Search Results (6,869)

Thyroid-related diseases, particularly thyroid cancer, are rising globally, emphasizing the critical need for the early detection and accurate screening of thyroid nodules. Ultrasound imaging has inherent limitations—high noise, low contrast, and blurred boundaries—that make manual interpretation subjective and error-prone. To address these challenges, YOLO-Thyroid, an improved model for the automatic detection of thyroid nodules in ultrasound images, is presented herein. Building upon the YOLOv8 architecture, YOLO-Thyroid introduces the C2fA module—an extension of C2f that incorporates Coordinate Attention (CA)—to enhance feature extraction. Additionally, loss functions were incorporated, including class-weighted binary cross-entropy to alleviate class imbalance and SCYLLA-IoU (SIoU) to improve localization accuracy during boundary regression. A publicly available thyroid ultrasound image dataset was optimized using format conversion and data augmentation. The experimental results demonstrate that YOLO-Thyroid outperforms mainstream object detection models across multiple metrics, achieving a higher detection precision of 54%. The recall, calculated based on the detection of nodules containing at least one feature suspected of being malignant, reaches 58.2%, while the model maintains a lightweight structure. The proposed method significantly advances ultrasound nodule detection, providing an effective and practical solution for enhancing diagnostic accuracy in medical imaging. Full article

Background/Objectives: The role of artificial intelligence (AI) in radiological image analysis is rapidly evolving. This study evaluates the diagnostic performance of Chat Generative Pre-trained Transformer Omni (GPT-4 Omni) in detecting intracranial hemorrhages (ICHs) in non-contrast computed tomography (NCCT) images, along with its ability to classify hemorrhage type, stage, anatomical location, and associated findings. Methods: A retrospective study was conducted using 240 cases, comprising 120 ICH cases and 120 controls with normal findings. Five consecutive NCCT slices per case were selected by radiologists and analyzed by ChatGPT-4o using a standardized prompt with nine questions. Diagnostic accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were calculated by comparing the model’s results with radiologists’ assessments (the gold standard). After a two-week interval, the same dataset was re-evaluated to assess intra-observer reliability and consistency. Results: ChatGPT-4o achieved 100% accuracy in identifying imaging modality type. For ICH detection, the model demonstrated a diagnostic accuracy of 68.3%, sensitivity of 79.2%, specificity of 57.5%, PPV of 65.1%, and NPV of 73.4%. It correctly classified 34.0% of hemorrhage types and 7.3% of localizations. All ICH-positive cases were identified as acute phase (100%). In the second evaluation, diagnostic accuracy improved to 73.3%, with a sensitivity of 86.7% and a specificity of 60%. The Cohen’s Kappa coefficient for intra-observer agreement in ICH detection indicated moderate agreement (κ = 0.469). Conclusions: ChatGPT-4o shows promise in identifying imaging modalities and ICH presence but demonstrates limitations in localization and hemorrhage type classification. These findings highlight its potential for improvement through targeted training for medical applications. Full article

Background/Objectives: Antimicrobial resistance represents a growing global health crisis, demanding innovative approaches to improve antibiotic stewardship. Artificial intelligence (AI) chatbots based on large language models have shown potential as tools to support clinicians, especially non-specialists, in optimizing antibiotic therapy. This review aims to synthesize current evidence on the capabilities, limitations, and future directions for AI chatbots in enhancing antibiotic selection and patient outcomes. Methods: A narrative review was conducted by analyzing studies published in the last five years across databases such as PubMed, SCOPUS, Web of Science, and Google Scholar. The review focused on research discussing AI-based chatbots, antibiotic stewardship, and clinical decision support systems. Studies were evaluated for methodological soundness and significance, and the findings were synthesized narratively. Results: Current evidence highlights the ability of AI chatbots to assist in guideline-based antibiotic recommendations, improve medical education, and enhance clinical decision-making. Promising results include satisfactory accuracy in preliminary diagnostic and prescriptive tasks. However, challenges such as inconsistent handling of clinical nuances, susceptibility to unsafe advice, algorithmic biases, data privacy concerns, and limited clinical validation underscore the importance of human oversight and refinement. Conclusions: AI chatbots have the potential to complement antibiotic stewardship efforts by promoting appropriate antibiotic use and improving patient outcomes. Realizing this potential will require rigorous clinical trials, interdisciplinary collaboration, regulatory clarity, and tailored algorithmic improvements to ensure their safe and effective integration into clinical practice. Full article

