Search Results (1,621)

Objectives: This study aims to evaluate whether contemporary artificial intelligence (AI), including convolutional neural networks (CNNs) for medical imaging and large language models (LLMs) for language processing, could replace physicians in the near future and to identify the principal clinical, technical, and regulatory barriers. Methods: A narrative review is conducted on the scientific literature addressing AI performance and reproducibility in medical imaging, LLM competence in medical knowledge assessment and patient communication, limitations in out-of-distribution generalization, absence of physical examination and sensory inputs, and current regulatory and legal frameworks, particularly within the European Union. Results: AI systems demonstrate high accuracy and reproducibility in narrowly defined tasks, such as image interpretation, lesion measurement, triage, documentation support, and written communication. These capabilities reduce interobserver variability and support workflow efficiency. However, major obstacles to physician replacement persist, including limited generalization beyond training distributions, inability to perform physical examination or procedural tasks, susceptibility of LLMs to hallucinations and overconfidence, unresolved issues of legal liability at higher levels of autonomy, and the continued requirement for clinician oversight. Conclusions: In the foreseeable future, AI will augment rather than replace physicians. The most realistic trajectory involves automation of well-defined tasks under human supervision, while clinical integration, physical examination, procedural performance, ethical judgment, and accountability remain physician-dependent. Future adoption should prioritize robust clinical validation, uncertainty management, escalation pathways to clinicians, and clear regulatory and legal frameworks. Full article

Tree pollen allergies are influenced by regional atmospheric pollen concentrations and flora distribution. Climate change and urban landscaping have altered airborne pollen profiles in Ukraine, potentially affecting sensitization patterns. We examined 7518 patients (57.63% children) sensitized to at least one of 26 molecular components from 19 tree species using ALEX testing (2020–2022). Atmospheric pollen data from Ukrainian aerobiology stations were integrated with clinical data. Regional sensitization was mapped using the Geographic Information System, and Bayesian network modeling determined hierarchical relationships. Sensitization to Cry j 1 (46.01%), Bet v 1 (41.67%), and Fag s 1 (34.38%) dominated across age groups. High Fagales sensitization correlated with elevated atmospheric Betula, Alnus, and Corylus pollen concentrations, confirming environmental exposure-sensitization relationships. Bayesian modeling identified Bet v 1 as the root allergen (89.43% accuracy) driving cascading sensitization to other Fagales and non-Fagales allergens. Unexpectedly high Cry j 1 sensitization despite minimal atmospheric Cryptomeria presence suggests Thuja and Ambrosia cross-reactivity. Fagales sensitization dominated 10 of 17 regions, correlating with forest geography and urban landscaping. This study validates aerobiological monitoring’s clinical relevance. Diagnostic protocols should prioritize Bet v 1 while interpreting Cry j 1 positivity as potential cross-reactivity. Climate-driven shifts in atmospheric pollen patterns require ongoing coordinated aerobiological and clinical surveillance. Full article

