Search Results (1,737)

The rapid evolution of artificial intelligence (AI) and machine learning (ML) technologies has initiated a paradigm shift in contemporary spine care. This narrative review synthesizes advances across imaging-based diagnostics, surgical planning, genomic risk stratification, and post-operative outcome prediction. We critically assess high-performing AI tools, such as convolutional neural networks for vertebral fracture detection, robotic guidance platforms like Mazor X and ExcelsiusGPS, and deep learning-based morphometric analysis systems. In parallel, we examine the emergence of ambient clinical intelligence and precision pharmacogenomics as enablers of personalized spine care. Notably, genome-wide association studies (GWAS) and polygenic risk scores are enabling a shift from reactive to predictive management models in spine surgery. We also highlight multi-omics platforms and federated learning frameworks that support integrative, privacy-preserving analytics at scale. Despite these advances, challenges remain—including algorithmic opacity, regulatory fragmentation, data heterogeneity, and limited generalizability across populations and clinical settings. Through a multidimensional lens, this review outlines not only current capabilities but also future directions to ensure safe, equitable, and high-fidelity AI deployment in spine care delivery. Full article

Cardiac magnetic resonance (CMR) imaging has become a key tool in evaluating myocardial injury secondary to coronary artery disease (CAD), providing detailed assessments of cardiac morphology, function, and tissue composition. The integration of artificial intelligence (AI), including machine learning and deep learning techniques, has enhanced the diagnostic capabilities of CMR by automating segmentation, improving image interpretation, and accelerating clinical workflows. Radiomics, through the extraction of quantitative imaging features, complements AI by revealing sub-visual patterns relevant to disease characterization. This systematic review analyzed AI applications in CMR for CAD. A structured search was conducted in MEDLINE, Web of Science, and Scopus up to 17 March 2025, following PRISMA guidelines and quality-assessed with the CLAIM checklist. A total of 106 studies were included: 46 on classification, 19 using radiomics, and 41 on segmentation. AI models were used to classify CAD vs. controls, predict major adverse cardiovascular events (MACE), arrhythmias, and post-infarction remodeling. Radiomics enabled differentiation of acute vs. chronic infarction and prediction of microvascular obstruction, sometimes from non-contrast CMR. Segmentation achieved high performance for myocardium (DSC up to 0.95), but scar and edema delineation were more challenging. Reported performance was moderate-to-high across tasks (classification AUC = 0.66–1.00; segmentation DSC = 0.43–0.97; radiomics AUC = 0.57–0.99). Despite promising results, limitations included small or overlapping datasets. In conclusion, AI and radiomics offer substantial potential to support diagnosis and prognosis of CAD through advanced CMR image analysis. Full article

This study evaluates the degree to which small and medium sized enterprises (SMEs) are prepared to adopt smart manufacturing in contrast to large enterprises, a transition that depends on the effective use of the Internet of Things, artificial intelligence (AI), and advanced analytics. While many large multinational companies have already integrated such technologies, smaller firms still struggle because of tight budgets, limited technical expertise, and difficulties in scaling new systems. To capture these realities, the investigation refines the Initiative Mittelstand-Digital für Produktionsunternehmen und Logistik-Systeme (IMPULS) Industry 4.0 readiness model, which was initially developed to help German SMEs, so that it aligns with the circumstances faced by smaller manufacturers. A thorough review of published work first surveys existing readiness and maturity frameworks, highlights their limitations, and guides the selection of new, SME-specific indicators. The framework gauges readiness across six dimensions: strategic planning and organizational design, smart factory infrastructure, lean operations, digital products, data-driven services, and workforce capability. Each dimension is operationalized through a questionnaire that offers clear benchmarks and actionable targets suited to the current resources of each enterprise. Weaving strategic vision, skill growth, and cooperative support, the approach offers managers a direct path to sharper competitiveness and lasting innovation within a changing industrial landscape. Additionally, a separate Strengths, Weaknesses, Opportunities, and Threats (SWOT) analysis is provided for each dimension based on survey data offering decision-makers concise guidance for future investment. The proposed adaptation of the IMPULS framework, validated through empirical data from 31 SMEs, introduces a novel readiness index, diagnostic gap metrics, and actionable cluster profiles tailored to developing-country industrial ecosystems. Full article