Neonatal mortality remains a critical global challenge, particularly in resource-limited settings with restricted access to advanced diagnostic tools. Early detection of life-threatening conditions like Sepsis and Respiratory Distress Syndrome (RDS), which significantly contribute to neonatal deaths, is crucial for timely interventions and improved survival rates. This study investigates the use of newborn cry sounds, specifically the expiratory segments (the most informative parts of cry signals) as non-invasive biomarkers for early disease diagnosis. We utilized an expanded and balanced cry dataset, applying Self-Supervised Learning (SSL) models—wav2vec 2.0, WavLM, and HuBERT—to extract feature representations directly from raw cry audio signals. This eliminates the need for manual feature extraction while effectively capturing complex patterns associated with sepsis and RDS. A classifier consisting of a single fully connected layer was placed on top of the SSL models to classify newborns into Healthy, Sepsis, or RDS groups. We fine-tuned the SSL models and classifiers by optimizing hyperparameters using two learning rate strategies: linear and annealing. Results demonstrate that the annealing strategy consistently outperformed the linear strategy, with wav2vec 2.0 achieving the highest accuracy of approximately 90% (89.76%). These findings highlight the potential of integrating this method into Newborn Cry Diagnosis Systems (NCDSs). Such systems could assist medical staff in identifying critically ill newborns, prioritizing care, and improving neonatal outcomes through timely interventions. Full article

Despite significant advancements in the automatic classification of skin lesions using artificial intelligence (AI) algorithms, skepticism among physicians persists. This reluctance is primarily due to the lack of transparency and explainability inherent in these models, which hinders their widespread acceptance in clinical settings. The primary objective of this study is to develop a highly accurate AI-based algorithm for skin lesion classification that also provides visual explanations to foster trust and confidence in these novel diagnostic tools. By improving transparency, the study seeks to contribute to earlier and more reliable diagnoses. Additionally, the research investigates the impact of Test Time Augmentation (TTA) on the performance of six Convolutional Neural Network (CNN) architectures, which include models from the EfficientNet, ResNet (Residual Network), and ResNeXt (an enhanced variant of ResNet) families. To improve the interpretability of the models’ decision-making processes, techniques such as t-distributed Stochastic Neighbor Embedding (t-SNE) and Gradient-weighted Class Activation Mapping (Grad-CAM) are employed. t-SNE is utilized to visualize the high-dimensional latent features of the CNNs in a two-dimensional space, providing insights into how the models group different skin lesion classes. Grad-CAM is used to generate heatmaps that highlight the regions of input images that influence the model’s predictions. Our findings reveal that Test Time Augmentation enhances the balanced multi-class accuracy of CNN models by up to 0.3%, achieving a balanced accuracy rate of 97.58% on the International Skin Imaging Collaboration (ISIC 2019) dataset. This performance is comparable to, or marginally better than, more complex approaches such as Vision Transformers (ViTs), demonstrating the efficacy of our methodology. Full article

Artificial intelligence (AI) is increasingly applied in a wide range of healthcare and Intensive Care Unit (ICU) areas to serve—among others—as a tool for disease detection and prediction, as well as for healthcare resources’ management. Since sepsis is a high mortality and rapidly developing organ dysfunction disease afflicting millions in ICUs and costing huge amounts to treat, the area can benefit from the use of AI tools for early and informed diagnosis and antibiotic administration. Additionally, resource allocation plays a crucial role when patient flow is increased, and resources are limited. At the same time, sensitive data use raises the need for ethical guidelines and reflective datasets. Additionally, explainable AI is applied to handle AI opaqueness. This study aims to present existing clinical approaches for infection assessment in terms of scoring systems and diagnostic biomarkers, along with their limitations, and an extensive overview of AI applications in healthcare and ICUs in terms of (a) sepsis detection/prediction and sepsis mortality prediction, (b) length of ICU/hospital stay prediction, and (c) ICU admission/hospitalization prediction after Emergency Department admission, each constituting an important factor towards either prompt interventions and improved patient wellbeing or efficient resource management. Challenges of AI applications in ICU are addressed, along with useful recommendations to mitigate them. Explainable AI applications in ICU are described, and their value in validating, and translating predictions in the clinical setting is highlighted. The most important findings and future directions including multimodal data use and Transformer-based models are discussed. The goal is to make research in AI advances in ICU and particularly sepsis prediction more accessible and provide useful directions on future work. Full article

