搜索结果：Diagnostic

Rare diseases collectively affect hundreds of millions of individuals worldwide, yet the majority remain underdiagnosed, undercharacterized, and underrepresented in biomedical research. Although individually rare, these conditions impose a significant global health burden, often associated with prolonged diagnostic delays, fragmented care pathways, and limited therapeutic options. Advances in genomic technologies have transformed the understanding of many rare diseases by enabling identification of disease-causing variants and molecular pathways that can be targeted therapeutically. However, these advances have not been distributed equitably across global populations. In many regions, particularly low- and middle-income countries (LMICs), limited access to genomic diagnostics and research infrastructure continues to impede accurate diagnosis and participation in therapeutic discovery. Biobanking represents a critical but underutilized component of the rare disease research ecosystem. Biobanks provide foundational infrastructure for translational research, biomarker discovery and clinical trial development by systematically collecting and preserving biospecimens linked to clinical and phenotypic data. When aligned with international standards and integrated with interoperable data systems, biobanks enable large-scale collaborative research even for extremely rare conditions. This opinion article argues that biobanking should be recognized as core infrastructure within rare disease strategies rather than as a secondary research activity. Using PIK3CA-Related Overgrowth Spectrum (PROS) disorders as an illustrative example, we examine how integrating biospecimen repositories with clinical and genomic data can improve diagnostic accuracy, facilitate genotype:phenotype correlations, and accelerate development of pathway-targeted therapies. We further discuss how establishing locally anchored but globally interoperable biobanks may help address persistent inequities in rare disease research by ensuring that diverse populations contribute to and benefit from advances in precision medicine. The importance of representative biobanking and inclusive rare disease datasets is particularly acute when considering how clinical presentations vary across populations. Individuals with darker skin tones frequently present with dermatologic and vascular manifestations of PROS disorders in ways that may differ from presentations documented in existing clinical atlases and training datasets. Such differences can contribute to delayed recognition, misclassification, and prolonged diagnostic odysseys. Racial and ethnically underrepresented populations with rare diseases thus face compounded disadvantages: limited genomic characterization within reference datasets, underrepresentation in biospecimen repositories, and reduced access to diagnostic tools calibrated primarily on non-diverse cohorts. Ensuring that diverse populations are systematically represented in biospecimen collections, imaging datasets, genomic repositories, and longitudinal clinical annotation is therefore not simply an equity consideration but a scientific and clinical necessity for improving diagnostic accuracy and therapeutic development across all populations.

In vivo confocal microscopy (IVCM) is a critical ophthalmic examination that provides in vivo cytological and neurological information essential for diagnosing corneal and certain systemic diseases, but its clinical utility is limited by time-consuming interpretation and the need for subspecialty expertise. We developed IVCM-Insight, an artificial intelligence (AI) system integrating image-text contrastive learning with large language models (LLMs) for automated report generation and interactive question answering (QA). Based on 30,368 IVCM images and 4155 paired clinical reports, the model was trained with contrastive alignment, image-conditioned language modeling, and multi-image consistency loss to produce structured diagnostic reports while a domain-adapted LLM supported patient-centered QA. Automated evaluation showed strong agreement with the reference reports: Bilingual Evaluation Understudy (BLEU)-1 to BLEU-4 scores were 0.69, 0.58, 0.47, and 0.41, Recall-Oriented Understudy for Gisting Evaluation (ROUGE-L) was 0.67, Consensus-based Image Description Evaluation (CIDEr) was 1.85, and Metric for Evaluation of Translation with Explicit Ordering (METEOR) was 0.66. In addition, the multi-label classification achieved an accuracy of 0.96 and an F1 score of 0.80. Manual assessment by corneal specialists rated report accuracy (4.17), completeness (4.19), coherence (4.70), and diagnostic support (4.06), with excellent inter-rater reliability; QA outputs achieved high accuracy (4.33), relevance (4.54), and non-harmfulness (4.81). Representative cases, including cytomegalovirus, fungal, and Acanthamoeba keratitis, demonstrated accurate detection of key findings and clinically safe explanations. To our knowledge, IVCM-Insight is the first dedicated AI system for comprehensive IVCM interpretation, with potential to enhance diagnostic efficiency, strengthen physician-patient communication, and broaden access to advanced corneal imaging across care settings.