This study aimed to develop a local dataset of abnormal RBC morphology from confirmed cases of anemia and thalassemia in Thailand, providing a foundation for medical image analysis and future AI-assisted diagnostics. Blood smear samples from six hematological disorders were collected between April and May 2025, with twelve regions of interest segmented into approximately 34,000 single-cell images. To characterize cell variability, a convolutional autoencoder was applied to extract latent features, while ellipse fitting was used to quantify cell geometry. Expert hematologists validated representative clusters to ensure clinical accuracy, and data augmentation was employed to address class imbalance and expand rare morphological types. From the dataset, 14,089 high-quality single-cell images were used to classify RBC morphology into 36 clinically meaningful categories. Unlike existing datasets that rely on limited or curated samples, this dataset reflects population-specific characteristics and morphological diversity relevant to Southeast Asia. The results demonstrate the feasibility of establishing scalable and interpretable datasets that integrate computational methods with expert knowledge. The proposed dataset serves as a robust resource for advancing hematology research and contributes to bridging traditional diagnostics with AI-driven clinical support systems. Full article

Integration of machine learning (ML) and artificial intelligence (AI) into point-of-care (POC) sensor systems represents a transformative advancement in healthcare. This integration enables sophisticated data analysis and real-time decision-making in emergency and intensive care settings. AI and ML algorithms can process complex biomedical data, improve diagnostic accuracy, and enable early disease detection for better patient outcomes. Predictive analytics in POC devices supports proactive healthcare by analyzing data to forecast health issues and facilitating early intervention and personalized treatment. This review covers the key areas of ML and AI integration in POC devices, including data analysis, pattern recognition, real-time decision support, predictive analytics, personalization, automation, and workflow optimization. Examples of current POC devices that use ML and AI include AI-powered blood glucose monitors, portable imaging devices, wearable cardiac monitors, AI-enhanced infectious disease detection, and smart wound care sensors are also discussed. The review further explores new directions for POC sensors and ML integration, including mental health monitoring, nutritional monitoring, metabolic health tracking, and decentralized clinical trials (DCTs). We also examined the impact of integrating ML and AI into POC devices on healthcare accessibility, efficiency, and patient outcomes. Full article

Breast cancer is one of the leading causes of death among women of all ages and backgrounds globally. In recent years, the growing deficit of expert radiologists—particularly in underdeveloped countries—alongside a surge in the number of images for analysis, has negatively affected the ability to secure timely and precise diagnostic results in breast cancer screening. AI technologies offer powerful tools that allow for the effective diagnosis and survival forecasting, reducing the dependency on human cognitive input. Towards this aim, this research introduces a deep meta-learning framework for swift analysis of mammography images—combining a Siamese network model with a triplet-based loss function—to facilitate automatic screening (recognition) of potentially suspicious breast cancer cases. Three pre-trained deep CNN architectures, namely GoogLeNet, ResNet50, and MobileNetV3, are fine-tuned and scrutinized for their effectiveness in transforming input mammograms to a suitable embedding space. The proposed framework undergoes a comprehensive evaluation through a rigorous series of experiments, utilizing two different, publicly accessible, and widely used datasets of digital X-ray mammograms: INbreast and CBIS-DDSM. The experimental results demonstrate the framework’s strong performance in differentiating between tumorous and normal images, even with a very limited number of training samples, on both datasets. Full article

Introduction: We aimed to prove integration of advanced machine learning methods within a robust ensemble framework can enhance clinical decision-support for neurologists managing patients in the emergency department (ED). Methods: We engineered an ensemble framework leveraging the capabilities of the Gemini 1.5-pro-002 large language model (LLM). The model was enhanced using prompt engineering and retrieval-augmented generation (RAG). Predictive modeling achieved by combining eXtreme Gradient Boosting (XGBoost) and logistic regression for optimal accuracy in clinical decision-making. Key clinical outcomes, such as admission and mortality, were assessed. A random subset of 100 cases was reviewed by three senior neurologists to evaluate the alignment of the AI’s predictions with expert clinical judgment. Results: We retrospectively analyzed 1368 consecutive ED patients who underwent neurological consultations, assessing their clinical features, diagnostic tests, and admission outcomes. Patients admitted were typically older and had higher mortality rates, shorter intervals to neurological evaluation, and a higher incidence of acute stroke compared to those discharged. For the primary analysis (n = 250), the Neuro artificial intelligence (AI) model demonstrated significant performance metrics, achieving an area under the curve (AUC) of 0.88 for general admission predictions in comparison to actual outcomes, an AUC of 0.86 for neurological department admissions, 0.93 for long-term mortality risk, and 1 for 48 h mortality risk. Our Neuro AI model predictions showed a strong correlation with expert consensus (Pearson correlation 0.79, p < 0.001), indicating its ability to provide consistent support amid divergent clinical opinions. Conclusions: Our Neuro AI model accurately predicted hospital admissions (AUC = 0.88) and neurological department admissions (AUC = 0.86), demonstrating strong alignment with expert clinical judgment. Full article

