Search Results (1,180)

Objectives: Artificial intelligence (AI) is a transformative development in the field of medicine. In the field of musculoskeletal radiology, agentic AI is a technology that could flourish, but currently, the limited evidence base is fragmented and sparse, and we present a scoping review of it. Methods: Parallel searches were conducted in four databases: PubMed, Embase, Scopus, and Web of Science. Search terms included all agentic AI and autonomous AI agents, as well as radiology. All papers underwent screening by two independent reviewers, with conflicts resolved through consensus. Initially, inclusion criteria involved all papers on general radiology, which were later stratified for musculoskeletal radiology and applicable papers to ensure inclusion of all suitable studies. A thematic analysis was undertaken by two independent reviewers. Results: Eleven studies met the inclusion criteria, comprising two MSK (musculoskeletal)-specific and nine general radiology papers applicable to MSK workflows. Four key themes emerged. Agentic decision support was demonstrated across five studies, showing improved diagnostic coordination, pathway navigation, and reduced clinician workload. Workflow optimisation was highlighted in four studies, with agentic systems enhancing administrative efficiency, modality selection, and overall radiology throughput. Image analysis and reconstruction were improved in three studies, with multi-agent systems enabling enhanced image quality and automated interpretation. Finally, four studies addressed conceptual, ethical, and governance considerations, emphasising the need for transparency, safety frameworks, and clinician oversight. Conclusion: Agentic AI shows considerable promise for enhancing MSK radiology through improved decision support, image analysis, and workflow efficiency; however, the current evidence remains limited and largely theoretical. Full article

As artificial intelligence (AI) continues to expand across clinical environments, healthcare is transitioning from static decision-support tools to dynamic, autonomous agents capable of reasoning, coordination, and continuous interaction. In the context of geriatric medicine, a field characterized by multimorbidity, cognitive decline, and the need for long-term personalized care, this evolution opens new frontiers for delivering adaptive, assistive, and trustworthy digital support. However, the autonomy and interconnectivity of these systems introduce heightened cybersecurity and ethical challenges. This paper presents a Secure Agentic AI Architecture (SAAA) tailored to the unique demands of geriatric healthcare. The architecture is designed around seven layers, grouped into five functional domains (cognitive, coordination, security, oversight, governance) to ensure modularity, interoperability, explainability, and robust protection of sensitive health data. A review of current AI agent implementations highlights limitations in security, transparency, and regulatory alignment, especially in multi-agent clinical settings. The proposed framework is illustrated through a practical use case involving home-based care for elderly patients with chronic conditions, where AI agents manage medication adherence, monitor vital signs, and support clinician communication. The architecture’s flexibility is further demonstrated through its application in perioperative care coordination, underscoring its potential across diverse clinical domains. By embedding trust, accountability, and security into the design of agentic systems, this approach aims to advance the safe and ethical integration of AI into aging-focused healthcare environments. Full article

Background: First-trimester prenatal screening is a fundamental component of modern obstetric care, offering early insights into fetal health and development. A key focus of this screening is the detection of chromosomal abnormalities, such as Trisomy 21 (Down syndrome), which can have significant implications for pregnancy management and parental counseling. Over the years, various non-invasive methods have been developed, with ultrasound-based assessments becoming a cornerstone of early evaluation. Among these, the measurement of Nuchal Translucency (NT) has emerged as a critical marker. This sonographic measurement, typically performed between 11- and 13-weeks 6+ days of gestation, quantifies the fluid-filled space at the back of the fetal neck. An increased NT measurement is a well-established indicator of a higher risk for aneuploidies and other congenital conditions, including heart defects. The Fetal Medicine Foundation has established standardized criteria for this measurement to ensure its reliability and widespread adoption in clinical practice. Methods: We utilized two datasets comprising 2425 ultrasound images from Shenzhen People’s Hospital China and the National Hospital of Obstetrics and Gynecology Vietnam. The methodology employs a two-stage Deep Learning framework: first, a DenseNet121 model assesses image quality to filter non-standard planes; second, a novel DenseNet-based segmentation delineates the NT region for automated measurement. Results: The quality assessment module achieved 94% accuracy in distinguishing standard from non-standard planes. For segmentation, the proposed model achieved a Dice coefficient of 0.897 and an overall accuracy of 98.9%, outperforming the standard U-Net architecture. Clinically, 55.47% of automated measurements deviated by less than 1 mm from expert annotations, and the system demonstrated > 90% sensitivity and specificity for identifying high-risk cases (NT ≥ 2.5 mm). Conclusions: The proposed framework successfully integrates quality assurance with automated measurement, offering a robust decision-support tool to reduce variability and improve screening accuracy in prenatal care. Full article