Accurate and precise prediction of actual evapotranspiration (AET) on a large scale is a fundamental issue in natural sciences such as forestry (especially in species selection and planning), hydrology, and agriculture. With the estimation of AET, controlling dams, agriculture, and irrigation and providing potable and utility water supply for industry would be possible. Gathering reliable AET data is possible only with a sufficient weather station network, which is rarely established in many countries like Turkey. Therefore, climate models must be developed for reliable AET data, especially in countries with complex terrains. This study aimed to generate spatiotemporal AET surfaces using the Australian National University spline (ANUSPLIN) model and compare the results with the maps generated by the inverse distance weighting (IDW) and co-kriging (KRG) interpolation techniques. Findings from the interpolated surfaces were validated in three ways: (1) some diagnostics from the surface fitting model include measures such as signal, mean, root mean square predictive error, root mean square error estimate, root mean square residual of the spline, and the estimated standard deviation of noise in the spline; (2) a comparison of common error statistics between the interpolated surfaces and withheld climate data; and (3) evaluation by comparing model results with other interpolation methods using metrics such as mean absolute error, mean error, root mean square error, and adjusted R² (R²_adj). The correlation between AET and normalized difference vegetation index (NDVI) was also evaluated. ANUSPLIN outperformed the other techniques, accounting for 73 to 94% (RMSE: 3.7 to 26.1%) of the seasonal variation in AET with an annual value of 83% (RMSE: 10.0%). The correlation coefficient between observed and predicted AET based on NDVI ranged from 0.49 to 0.71 for point-based and 0.62 to 0.83 for polygon-based data. The generated maps at a spatial resolution of 0.005° × 0.005° could provide valuable insights to researchers and practitioners in the natural resources management domain. Full article

Background/Objectives: Medication-overuse headache (MOH) is a disabling condition affecting patients with chronic migraine resulting from excessive use of acute headache medication. It is characterized by both pain modulation and addiction-like mechanisms involving the brainstem raphe, a region critical to serotonergic signaling. This study investigates whether alterations in the brainstem raphe, assessed via transcranial sonography (TCS), are associated with MOH and independent of depressive symptoms, aiming to explore their utility as a biomarker. Methods: This prospective case-control study included 60 migraine patients (15 with MOH) and 7 healthy controls. Comprehensive clinical and psychometric assessments were performed to evaluate headache burden, medication use, and depressive symptoms. TCS was used to assess brainstem raphe echogenicity, with findings analyzed using generalized linear models adjusted for depression. Results: Non-visibility of the brainstem raphe was significantly associated with MOH, with an unadjusted odds ratio (OR) of 6.88 (95% CI: 1.32–36.01, p = 0.02). After adjusting for depressive symptoms, this association remained significant, with an adjusted OR of 1.85 (95% CI: 1.02–3.34, p = 0.041). TCS demonstrated good intraclass correlation, highlighting its reproducibility and ability to detect changes relevant to MOH pathophysiology. Conclusions: Brainstem raphe alterations are associated with MOH and may serve as a potential biomarker for its diagnosis and management. TCS offers a non-invasive, cost-effective tool for identifying MOH-specific mechanisms, which could improve clinical decision-making and support personalized care in chronic headache disorders. Further studies are needed to validate these findings and refine the clinical applications of brainstem-focused diagnostics. Full article

Cancer’s heterogeneity presents significant challenges in accurate diagnosis and effective treatment, including the complexity of identifying tumor subtypes and their diverse biological behaviors. This review examines how feature selection techniques address these challenges by improving the interpretability and performance of machine learning (ML) models in high-dimensional datasets. Feature selection methods—such as filter, wrapper, and embedded techniques—play a critical role in enhancing the precision of cancer diagnostics by identifying relevant biomarkers. The integration of multi-omics data and ML algorithms facilitates a more comprehensive understanding of tumor heterogeneity, advancing both diagnostics and personalized therapies. However, challenges such as ensuring data quality, mitigating overfitting, and addressing scalability remain critical limitations of these methods. Artificial intelligence (AI)-powered feature selection offers promising solutions to these issues by automating and refining the feature extraction process. This review highlights the transformative potential of these approaches while emphasizing future directions, including the incorporation of deep learning (DL) models and integrative multi-omics strategies for more robust and reproducible findings. Full article