Background: Skin cancer represents one of the most prevalent malignancies worldwide, with melanoma accounting for approximately 75% of skin cancer-related deaths despite comprising fewer than 5% of cases. Early detection dramatically improves survival rates from 14% to over 99%, highlighting the urgent need for accurate and accessible diagnostic tools. While deep learning has shown promise in dermatological diagnosis, existing approaches lack clinical explainability and deployable interfaces that bridge the gap between research innovation and practical healthcare applications. Methods: This study implemented a comprehensive multimodal deep learning framework using the HAM10000 dataset (10,015 dermatoscopic images across seven diagnostic categories). Three CNN architectures (DenseNet-121, EfficientNet-B3, ResNet-50) were systematically compared, integrating patient metadata, including age, sex, and anatomical location, with dermatoscopic image analysis. The first implementation of XRAI (eXplanation with Region-based Attribution for Images) explainability for skin lesion classification was developed, providing spatially coherent explanations aligned with clinical reasoning patterns. A deployable web-based clinical interface was created, featuring real-time inference, comprehensive safety protocols, risk stratification, and evidence-based cosmetic recommendations for benign conditions. Results: EfficientNet-B3 achieved superior performance with 89.09% test accuracy and 90.08% validation accuracy, significantly outperforming DenseNet-121 (82.83%) and ResNet-50 (78.78%). Test-time augmentation improved performance by 1.00 percentage point to 90.09%. The model demonstrated excellent performance for critical malignant conditions: melanoma (81.6% confidence), basal cell carcinoma (82.1% confidence), and actinic keratoses (88% confidence). XRAI analysis revealed clinically meaningful attention patterns focusing on irregular pigmentation for melanoma, ulcerated borders for basal cell carcinoma, and surface irregularities for precancerous lesions. Error analysis showed that misclassifications occurred primarily in visually ambiguous cases with high correlation (0.855–0.968) between model attention and ideal features. The web application successfully validated real-time diagnostic capabilities with appropriate emergency protocols for malignant conditions and comprehensive cosmetic guidance for benign lesions. Conclusions: This research successfully developed the first clinically deployable skin lesion classification system combining diagnostic accuracy with explainable AI and practical patient guidance. The integration of XRAI explainability provides essential transparency for clinical acceptance, while the web-based deployment democratizes access to advanced dermatological AI capabilities. Comprehensive validation establishes readiness for controlled clinical trials and potential integration into healthcare workflows, particularly benefiting underserved regions with limited specialist availability. This work bridges the critical gap between research-grade AI models and practical clinical utility, establishing a foundation for responsible AI integration in dermatological practice. Full article

Diabetic Retinopathy (DR) is a leading cause of vision impairment globally, underscoring the need for accurate and early diagnosis to prevent disease progression. Although fundus imaging serves as a cornerstone of Computer-Aided Diagnosis (CAD) systems, several challenges persist, including lesion scale variability, blurry morphological patterns, inter-class imbalance, limited labeled datasets, and computational inefficiencies. To address these issues, this study proposes an end-to-end diagnostic framework that integrates an enhanced preprocessing pipeline with a novel deep learning architecture, Hierarchical-Inception-Residual-Dense Network (HIRD-Net). The preprocessing stage combines Contrast Limited Adaptive Histogram Equalization (CLAHE) with Dilated Difference of Gaussian (D-DoG) filtering to improve image contrast and highlight fine-grained retinal structures. HIRD-Net features a hierarchical feature fusion stem alongside multiscale, multilevel inception-residual-dense blocks for robust representation learning. The Squeeze-and-Excitation Channel Attention (SECA) is introduced before each Global Average Pooling (GAP) layer to refine the Feature Maps (FMs). It further incorporates four GAP layers for multi-scale semantic aggregation, employs the Hard-Swish activation to enhance gradient flow, and utilizes the Focal Loss function to mitigate class imbalance issues. Experimental results on the IDRiD-APTOS2019, DDR, and EyePACS datasets demonstrate that the proposed framework achieves 93.46%, 82.45% and 79.94% overall classification accuracy using only 4.8 million parameters, highlighting its strong generalization capability and computational efficiency. Furthermore, to ensure transparent predictions, an Explainable AI (XAI) approach known as Gradient-weighted Class Activation Mapping (Grad-CAM) is employed to visualize HIRD-Net’s decision-making process. Full article