Background/Objectives: Colorectal cancer (CRC) is a major public health challenge in Brazil, characterized by marked regional disparities. Although national legislation mandates that treatment begin within 60 days after diagnosis, compliance remains inconsistent, particularly within the Unified Health System (SUS). This study aimed to analyze the time to treatment initiation for colon (C18) and rectal (C20) cancer in Brazil from 2013 to 2024, assessing regional inequalities, temporal trends, and factors associated with treatment delays. Methods: We conducted an ecological study using secondary data from the Ministry of Health’s PAINEL-Oncologia platform, which integrates information from SIA/SUS, SIH/SUS, and SISCAN. Records of patients diagnosed with colon and rectal cancer (ICD-10 C18–C20) were evaluated. Temporal trends were analyzed using Joinpoint regression, and factors associated with delayed treatment initiation (>60 days) were identified through multiple logistic regression models. Results: Persistent discrepancies were observed between diagnostic and treatment trends from 2013 to 2024, with the Annual Percent Change (APC) for diagnosis exceeding that for treatment, particularly among adults aged 55–69 years. The Southeast and South regions accounted for over 70% of all diagnosed cases, starkly contrasting with the less than 25% in the North and Northeast. More than 50% of patients across all clinical stages initiated treatment after the legally mandated 60-day period. Women with rectal cancer had a 28% higher risk (RR = 1.28) of being diagnosed at stage IV. Chemotherapy was the predominant initial therapeutic modality, while the need for combined chemo-radiotherapy was associated with markedly elevated risk ratios for delay (e.g., RR = 26.53 for stage IV rectal cancer). Treatment initiation delays (>60 days) were significantly associated with residence in the North/Northeast regions, female sex (for rectal cancer), advanced-stage disease, and complex therapeutic regimens. Conclusions: The study demonstrates persistent regional inequalities and highlights a substantial mismatch between diagnostic capacity and therapeutic availability in Brazil. These gaps contribute to treatment delays and reinforce the need to strengthen and expand oncological care networks to ensure equitable access and improve outcomes, particularly in underserved regions. Full article

Intravenous thrombolysis with recombinant tissue-type plasminogen activator (tPA) remains a keystone of acute ischemic stroke treatment but in a subset of patients is complicated by angioedema, a potentially life-threatening adverse event largely mediated by bradykinin signaling. The unpredictable and idiosyncratic nature of this reaction has long suggested an underlying genetic contribution, yet its molecular architecture has remained poorly characterized. We hypothesized that alteplase-associated angioedema represents a multigenic susceptibility phenotype, arising from the convergence of rare genetic variants across multiple interacting physiological systems rather than from a single causal variant. To explore this hypothesis, we performed clinical exome sequencing in a cohort of 11 patients who developed angioedema following alteplase administration. Rather than identifying a shared pathogenic variant, we observed distinct yet convergent patterns of genetic vulnerability, allowing patients to be grouped according to dominant, but overlapping, biological axes. These included alterations affecting bradykinin regulation (e.g., ACE, SERPING1, XPNPEP2), endothelial structure and hemostasis (e.g., VWF, COL4A1), neurovascular and calcium signaling (e.g., SCN10A, RYR1), and vascular repair or remodeling pathways (e.g., PSEN2, BRCA2). Notably, many of the identified variants were classified as Variant of Uncertain Significance (VUS) or likely benign significance in isolation. However, when considered within an integrated, pathway-based framework, these variants can be interpreted as capable of contributing cumulatively to system level fragility, a phenomenon best described as “contextual pathogenicity”. Under the acute biochemical and proteolytic stress imposed by thrombolysis, this reduced physiological reserve may allow otherwise compensated vulnerabilities to become clinically manifest. Together, these findings support a model in which severe alteplase-associated angioedema appears as an emergent property of interacting genetic networks, rather than a monogenic disorder. This systems level perspective underscores the limitations of gene centric interpretation for adverse drug reactions and highlights the potential value of pathway informed, multi-genic approaches to risk stratification. Such frameworks may ultimately contribute to safer, more personalized thrombolytic decision, while providing a conceptual foundation for future functional and translational studies. Full article

Accurate upper-limb motor assessment is critical for post-stroke rehabilitation but relies on subjective clinical scales. This study proposes the Action-Aware Multimodal Wavelet Fusion Network (AMWFNet), integrating surface electromyography (sEMG) and robotic kinematics for automated Fugl-Meyer Assessment (FMA-UE)-aligned quantification. Continuous Wavelet Transform (CWT) converts heterogeneous signals into unified time-frequency scalograms. A learnable modality gating mechanism dynamically weights physiological and kinematic features, while action embeddings encode task contexts across 18 standardized reaching tasks. Validated on 40 participants (20 post-stroke, 20 healthy), AMWFNet achieved 94.68% accuracy in six-class classification, outperforming baselines by 9.17% (Random Forest: 85.51%, SVM: 85.30%, 1D-CNN: 91.21%). The lightweight architecture (1.27M parameters, 922ms inference) enables real-time assessment-training integration in rehabilitation robots, providing an objective, efficient solution. Full article