Colic is a leading cause of mortality in horses, demanding precise and timely interventions. This study integrates machine learning and explainable artificial intelligence (XAI) to predict survival outcomes in horses with colic, using clinical, procedural, and diagnostic data. Random forest and XGBoost emerged as top-performing models, achieving F1 scores of 85.9% and 86.1%, respectively. SHAP (Shapley additive explanations) was employed to provide interpretable insights, offering both global and local explanations for model predictions. The analysis revealed that key features, such as pulse rate, lesion type, and total protein levels, significantly influenced survival likelihood. Local interpretations highlighted the unique contribution of clinical factors to individual cases, enabling personalized insights that guide targeted treatment strategies. These tailored predictions empower veterinarians to prioritize interventions based on the specific conditions of each horse, moving beyond generalized care protocols. By combining predictive accuracy with interpretability, this study advances precision veterinary medicine, enhancing outcomes for equine colic cases and setting a benchmark for future applications of AI in animal health. Full article

Background/Objectives: The failure of physiological left-right (LR) patterning, a critical embryological process responsible for establishing the asymmetric positioning of internal organs, leads to a spectrum of congenital abnormalities characterized by laterality defects, collectively known as “heterotaxy”. MMP21 biallelic variants have recently been associated with heterotaxy syndrome and congenital heart defects (CHD). However, the genotype–phenotype correlations and the underlying pathogenic mechanisms remain poorly understood. Methods: Patients harboring biallelic MMP21 missense variants who underwent diagnostic genetic testing for CHD or heterotaxy were recruited at the Institute for Maternal and Child Health—I.R.C.C.S. “Burlo Garofolo”. Additionally, a literature review on MMP21 missense variants was conducted, and clinical data from reported patients, along with molecular data from in silico and modeling tools, were collected. Results: A total of 18 MMP21 missense variants were reported in 26 patients, with the majority exhibiting CHD (94%) and variable extra-cardiac manifestations (64%). In our cohort, through Whole-Exome Sequencing (WES) analysis, the missense p.(Met301Ile) variant was identified in two unrelated patients, who both presented with heterotaxy syndrome. Conclusions: Our comprehensive analysis of MMP21 missense variants supports the pathogenic role of the p.(Met301Ile) variant and provides significant insights into the disease pathogenesis. Specifically, missense variants are distributed throughout the gene without clustering in specific regions, and phenotype comparisons between patients carrying missense variants in compound heterozygosity or homozygosity do not reveal significant differences. These findings may suggest a potential loss-of-function mechanism for MMP21 missense variants, especially those located in the catalytic domain, and highlight their critical role in the pathogenesis of heterotaxy syndrome. Full article

Background/Objectives: Despite advances in diagnostic techniques, accurate classification of lung cancer subtypes remains crucial for treatment planning. Traditional methods like genomic studies face limitations such as high cost and complexity. This study investigates whether integrating atomic force microscopy (AFM) measurements with conventional clinical and histopathological data can improve lung cancer subtype classification. Methods: We developed and analyzed a novel dataset combining clinical, histopathological, and AFM-derived biophysical characteristics from 37 lung cancer patients. Various machine learning techniques were evaluated, with a focus on Bayesian Networks due to their ability to handle complex data with missing values. Leave-One-Out Cross-Validation was employed to assess model performance. Results: The integration of biophysical features improved classification accuracy from 86.49% to 89.19% using a data-driven Bayesian Network model, though this improvement was not statistically significant (p = 1.0). Four key features were identified as highly predictive: sex, vascular invasion, perineural invasion, and ALK mutation. A simplified model using only these features achieved identical performance with significantly reduced complexity (BIC 51.931 vs. 268.586). Conclusions: While AFM-derived measurements showed promise for enhancing lung cancer subtype classification, larger datasets are needed to fully validate their impact. Our findings demonstrate the feasibility of incorporating biophysical measurements into cancer classification frameworks and identify the most predictive features for accurate diagnosis. Further research with expanded datasets is needed to validate these findings. Full article