Background: The diaphragm is the primary respiratory muscle, and its proper function is essential for efficient breathing. Respiratory muscle weakness is a common complication that can hinder the withdrawal of mechanical ventilation. This weakness not only negatively affects patients’ quality of life but also represents an economic challenge for healthcare systems, as it significantly increases medical costs due to prolonged hospitalization and the need for additional procedures to manage associated complications. Ultrasonography has emerged as a precise technique for assessing diaphragmatic function through measurements such as diaphragmatic excursion and thickening fraction, with the right hemidiaphragm being the most suitable for evaluation. However, several studies have shown that diaphragmatic ultrasound measurements vary considerably in both healthy individuals and patients, mainly due to the lack of standardization of body position during assessment. Therefore, it is necessary to investigate how patient posture influences diaphragmatic ultrasound measurements in order to standardize protocols, improve diagnostic accuracy, and support reliable clinical decision-making. We employed ultrasonography to determine the influence of changes in body position on diaphragmatic excursion in a healthy population from the city of Cali. Methods: A descriptive cross-sectional study was conducted in 36 healthy adults aged 18 to 65 years, distributed into sex and age groups. Diaphragmatic excursion was assessed using a 3.5–5 MHz ultrasound transducer. Participants were evaluated in five body positions: supine at 0°, and head-of-bed inclinations of 30°, 45°, 70°, and 90°. Results: A progressive increase in diaphragmatic excursion was observed from the supine position (0°) up to 70° inclination. The 70° inclination showed the greatest diaphragmatic mobility as measured by ultrasonography. This finding suggests the existence of an optimal intermediate position in which biomechanical conditions and intra-abdominal pressure allow more efficient diaphragmatic contraction. Conclusions: The results of this study demonstrate that changes in body position significantly influence diaphragmatic excursion in healthy individuals, with a trunk inclination of 70° yielding the greatest diaphragmatic mobility. These findings support the importance of considering body posture as a key determinant in the functional assessment of the diaphragm using ultrasonography. Full article

Artificial intelligence (AI) is rapidly reshaping gastrointestinal (GI) surgery by enhancing decision-making, intraoperative performance, and postoperative management. The integration of AI-driven systems is enabling more precise, data-informed, and personalized surgical interventions. This review provides a state-of-the-art overview of AI applications in GI surgery, organized into four key domains: surgical simulation, surgical computer vision, surgical data science, and surgical robot autonomy. A comprehensive narrative review of the literature was conducted, identifying relevant studies of technological developments in this field. In the domain of surgical simulation, AI enables virtual surgical planning and patient-specific digital twins for training and preoperative strategy. Surgical computer vision leverages AI to improve intraoperative scene understanding, anatomical segmentation, and workflow recognition. Surgical data science translates multimodal surgical data into predictive analytics and real-time decision support, enhancing safety and efficiency. Finally, surgical robot autonomy explores the progressive integration of AI for intelligent assistance and autonomous functions to augment human performance in minimally invasive and robotic procedures. Surgical AI has demonstrated significant potential across different domains, fostering precision, reproducibility, and personalization in GI surgery. Nevertheless, challenges remain in data quality, model generalizability, ethical governance, and clinical validation. Continued interdisciplinary collaboration will be crucial to translating AI from promising prototypes to routine, safe, and equitable surgical practice. Full article

Dengue virus (DENV) infection is a significant public health concern in Indonesia, with increasing cases and severity posing challenges to the country’s healthcare systems. This study aims to develop and validate a machine learning-based prediction model for assessing dengue infection cases and their severity. The model incorporates epidemiological, clinical, and environmental factors to enhance early detection and resource allocation. Additionally, the model can be utilized to support logistics planning, such as the distribution of diagnostic kits and the preparation of health facilities in each region across Indonesia, ensuring timely and targeted responses to potential outbreaks. We applied various machine learning algorithms, including logistic regression, random forest, XGBoost, and SVM models, and evaluated them to determine the most effective predictive model. The results demonstrate the model’s efficacy in predicting dengue cases and severity, which can support public health interventions and clinical decision-making. Geospatial clustering and correlation matrices were generated to visualize risk patterns and support predictions. The XGBoost model demonstrated the highest performance, achieving an accuracy of 85%. Our findings suggest that integrating clinical and environmental data through machine learning (ML) techniques can significantly improve early detection and inform resource allocation strategies. The model offers a promising approach for public health surveillance and targeted interventions in dengue-endemic regions. Full article