Hemorrhagic complications during pleural interventions—such as thoracentesis and chest tube insertion—remain a significant clinical concern, primarily due to inadvertent injury of the intercostal artery (ICA). The highly variable ICA anatomy is frequently not visualized on conventional imaging, limiting the reliability of landmark-based techniques. Color Doppler thoracic ultrasound (CDUS) has emerged as a non-invasive, real-time modality capable of identifying ICAs and their anatomical variants prior to pleural access. This narrative review synthesizes current evidence on CDUS-guided ICA screening, focusing on its technical principles, diagnostic performance, and clinical applicability. While feasibility and utility are supported by multiple observational studies, robust evidence demonstrating a reduction in bleeding complications is still lacking. Barriers to widespread implementation include heterogeneous scanning protocols, operator dependency, and the absence of standardized training. We discuss the anatomical rationale for pre-procedural vascular mapping and highlight emerging protocols aimed at standardizing ICA visualization. Although not yet incorporated into major clinical guidelines, CDUS represents a promising tool to enhance procedural safety. Emerging AI applications may further improve vessel detection by reducing operator dependency and enhancing reproducibility. High-quality prospective studies are essential to validate potential clinical benefits, optimize implementation strategies, and support integration into routine pleural practice. Full article

Purpose: This review aims to synthesize current knowledge of anatomical variations of the popliteofibular ligament (PFL) and evaluate the clinical relevance of the classification system proposed by Olewnik et al. in the context of the diagnosis, surgical treatment, and rehabilitation of posterolateral corner (PLC) injuries. Methods: A comprehensive analysis of anatomical, surgical, and radiological studies concerning the PFL was conducted. The implications of PFL morphological variants were examined across clinical applications, with an emphasis on reconstructive strategies, imaging interpretation, and rehabilitation planning. Emerging research directions, including AI-supported imaging and personalized algorithms, were also explored. Results: Olewnik’s classification identifies three distinct types of PFL, each with unique structural and biomechanical properties. Recognizing these variants enhances intraoperative orientation, facilitates tailored surgical techniques, and supports individualized rehabilitation protocols. Variant-specific biomechanics, identified via cadaveric studies and imaging, are essential for optimizing functional outcomes and minimizing postoperative instability. Furthermore, the classification offers a platform for developing future diagnostic and decision-support tools using artificial intelligence. Conclusions: The Olewnik et al. classification system should be adopted as a modern anatomical standard for the PFL. Its integration into clinical practice has the potential to improve surgical precision, reduce complication rates, and enhance patient-specific treatment planning. This framework also supports future advancements in orthopedic imaging, education, and AI-driven diagnostics. Beyond descriptive anatomy, we provide a pragmatic surgical algorithm for PLC repair/reconstruction that accounts for scar- and fibrosis-dominated fields and the limited bone stock of the fibular head. Full article