Objectives: This study investigates the potential of artificial intelligence (AI), specifically large language models (LLMs) like ChatGPT, to enhance decision support in diagnosing epilepsy. AI tools can improve diagnostic accuracy, efficiency, and decision-making speed. The aim of this study was to compare the level of agreement in epilepsy diagnosis between human experts (epileptologists) and AI (ChatGPT), using the 2014 International League Against Epilepsy (ILAE) criteria, and to identify potential predictors of diagnostic errors made by ChatGPT. Methods: A retrospective analysis was conducted on data from 597 patients who visited the emergency department for either a first epileptic seizure or a recurrence. Diagnoses made by experienced epileptologists were compared with those made by ChatGPT 4.0, which was trained on the 2014 ILAE epilepsy definition. The agreement between human and AI diagnoses was assessed using Cohen’s kappa statistic. Sensitivity and specificity were compared using 2 × 2 contingency tables, and multivariate analyses were performed to identify variables associated with diagnostic errors. Results: Neurologists diagnosed epilepsy in 216 patients (36.2%), while ChatGPT diagnosed it in 109 patients (18.2%). The agreement between neurologists and ChatGPT was very low, with a Cohen’s kappa value of −0.01 (95% confidence intervals, CI: −0.08 to 0.06). ChatGPT’s sensitivity was 17.6% (95% CI: 14.5–20.6), specificity was 81.4% (95% CI: 78.2–84.5), positive predictive value was 34.8% (95% CI: 31.0–38.6), and negative predictive value was 63.5% (95% CI: 59.6–67.4). ChatGPT made diagnostic errors in 41.7% of the cases, with errors more frequent in older patients and those with specific medical conditions. The correct classification was associated with acute symptomatic seizures of unknown etiology. Conclusions: ChatGPT 4.0 does not reach human clinicians’ performance in diagnosing epilepsy, showing poor performance in identifying epilepsy but better at recognizing non-epileptic cases. The overall concordance between human clinicians and AI is extremely low. Further research is needed to improve the diagnostic accuracy of ChatGPT and other LLMs. Full article

The tissue specificity of DNA methylation refers to the significant differences in DNA methylation patterns in different tissues. This specificity regulates gene expression, thereby supporting the specific functions of each tissue and the maintenance of normal physiological activities. Abnormal tissue-specific patterns of DNA methylation are closely related to age-related diseases. This abnormal methylation pattern affects the regulation of gene expression, which may lead to changes in cell function and promote the occurrence of pathological conditions. By analyzing the differences in these methylation patterns, key CpG sites for disease diagnosis can be effectively screened. The main goal of this paper is to use the characteristics associated with tissue-specific abnormal expression and disease to construct an age-related disease diagnosis model. First, we combined chi-square tests and logistic regression to identify tissue-specific and disease-specific CpG sites, laying the foundation for accurate medical diagnosis, and verified the biological relevance of these CpG sites through enrichment analysis. Then we used the Transformer model to fit these CpG sites and realized the automatic diagnosis of age-related diseases. Our work proves that the tissue specificity of DNA methylation has the potential to diagnose age-related diseases, and proves the scientific nature of our proposed diagnostic method from a biological perspective. Full article

Rolling bearings, as critical components of rotating machinery, directly affect the reliability and efficiency of the system. Due to extended operation under high load, harsh environmental conditions, and continuous use, bearings become more susceptible to failure, leading to a higher likelihood of malfunction. To prevent sudden failures, reduce downtime, and optimize maintenance strategies, early and accurate diagnosis of rolling bearing faults is essential. Although existing methods have achieved certain success in processing acoustic and vibration signals, they still face challenges such as insufficient feature fusion, inflexible weight allocation, lack of effective feature selection mechanisms, and low computational efficiency. To address these challenges, we propose a dynamic weighted multimodal fault diagnosis model based on the fusion of acoustic and vibration information. This model aims to enhance feature fusion, dynamically adapt to signal characteristics, optimize feature selection, and reduce computational complexity. The model incorporates an adaptive fusion method based on a multi-branch convolutional structure, enabling unified processing of both acoustic and vibration signals. At the same time, a cross-modal dynamic weighted fusion mechanism is employed, allowing the real-time adjustment of weight distribution based on signal characteristics. By utilizing an attention mechanism for dynamic feature selection and weighting, the robustness of classification is further improved. Additionally, when processing acoustic signals, a depthwise separable convolutional network is used, effectively reducing computational complexity. Experimental results demonstrate that our method significantly outperforms other algorithms in terms of convergence speed and final performance. Additionally, the accuracy curve during training showed minimal fluctuation, reflecting higher robustness. The model achieved over 99% diagnostic accuracy under all signal-to-noise ratio (SNR) conditions, showcasing exceptional robustness and noise resistance in both noisy and high-SNR environments. Furthermore, its superiority across different data scales, especially in small-sample learning and stability, highlights its strong generalization capability. Full article