Various sensors are increasingly being adopted to support intelligent healthcare systems, which address the growing problem of staff shortages in assisted-living communities. In this context, detecting and assessing pain remain critical yet challenging tasks in both clinical and non-clinical settings. Traditional approaches such as self-reporting, physiological signal monitoring, and facial expression analysis often face limitations related to accessibility, equipment costs, and the need for professional support. To overcome these challenges in this work, we investigate a sensor-assisted system for pain detection and propose a lightweight framework that enables real-time classification of pain levels using acoustic sensors. Our system exploits the spectral features of voice signals that strongly correlate with pain to train Convolutional Neural Network (CNN) models. Our system has been validated through simulations in Jupiter Notebook and a Raspberry Pi-based hardware prototype. The experimental results demonstrate that the proposed three-level pain classification approach obtains an average accuracy of 72.74%, outperforming existing methods with the same pain-level granularity by 18.94–26.74% and achieving performance comparable to that of binary pain detection methods. Our hardware prototype, built from commercial off-the-shelf components for under 100 USD, achieves real-time processing speeds ranging from approximately 6 to 22 s. In addition to CNN models, our experiments demonstrate that other machine learning algorithms, such as Artificial Neural Networks, XGBoost, Random Forests, and Decision Trees, also prove to be applicable within our pain level classification framework. Full article

Therapeutic inertia in lipid-lowering treatment remains a striking paradox of modern cardiovascular medicine: at a time when the causal role of LDL-cholesterol in atherosclerotic disease is unequivocal and potent therapies are widely available, a substantial proportion of high- and very-high-risk patients still fail to receive timely treatment intensification. Contemporary European and international data consistently show fewer than one in three patients in secondary prevention achieve guideline-recommended LDL-C targets, revealing a persistent and unacceptable gap between scientific evidence and clinical reality. This narrative review examines therapeutic inertia as a key explanatory framework for this gap, describing its epidemiology, mechanisms, and clinical consequences in secondary cardiovascular prevention. We summarize the main physician-, patient-, and system-level determinants and propose recurrent clinician “phenotypes” of inertia that may help explain why opportunities are missed even in the highest-risk patients. The consequences are profound: therapeutic inertia contributes to what we propose as the conceptual framework of an “avoidable atherosclerotic burden”, the cumulative vascular injury that accrues each period in which LDL-C remains above target, translating into higher rates of avoidable cardiovascular events, and increased healthcare costs. Emerging strategies such as upfront combination therapy, decision-support systems, structured lipid pathways, and the integration of artificial intelligence offer practical tools to shift lipid management from reactive to proactive care. Overcoming therapeutic inertia is therefore not merely a matter of improving process metrics, but a clinical and ethical imperative. Closing the gap between evidence and practice requires transforming optimal lipid management from an exception into a system-level default, ensuring that every patient receives the full benefit of therapies proven to save lives. This work proposes a novel characterization of clinician ‘phenotypes’ and the concept of ‘avoidable atherosclerotic burden’ as a framework to understand and address this gap. Full article

Canine mammary tumours often present as multiple synchronous nodules, necessitating decisions regarding staging intensity and surgical planning prior to histology. We developed two preoperative nodule-level prediction models using only the medical history and physical examination of client-owned bitches with mammary disease, which were staged using the WHO-modified TNM system with a M0 classification (no distant metastasis) at the time of presentation. This retrospective study analysed 286 surgically excised mammary nodules from 92 dogs managed under a standardised mammary oncology protocol; those with inflammatory mammary carcinoma or distant metastasis were excluded. The outcomes were (i) malignant versus benign/non-neoplastic histology (for all nodules) and (ii) intermediate/high histologic grade (II–III versus I) among carcinomas. Separate multivariable Firth penalised logistic regression models accounted for within-dog clustering with dog-level bootstrap internal validation. Multiple imputation was used in a sensitivity analysis for missingness in the detection-to-surgery interval. Malignancy was confirmed in 87/286 (30.4%) of the nodules (86 carcinomas), including 35/87 (40.2%) that measured less than 1 cm. Among complete cases (153 nodules), malignancy was associated with age at neutering, maximum tumour diameter, owner-reported rapid growth and a detection-to-surgery interval of more than 3.5 months (an exploratory ROC-derived threshold) with good discrimination (area under the curve (AUC) 0.805; optimism-corrected 0.799) and acceptable calibration. Among carcinomas (83 specimen), previous mammary tumours, bloody nipple discharge and fewer synchronous nodules were associated with intermediate/high malignancy grade (AUC 0.859). Sensitivity analyses yielded directionally consistent estimates. Routinely available clinical information may provide interpretable preoperative risk stratification to support staging and surgical planning, pending external validation. Full article