The rapid advancement of sequencing technologies has led to the generation of complex multi-omics data, which are often high-dimensional, noisy, and imbalanced, posing significant challenges for traditional machine learning methods. The novelty of this work resides in the architecture-level integration of autoencoders with Generative Adversarial Network (GAN) and Conditional Tabular Generative Adversarial Network (CTGAN) models, where the autoencoder is employed for latent feature extraction and noise reduction, while GAN-based models are used for realistic sample generation and class imbalance mitigation in multi-omics cancer datasets. This study proposes a novel framework that combines an autoencoder for dimensionality reduction and a CTGAN for generating synthetic samples to balance underrepresented classes. The process starts with selecting the most discriminative features, then extracting latent representations for each omic type, merging them, and generating new minority samples. Finally, all samples are used to train a neural network to predict specific cancer outcomes, defined here as clinically relevant biomarkers or patient characteristics. In this work, the considered outcome in the bladder cancer is Tumor Mutational Burden (TMB), while the breast cancer outcome is menopausal status, a key factor in treatment planning. Experimental results show that the proposed model achieves high precision, with an average precision of 0.9929 for TMB prediction in bladder cancer and 0.9748 for menopausal status in breast cancer, and reaches perfect precision (1.000) for the positive class in both cases. In addition, the proposed AE–CTGAN framework consistently outperformed an autoencoder combined with a standard GAN across all evaluation metrics, achieving average accuracies of 0.9929 and 0.9748, recall values of 0.9846 and 0.9777, and F1-scores of 0.9922 for bladder and breast cancer datasets, respectively. A comparative fidelity analysis in the latent space further demonstrated the superiority of CTGAN, reducing the average Euclidean distance between real and synthetic samples by approximately 72% for bladder cancer and by up to 84% for breast cancer compared to a standard GAN. These findings confirm that CTGAN generates high-fidelity synthetic samples that preserve the structural characteristics of real multi-omics data, leading to more reliable class balancing and improved predictive performance. Overall, the proposed framework provides an effective and robust solution for handling class imbalance in multi-omics cancer data and enhances the accuracy of clinically relevant outcome prediction. Full article

This study aims to assess hand function recovery in stroke patients during the mid-to-late Brunnstrom stages and to encourage active participation in rehabilitation exercises. To this end, a deep residual network (ResNet) integrated with Focal Loss is employed for gesture recognition, achieving a Macro F1 score of 91.0% and a validation accuracy of 90.9%. Leveraging the millimetre-level precision of Leap Motion 2 hand tracking, a mapping relationship for hand skeletal joint points was established, and a static assessment gesture data set containing 502,401 frames was collected through analysis of the FMA scale. The system implements an immersive augmented reality interaction through the Unity development platform; C# algorithms were designed for real-time motion range quantification. Finally, the paper designs a rehabilitation system framework tailored for home and community environments, including system module workflows, assessment modules, and game logic. Experimental results demonstrate the technical feasibility and high accuracy of the automated system for assessment and rehabilitation training. The system is designed to support stroke patients in home and community settings, with the potential to enhance rehabilitation motivation, interactivity, and self-efficacy. This work presents an integrated research framework encompassing hand modelling and deep learning-based recognition. It offers the possibility of feasible and economical solutions for stroke survivors, laying the foundation for future clinical applications. Full article