Background: Artificial intelligence (AI) can improve efficiency, documentation, and diagnostic quality in ophthalmology. This study examined clinical AI adoption, institutional readiness, perceived utility, trust, ethical concerns, and educational needs among Swiss ophthalmologists and residents. Methods: In May 2025, an anonymous online survey was distributed to board-certified ophthalmologists and residents across Switzerland. The structured questionnaire addressed clinical AI use, institutional infrastructure, perceptions of diagnostic utility, trust, ethical–legal concerns, and educational preparedness. Responses were recorded on five-point Likert scales. Results: Of 106 respondents (mean age 42.4 ± 11.4 years, 48.1% female), 20.8% reported current clinical AI use. Willingness to use AI exceeded 65% across all 10 diagnostic scenarios, but active use remained ≤12.1%. Institutional readiness was low: 6.6% reported AI-related guidelines, 26.4% had access to an institutional AI contact person, and 28.3% received supervisor support (more often among residents). While 80% agreed that AI can support diagnostics, only 12.1% trusted AI recommendations as much as those from colleagues; 87.9% critically reviewed the results, and 93.9% endorsed the use of AI in an assistive but not independently decision-making role. Ethical–legal concerns included unresolved liability (74.8%), informed consent (66.7%), and data protection adequacy (49.5%). Structured AI education was supported by 77.8%, yet only 15.1% felt prepared, and two-thirds (66.7%) indicated they would use AI more with better training. Conclusions: Ophthalmologists and residents in Switzerland express strong interest in the clinical use of AI and recognize its diagnostic potential. Major barriers include insufficient institutional structures, lack of regulatory clarity, and inadequate educational preparation. Addressing these deficits will be essential for responsible AI integration into ophthalmologic practice. Full article

Background: This study investigates the diagnostic reliability of an artificial intelligence (AI)-based software (Diagnocat) in caries, dental restorations, missing teeth, and periodontal bone loss on panoramic radiographs (PRs), comparing its performance with evaluations from three independent dental experts serving as ground truth. Methods: A total of 104 PRs were analyzed using Diagnocat, which assigned a likelihood score (0–100%) for each condition. The same images were independently evaluated by three experts. The diagnostic performance of Diagnocat was evaluated using sensitivity, specificity, and receiver operating characteristic (ROC) curve analysis, while inter-rater agreement was assessed through Cohen’s kappa (κ). Results: Diagnocat showed high overall sensitivity (99.2%), identifying nearly all conditions marked as present by human evaluators. Specificity was low (8.7%), indicating a tendency to overdiagnose. Overall accuracy was 96%, likely influenced by the coexistence of multiple conditions. Sensitivity ranged from 77% to 96%, while specificity varied: dental restorations (66%), missing teeth (68%), periodontal bone loss (71%), and caries signs (47%). The agreement was fair for dental restorations (κ = 0.39) and missing teeth (κ = 0.37), but poor for caries signs (κ = −0.15) and periodontal bone loss (κ = −0.62). Conclusions: Diagnocat shows promise as a screening tool due to its high sensitivity, but low specificity and poor agreement for certain conditions warrant cautious interpretation alongside clinical evaluation. Full article

Medical physicists are transforming physiological measurements and electrophysiological applications by addressing challenges like motion artifacts and regulatory compliance through advanced signal processing, artificial intelligence (AI), and statistical rigor. Their innovations in wearable electrophysiology achieve 8–12 dB signal-to-noise ratio (SNR) improvements in EEG, 60% motion artifact reduction, and 94.2% accurate AI-driven arrhythmia detection at 12 μW power. In precision neurology, machine learning (ML) with evoked potentials (EPs) predicts spinal cord injury (SCI) recovery and multiple sclerosis (MS) progression with 79.2% accuracy based on retrospective data from 560 SCI/MS patients. By integrating multimodal data (EPs, MRI), developing quantum sensors, and employing federated learning, these can enhance diagnostic precision and prognostic accuracy. Clinical applications span epilepsy, stroke, cardiac monitoring, and chronic pain management, reducing diagnostic errors by 28% and optimizing treatments like deep brain stimulation (DBS). In this paper, we review the current state of wearable devices and provide some insight into possible future directions. Embedding medical physicists into standardization efforts is critical to overcoming barriers like quantum sensor power consumption, advancing personalized, evidence-based healthcare. Full article

CD19-targeted therapies, including monoclonal antibodies, antibody–drug conjugates, and chimeric antigen receptor (CAR) T-cell products, have significantly improved outcomes in relapsed/refractory diffuse large B-cell lymphoma (R/R DLBCL). Despite their clinical efficacy, resistance and antigen modulation pose substantial challenges, especially in patients requiring sequential therapy. This review provides a comprehensive overview of CD19 biology and its relevance as a therapeutic target. We examine mechanisms of resistance such as antigen loss, epitope masking, and T-cell exhaustion, as well as the implications of tumor microenvironmental immunosuppression. Future efforts should prioritize the integration of real-time diagnostics, such as flow cytometry, immunohistochemistry, and transcriptomic profiling, and AI-assisted predictive models to optimize therapeutic sequencing and expand access to personalized immunotherapy. Full article