Cardiac rehabilitation (CR) improves functional capacity and reduces cardiovascular morbidity, yet clinical response remains highly heterogeneous and difficult to stratify using conventional assessment. This study presents a machine-learning framework for the early stratification of CR patients into responders and non-responders based exclusively on pre-intervention baseline characteristics. A total of 122 patients undergoing an 8-week CR program were evaluated using 56 clinical, physiological and metabolic predictors. Multiple classification models were trained under a stratified 10-fold cross-validation scheme. Among them, an SVM-RBF classifier achieved the best performance and retained high discriminative capacity after dimensionality reduction. The final reduced model, based on the ten most informative features identified through convergence between Random Forest and SHAP analyses, preserved >95% of the full-feature performance. The predictors were physiologically coherent, reflecting muscular strength, ventilatory efficiency, chronotropic modulation and metabolic burden. SHAP-based explainability enabled patient-level attribution of improvement likelihood, identifying modifiable variables associated with favorable or limited training response. In parallel, we developed a web-based clinical decision-support prototype that estimates improvement probability and highlights the most influential determinants for each patient, illustrating translational applicability for precision rehabilitation planning. These findings support a transition toward personalized CR strategies guided by explainable AI and baseline phenotyping. Full article

Non-muscle-invasive bladder cancer (NMIBC) accounts for approximately 70% of newly diagnosed bladder cancer cases but exhibits significant clinical heterogeneity in treatment response and progression risk. While intravesical bacillus Calmette–GuérinCa (BCG) therapy remains the gold standard for high-risk disease, approximately 30–50% of patients experience BCG failure, creating a critical decision point between additional bladder-sparing therapy (BST) and early radical cystectomy (RC). Recent clinical data from the CISTO study suggest that, in appropriately selected patients, RC may be associated with higher 12-month recurrence-free survival while maintaining comparable cancer-specific survival and physical functioning. In this narrative review, we synthesize contemporary evidence on NMIBC genomic and transcriptomic subtypes, immune contexture, and clinicopathologic features associated with BCG response and progression risk, with emphasis on clinically oriented classification systems such as BCG Response Subtypes (BRS1–3) and UROMOL21. We highlight how tumor-intrinsic biology (e.g., EMT-associated programs), immune phenotypes (inflamed vs. immune-cold microenvironments), and genomic alterations may help refine risk stratification beyond traditional clinicopathologic models. To facilitate clinical integration, we propose a conceptual decisional framework that combines molecular subtype assignment, immune profiling, key pathologic risk factors, and patient considerations to generate probabilistic risk tiers that support selection among early RC, BST, and clinical trial strategies. Standardized multicenter cohorts and prospective evaluation are needed to validate integrated models and define their clinical utility for the precision timing of cystectomy in BCG-unresponsive NMIBC. Full article

Background: Accurate staging of bladder cancer is critical for guiding clinical management, particularly the distinction between non–muscle-invasive (T1) and muscle-invasive (T2–T4) disease. Although MRI offers superior soft-tissue contrast, image interpretation remains opera-tor-dependent and subject to inter-observer variability. This study proposes an automated deep learning framework for MRI-based bladder cancer staging to support standardized radio-logical interpretation. Methods: A sequential AI-based pipeline was developed, integrating hybrid tumor segmentation using YOLOv11 for lesion detection and DeepLabV3 for boundary refinement, followed by three deep learning classifiers (VGG19, ResNet50, and Vision Transformer) for MRI-based stage prediction. A total of 416 T2-weighted MRI images with radiology-derived stage labels (T1–T4) were included, with data augmentation applied during training. Model performance was evaluated using accuracy, precision, recall, F1-score, and multi-class AUC. Performance un-certainty was characterized using patient-level bootstrap confidence intervals under a fixed training and evaluation pipeline. Results: All evaluated models demonstrated high and broadly comparable discriminative performance for MRI-based bladder cancer staging within the present dataset, with high point estimates of accuracy and AUC, particularly for differentiating non–muscle-invasive from muscle-invasive disease. Calibration analysis characterized the probabilistic behavior of predicted stage probabilities under the current experimental setting. Conclusions: The proposed framework demonstrates the feasibility of automated MRI-based bladder cancer staging derived from radiological reference labels and supports the potential of deep learning for stand-ardizing and reproducing MRI-based staging procedures. Rather than serving as an independent clinical decision-support system, the framework is intended as a methodological and work-flow-oriented tool for automated staging consistency. Further validation using multi-center datasets, patient-level data splitting prior to augmentation, pathology-confirmed reference stand-ards, and explainable AI techniques is required to establish generalizability and clinical relevance. Full article

