI, LLMs, and GVMs in healthcare, we conducted a systematic literature review guided by the PRISMA. After screening and quality assessment, 96 studies were synthesized to address four research questions: medical imaging applications, patient communication, specialized medical research models, and global healthcare initiatives. Findings indicate that GVMs, such as GANs, DiffMIC, and WSGAN, enhance the accuracy and segmentation of medical imaging, while GAI and LLM-based chatbots, including ChatGPT and IBM Watsonx Assistant, improve patient interaction and administrative efficiency. Specialized models, including Med-PaLM 2, BioGPT, and MedCPT, can be used to perform with high capability in drug discovery, genomic analysis, and evidence-based research. Furthermore, international case studies demonstrate regional adaptations, such as AlphaFold in the UK and scGPT in Canada, which are representative of innovation in public health and personalized care. In general, GAI, LLMs, and GVMs redefine healthcare operations and research worldwide by enabling precision diagnostics, customized communication, and accelerated biomedical innovation.
Background: Diabetic retinopathy is a preventable cause of vision loss, but screening coverage is limited when retinal imaging, expert interpretation, referral completion, and access to treatment are not uniformly available. Objective: The purpose of this review is to assess the clinical evidence, regulatory status, and health-system applicability of three FDA-cleared autonomous diabetic retinopathy screening platforms: LumineticsCore (formerly IDx-DR), EyeArt, and AEYE-DS. Scope: The review will address diagnostic performance, imageability, camera compatibility, acquisition workflow, evidence provenance, geographic validation, referral burden, and deployment context. CE-marked and international non-FDA systems are examined as comparators to provide context for global innovation. Methods: A narrative synthesis of evidence from January 2010 to April 2026 was performed using peer-reviewed studies, regulatory submissions, and real-world reports. Endpoints, reference standards, camera protocols, study populations, and ungradable-image handling differed across sources, precluding quantitative pooling. Key Findings: Autonomous DR screening has progressed from proving technical feasibility to demonstrating pathway fit. LumineticsCore aligns with controlled-workflow autonomy, EyeArt with program-scale triage, and AEYE-DS with portable access expansion. CE-marked and international systems broaden the field through handheld, smartphone-based, offline, and locally adapted models. Clinical value is shaped not only by sensitivity and specificity, but also by imageability, true screening denominator, referral burden, evidence maturity, patient follow-up, and local care capacity. Conclusions: Autonomous screening is most likely to reduce preventable vision loss when it operates as a care pathway linking image capture, referral completion, and treatment initiation. Future evidence should evaluate systems under fair local conditions, measure completed screening and treatment outcomes, and align each platform with the clinical capacity of the setting in which it is deployed
Background Localized scleroderma (LS) is a chronic inflammatory skin disease that can cause long-term functional and cosmetic morbidity, particularly in children. The Localized Scleroderma Cutaneous Assessment Tool (LoSCAT) is the standard for clinical evaluation but remains manual and time-intensive. Automating components of LoSCAT could improve scalability and consistency for clinical monitoring and research. Methods We retrospectively curated the largest number of de-identified clinical photographs from pediatric LS patients enrolled in the National Registry for Childhood Onset Scleroderma during 2010–2025. We developed a privacy-preserving R Shiny platform to support image labeling and quality control using LoSCAT-defined anatomic regions. Six trained raters labeled 5,965 images. For model development, we retained only single-label images and merged the original 18 LoSCAT-defined body regions into 12 side-agnostic classes. After this filtering process, a total of 2,145 high-quality images were included for training and evaluation. A Vision Transformer (ViT) model was fine-tuned using a patient-level stratified group split (training: 1,790 images; test: 355 images) to prevent leakage and preserve class distribution. Results The ViT classifier achieved 0.805 accuracy and 0.776 macro-F1 on the held-out test set. Misclassifications occurred primarily between adjacent or visually similar regions (e.g., abdomen vs lower back; thigh vs leg), consistent with clinically plausible anatomic ambiguity rather than random errors. The trained classifier was subsequently applied to additional images to generate body-region labels at scale. Conclusion Automated body-region recognition in pediatric localized scleroderma photographs is feasible and clinically interpretable. This work provides a reproducible, privacy-preserving workflow that enables large-scale image organization and establishes a foundation for future region-specific lesion scoring. This study focuses on body-region classification as a necessary and foundational step toward automated LoSCAT scoring.
Post-COVID obesity has emerged as a significant public health challenge in Dhaka, driven by a complex interplay of socio-economic, lifestyle, and environmental factors that were exacerbated during the COVID-19 pandemic through increased sedentary behavior, unhealthy dietary patterns, and reduced access to healthcare services. This situation has led to a growing number of individuals being medically classified as overweight and obese, thereby accelerating the prevalence of chronic diseases, increasing pressure on the healthcare system, and hindering public health progress in the city. To address this challenge, the present study introduces a novel analytical framework based on a Relative Error Support Vector Machine (RE-SVM) optimized using the Tasmanian Devil Optimiser (TDO), a recently developed metaheuristic particularly effective f, robust algorithm specifically designed transparency and derive actionable insights, eIn order to maintain transparency and also derive actionable insights, explainable AI (XAI) methodologies are incorporated to offer interpretable models that identify the major contributing factors of obesity within the urban fabric of Dhaka.182 The proposed model was trained and tested on a dataset based on the population of Dhaka city, comprising 2,182 records and 17 original attributes. In the full-feature setting, the optimized RE-SVM model achieved an accuracy of 99.06%, with precision, recall, and F1-score values of 0.9906. However, because obesity-level labels are closely related to BMI, which is directly determined by weight and height, an additional leakage-controlled ablation experiment was conducted by entirely removing Weight (kg) and Height (m) before model training. The revised analysis distinguishes between anthropometric-inclusive classification and non-anthropometric obesity-risk prediction. The most critical factor contributing to obesity in Dhaka is weight, particularly extreme weight ranges (<58.00 kg or >95.70 kg), followed by height and family history of overweight. These findings indicate that the proposed framework can identify predictive patterns in structured obesity-level data. However, because the dataset should not be interpreted as an independently collected population-representative Dhaka cohort, the results should be viewed as methodological evidence rather than direct epidemiological evidence. Locally collected and clinically validated Dhaka data are required before deriving targeted public health interventions from the model outputs.
The rapid advancement of Information Technology has significantly transformed healthcare delivery, influencing both patients and healthcare professionals. Telemedicine and e-Health applications have emerged as essential tools in nursing practice, enabling remote monitoring, chronic disease management, and improved patient engagement. This systematic review examined 32 English-language studies published between 2018 and 2024 in the PubMed and SpringerLink databases, focusing on the design, implementation, and outcomes of digital health systems in nursing. Most applications are designed for widely used devices such as smartphones and tablets. Findings indicate that remote nursing monitoring can enhance patient safety, improve healthcare professionals’ satisfaction with care delivery, and potentially reduce healthcare costs. Key barriers include digital literacy, data privacy concerns, and institutional resistance to technology adoption. Successful implementation requires affordable, secure, and user-friendly solutions tailored to both patients and nursing staff. Despite the challenges, recent years have seen increased efforts to integrate telemedicine programs into clinical practice, highlighting the growing importance of digital health in global nursing. These insights can inform nursing policy, training, and the design of future digital health interventions.