Background: Ovarian granulosa cells (GCs) play a pivotal role in folliculogenesis, and their dysfunction is central to disorders such as polycystic ovary syndrome (PCOS) and premature ovarian failure (POF). MicroRNAs (miRNAs) have emerged as crucial post-transcriptional regulators of GC homeostasis. Method: This review synthesizes current evidence by systematically analyzing relevant studies, integrating data from in vitro GC models, animal experiments, human cell lines, and clinical samples to elucidate the specific mechanisms by which miRNAs regulate GCs. Results: miRNAs precisely modulate GC proliferation, apoptosis, steroidogenesis, and oxidative stress responses by targeting key signaling pathways (e.g., PI3K/AKT/mTOR, TGF-β/SMAD) and functional genes (e.g., TP53, CYP19A1). Exosomal miRNAs serve as vital mediators of communication within the follicular microenvironment. To date, nearly 200 miRNAs have been associated with PCOS. Conclusions: miRNAs constitute a decisive regulatory network governing GC fate, offering promising therapeutic targets for PCOS and POF. However, significant challenges remain, primarily miRNA pleiotropy and the lack of follicle-specific delivery systems. Future clinical translation requires rigorous validation in human-relevant models. Full article

Non-AIDS-defining cancers (NADCs) have emerged as an increasingly prominent cause of non-AIDS-related morbidity and mortality among people living with HIV (PLWH). However, the scarcity of NADC clinical samples, compounded by privacy and security constraints, continues to present formidable obstacles to advancing pathological and clinical investigations. In this study, we adopted a joint analysis strategy and deeply integrated and analyzed transcriptomic data from 12,486 PLWH and cancer patients to systematically identify potential key regulators for 23 NADCs. This effort culminated in NADCdb—a database specifically engineered for NADC pathological exploration, structured around three mechanistic frameworks rooted in the interplay of immunosuppression, chronic inflammation, carcinogenic viral infections, and HIV-derived oncogenic pathways. The “rNADC” module performed risk assessment by prioritizing genes with aberrant expression trajectories, deploying bidirectional stepwise regression coupled with logistic modeling to stratify the risks for 21 NADCs. The “dNADC” module, synergized patients’ dysregulated genes with their regulatory networks, using Random Forest (RF) and Conditional Inference Trees (CITs) to identify pathogenic drivers of NADCs, with an accuracy exceeding 75% (in the external validation cohort, the prediction accuracy of the HIV-associated clear cell renal cell carcinoma model exceeded 90%). Meanwhile, “iPredict” identified 1905 key immune biomarkers for 16 NADCs based on the distinct immune statuses of patients. Importantly, we conducted multi-dimensional profiling of these key determinants, including in-depth functional annotations, phenotype correlations, protein–protein interaction (PPI) networks, TF-miRNA-target regulatory networks, and drug prediction, to deeply dissect their mechanistic roles in NADC pathogenesis. In summary, NADCdb serves as a novel, centralized resource that integrates data and provides analytical frameworks, offering fresh perspectives and a valuable platform for the scientific exploration of NADCs. Full article

We introduce the Onco-Hem Connectome (OHC), a patient similarity network (PSN) designed to organize real-world hemato-oncology inpatients by exploratory phenotypes with potential clinical utility. Background: Polypharmacy and drug–drug interactions (DDIs) are pervasive in hemato-oncology and vary with comorbidity and treatment intensity. Methods: We retrospectively analyzed a 2023 single-center cohort of 298 patients (1158 hospital episodes). Standardized feature vectors combined demographics, comorbidity (Charlson, Elixhauser), comorbidity polypharmacy score (CPS), aggregate DDI severity score (ADSS), diagnoses, and drug exposures. Cosine similarity defined edges (threshold ≥ 0.6) to build an undirected PSN; communities were detected with modularity-based clustering and profiled by drugs, diagnosis codes, and canonical chemotherapy regimens. Results: The OHC comprised 295 nodes and 4179 edges (density 0.096, modularity Q = 0.433), yielding five communities. Communities differed in comorbidity burden (Kruskal–Wallis ${\epsilon }^2$: Charlson 0.428, Elixhauser 0.650, age 0.125, all FDR-adjusted p < 0.001) but not in utilization (LOS, episodes) after FDR (${\epsilon }^2$ ≈ 0.006–0.010). Drug enrichment (e.g., enoxaparin $\Delta$ = +0.13 in Community 2; vinblastine $\Delta$ = +0.09 in Community 3) and principal diagnoses (e.g., C90.0 23%, C91.1 15%, C83.3 15% in Community 1) supported distinct clinical phenotypes. Robustness analyses showed block-equalized features preserved communities (ARI 0.946; NMI 0.941). Community drug signatures and regimen signals aligned with diagnosis patterns, reflecting the integration of resource-use variables in the feature design. Conclusions: The Onco-Hem Connectome yields interpretable, phenotype-level insights that can inform supportive care bundles, DDI-aware prescribing, and stewardship, and it provides a foundation for phenotype-specific risk models (e.g., prolonged stay, infection, high-DDI episodes) in hemato-oncology. Full article