Background/Objectives: With rising diabetes rates, early detection of complications such as diabetic retinopathy (DR), a leading cause of visual impairment, is crucial. Incorporating DR screening into primary care has shown positive results, and integrating technological advances and artificial intelligence (AI) into these processes offers promising potential. The overall study aims to evaluate the agreement between primary care physicians, ophthalmologists, and an AI system in DR screening and referral decisions within a real-world primary care setting. Methods: In this brief report, we present the study protocol and provide an initial overview and description of our sample. A total of 1517 retinographies, obtained by a non-mydriatic retinal camera, were retrospectively collected from 301 patients with diabetes. Results: Primary care physicians referred 34.5% of the patients to ophthalmology, primarily due to opacification, suspicion of DR, or other retinal diseases. Overall, 13.62% of the participants were suspected of having DR, with 9.63% having a definitive diagnosis. Conclusions: These initial descriptive findings will be further explored in the next phase of the study through the analysis of concordance between primary care physicians, the AI-based software, and ophthalmology specialists. Future results are expected to provide valuable insights into the reliability of DR screening across different evaluators and support the integration of effective DR screening strategies into real-world clinical practice. Full article

Background/Objectives: Malignant melanoma remains a highly aggressive malignancy with substantial mortality despite advances in systemic therapy. Identifying simple and reproducible prognostic biomarkers is essential for improving risk stratification. Inflammation- and nutrition-based indices—including the Systemic Immune–Inflammation Index (SII), Systemic Inflammatory Response Index (SIRI), dynamic SIRI, and the Controlling Nutritional Status (CONUT) score—have shown prognostic value in various cancers. This study assessed the prognostic significance of these indices in patients with locally advanced or metastatic melanoma using real-world data. Methods: A retrospective cohort of 138 patients treated between 2010 and 2023 was analyzed. Baseline demographic, clinical, nutritional, and inflammatory parameters were collected. Optimal cut-off values for SII, SIRI, 6-month SIRI, and dynamic SIRI were determined using receiver operating characteristic analysis. Overall survival (OS) and progression-free survival (PFS) were evaluated using the Kaplan–Meier method, and independent predictors were identified with multivariate Cox regression. Results: Elevated baseline SII and SIRI were significantly associated with shorter overall survival. Both 6-month SIRI and dynamic SIRI demonstrated strong prognostic value, emphasizing the importance of longitudinal inflammatory changes. In multivariate analysis, response to first-line therapy emerged as the only independent predictor of disease progression. Patients with a CONUT score ≥ 3 showed significantly shorter OS and PFS in univariate analyses, underscoring the prognostic relevance of nutritional status. Conclusions: SII, SIRI, 6-month SIRI, dynamic SIRI, and CONUT are practical, accessible, and reproducible biomarkers with meaningful prognostic value in advanced melanoma. Incorporating these indices into routine clinical assessment may enhance risk stratification and support more personalized treatment decision-making. Full article

This study examines clinician interactions with a Knowledge Graph (KG)-enhanced Large Language Model (LLM) for diagnostic support, with an emphasis on the rare condition pseudohypoparathyroidism (PHP). Ten medical professionals engaged with simulated diagnostic scenarios, using the KG-enhanced LLM to support reasoning and validate differential diagnoses. Evaluation included basic model performance (RAGAS = 0.85; F1 = 0.79) and clinician-centered outcomes, such as diagnostic conclusions, confidence, adherence, and efficiency. Results show the tool was most valuable for rare or uncertain cases, increasing clinician confidence and supporting reasoning, while familiar cases elicited selective adoption with minimal AI engagement. Participant feedback indicated generally high usability, accuracy, and relevance, with most reporting improved efficiency and trust. Statistical analysis confirmed that AI assistance significantly reduced time-to-diagnosis ($t\left(8\right)=4.99$, $p=0.001$, Cohen’s $d_z=1.66$, 95% CI [73.8, 197.2]; Wilcoxon $W=0.0$, $p=0.0039$). These findings suggest that KG-enhanced LLMs can effectively augment clinician judgment in complex cases, serving as reasoning aids or educational tools while preserving clinician control over decision-making. The study emphasizes evaluating AI not only for accuracy, but also for practical utility and integration into real-world clinical workflows. Full article