Despite widespread adoption, Electronic Medical Record (EMR) systems remain limited in providing intelligent clinical decision support, particularly for early detection of patient deterioration. We present MedROAD V2 (Medical Records Organization, Analysis, and Display), an open-source EMR that integrates AI-driven physiological analysis with comprehensive patient management. The system combines continuous vital sign monitoring and laboratory data using an ensemble of the following four complementary machine learning models: gradient boosting for supervised prediction, isolation forests for anomaly detection, autoencoders for pattern recognition, and Long Short-Term Memory networks for temporal modeling. A novel framework couples these predictions with a large language model (Claude AI) to generate explainable differential diagnoses grounded in medical literature. Validation on the MIMIC-IV database demonstrated excellent 12 h deterioration prediction. MedROAD demonstrates that combining quantitative prediction with natural language explanation can enhance clinical decision support while extending quality care to populations that would otherwise lack access. Full article

Wee1-like protein kinase 2 (WEE2) is an oocyte-specific kinase that regulates meiotic arrest and fertilization. Its largely restricted expression in female germ cells and absence in somatic tissues make it a highly selective target for reproductive health interventions. Despite its central role in human fertility, no clinically approved WEE2 modulator is available. In this study, we employed an integrated in silico approach that combines structure-based virtual screening, molecular dynamics (MD) simulations, and MM-PBSA free-energy calculations to identify repurposed drug candidates with potential WEE2 inhibitory activity. Screening of ~3800 DrugBank compounds against the WEE2 catalytic domain yielded ten high-affinity hits, from which Midostaurin and Nilotinib emerged as the most mechanistically relevant based on kinase-targeting properties and pharmacological profiles. Docking analyses revealed strong binding affinities (−11.5 and −11.3 kcal/mol) and interaction fingerprints highly similar to the reference inhibitor MK1775, including key contacts with hinge-region residues Val220, Tyr291, and Cys292. All-atom MD simulations for 300 ns demonstrated that both compounds induce stable protein–ligand complexes with minimal conformational drift, decreased residual flexibility, preserved compactness, and stable intramolecular hydrogen-bond networks. Principal component and free-energy landscape analyses further indicate restricted conformational sampling of WEE2 upon ligand binding, supporting ligand-induced stabilization of the catalytic domain. MM-PBSA calculations confirmed favorable binding free energies for Midostaurin (−18.78 ± 2.23 kJ/mol) and Nilotinib (−17.47 ± 2.95 kJ/mol), exceeding that of MK1775. To increase the translational prioritization of candidate hits, we place our structure-based pipeline in the context of modern machine learning (ML) and deep learning (DL)-enabled virtual screening workflows. ML/DL rescoring and graph-based molecular property predictors can rapidly re-rank docking hits and estimate absorption, distribution, metabolism, excretion, and toxicity (ADMET) liabilities before in vitro evaluation. Full article

Background and Objectives: Epilepsy is a chronic neurological disorder characterized by recurrent seizures caused by abnormal brain activity. Reliable near-real-time seizure detection is essential for preventing injuries, enabling early interventions, and improving the quality of life for patients with drug-resistant epilepsy. This study presents a near-real-time epileptic seizure detection framework designed for low-latency operation, focusing on improving both clinical reliability and patient comfort through electrode reduction. Method: The framework integrates bidirectional long short-term memory (BiLSTM) networks with wavelet-based feature extraction using Electroencephalogram (EEG) recordings from the EPILEPSIAE dataset. EEG signals from 161 patients comprising 1032 seizures were analyzed. Wavelet features were combined with raw EEG data to enhance temporal and spectral representation. Furthermore, electrode reduction experiments were conducted to determine the minimum number of strategically positioned electrodes required to maintain performance. Results: The optimized BiLSTM model achieved 86.9% accuracy, 86.1% recall, and an average detection delay of 1.05 s, with a total processing time of 0.065 s per 0.5 s EEG window. Results demonstrated that reliable detection is achievable with as few as six electrodes, maintaining comparable performance to the full configuration. Conclusions: These findings demonstrate that the proposed BiLSTM-wavelet approach provides a clinically viable, computationally efficient, and wearable-friendly solution for near-real-time epileptic seizure detection using reduced EEG channels. Full article

Accurate, subject-specific estimation of cervical muscle forces is a critical prerequisite for advancing spinal biomechanics and clinical diagnostics. However, this task remains challenging due to substantial inter-individual anatomical variability and the invasiveness of direct measurement techniques. In this study, we propose a novel data-driven biomechanical framework that addresses these limitations by integrating massive-scale personalized musculoskeletal simulations with an efficient Feedforward Neural Network (FNN) model. We generated an unprecedented dataset comprising one million personalized OpenSim cervical models, systematically varying key anthropometric parameters (neck length, shoulder width, head mass) to robustly capture human morphological diversity. A random subset was selected for inverse dynamics simulations to establish a comprehensive, physics-based training dataset. Subsequently, an FNN was trained to learn a robust, nonlinear mapping from non-invasive kinematic and anthropometric inputs to the forces of 72 cervical muscles. The model’s accuracy was validated on a test set, achieving a coefficient of determination (R²) exceeding 0.95 for all 72 muscle forces. This approach effectively transforms a computationally intensive biomechanical problem into a rapid tool. Additionally, the framework incorporates a functional assessment module that evaluates motion deficits by comparing observed head trajectories against a simulated idealized motion envelope. Validation using data from a healthy subject and a patient with restricted mobility demonstrated the framework’s ability to accurately track muscle force trends and precisely identify regions of functional limitations. This methodology offers a scalable and clinically translatable solution for personalized cervical muscle evaluation, supporting targeted rehabilitation and injury risk assessment based on readily obtainable sensor data. Full article

Artificial intelligence (AI) has revolutionized medical image analysis. Several neural network (NN) architectures were developed and applied across the last decade, becoming essential for automated diagnosis and clinical applications. AI based on NNs has become increasingly integrated into gastroenterology, offering new opportunities for automated lesion detection and workflow optimization. Small-bowel capsule endoscopy (SBCE) has benefited substantially from these advances, addressing long-standing challenges such as time-consuming video review and variability among readers. This systematic review and meta-analysis evaluated neural network-based models for lesion detection in SBCE, assessing pooled diagnostic accuracy and the impact of AI on reading time. A total of 44 primary studies were included: 36 validation studies for accuracy and 9 clinical studies for reading time. All NN architectures demonstrated high diagnostic performance, with a pooled accuracy of 95.3% (95% CI: 94.1–96.5%). More recent architectures, including transformer-based and capsule networks, outperformed classical convolutional neural networks (CNNs). AI assistance significantly reduced SBCE reading time, with a pooled mean reduction of 84% compared to standard review. These findings highlight the strong potential of AI to enhance SBCE efficiency and diagnostic reliability. Full article