Multimorbidity contributes to complexity in seniors, but the impact of co-occurring physical and psychiatric illnesses on emergency department (ED) visits has received little attention. We investigated relationships between trans-diagnostic psychiatric severity, physical multimorbidity, and their interaction with non-psychiatric ED use; and tested the association of continuity of primary care on these relationships. A retrospective cohort design (n = 2,560,986) measured exposures to physical multimorbidity, psychiatric severity, and continuity in primary care. The main outcome was number of medical ED visits. At each level of physical multimorbidity, non-psychiatric ED visits increased with psychiatric severity. There were direct effects of physical multimorbidity (OR 1.35, 95%CI 1.35 - 1.35), psychiatric severity (OR 1.52, 95%CI 1.49 - 1.54), and continuity of care (low vs high OR 1.26, 95%CI 1.24 - 1.28) on frequent non-psychiatric ED use. Continuity of care did not mediate the relationships of physical multimorbidity, psychiatric severity or their interaction on frequent non-medical ED use. Transdiagnostic psychiatric severity correlates with seniors using the ED for non-psychiatric reasons, especially for repeated visits, in addition to the expected contribution of physical multimorbidity. Continuity of primary care does not mediate this relationship. Understanding the contribution of regular primary care requires further investigation.

Precise cancer lesion analysis in medical imaging critically depends on the accurate definition of regions of interest (ROIs), which directly influence diagnostic and clinical outcomes. While peritumoral features are known to enhance lesion characterization, efficiently defining meaningful peritumoral ROIs remains a challenge. We propose an adaptive peritumoral area selection approach (APASA) that systematically identifies the most informative ROI surrounding a lesion, enabling the extraction of meaningful radiomic features for improved diagnostic performance. Unlike conventional heuristic or morphology-based methods, APASA leverages the minimum coverage graph algorithm, using the tumor ROI as a reference to construct a graph encompassing both the tumor and its peritumoral microenvironment. The effectiveness of the proposed approach was evaluated within AI-based frameworks for automated lesion differentiation in breast and thyroid cancers. Extensive experiments employing five widely used machine learning models demonstrated that APASA-selected peritumoral features consistently outperformed conventional morphological dilation. Performance improvements reached up to 30.75% in AUC and 29.00% in F1-score compared with the tumor ROI baseline. Moreover, the optimal model was found to vary depending on the ROI type, shape, and cancer type, offering new insights into the interaction between ROI selection and model choice. These results highlight APASA as a principled and efficient strategy for adaptive ROI definition in ultrasound-based cancer lesion analysis, demonstrating effectiveness across two ultrasound datasets, with potential extension to other imaging modalities and clinical settings pending further validation.

The increasing use of digital communication platforms has led individuals to express emotions and mental health concerns through text containing implicit emotional cues, informal language, and non-standard expressions. Traditional sentiment analysis systems often struggle to capture these contextual nuances, limiting their effectiveness in mental health-related text analysis . To address this challenge, this study proposes a two-layer framework that combines Azure Sentiment Analysis and Azure Custom Text Classification for sentiment and mental health-related text categorization. In the first layer, user-generated text is classified into positive, neutral, or negative sentiment categories using Azure Sentiment Analysis. Text identified as negative is subsequently analysed using Azure Custom Text Classification to categorize content into predefined mental health-related classes, including Anxiety, Depression, PTSD, Social Anxiety Disorder, and Suicidal Ideation and Behaviour. The proposed framework aims to provide a structured approach for identifying linguistic patterns associated with mental health-related discussions and supporting mental health screening and triage applications. Experimental evaluation using an 80% training and 20% testing split achieved an overall Precision, Recall, and F1-score of 96.97%. Class-level evaluation demonstrated strong performance across multiple categories, with F1-scores ranging from 0.94 to 1.000. The findings indicate that the proposed architecture can effectively classify mental health-related textual content within the evaluated dataset while providing a scalable framework for automated sentiment and text classification. The study contributes to the growing field of intelligent emotional computing and highlights the potential of cloud-based natural language processing tools for mental health-related text analytics . The reported results are limited to the evaluated dataset and should be interpreted as a text classification and screening approach rather than a clinical diagnostic system. This manuscript presents the computational component of a broader mixed-methods study registered under CTRI/2024/06/068766, titled "Exploring Mental Health Status in a Selected Population: A Corpus Analysis Combining Forensic Linguistics and Psychology - a Mixed Method Study." The current work focuses on the development and validation of an AI-based diagnostic tool for mental health assessment using synthetic and anonymized textual data, constituting a secondary objective of the registered protocol. Registry: Clinical Trials Registry- India (CTRI) Trial Registration Number: CTRI/2024/06/068766 Date of Registration: 12.06.2024.

Scabies, a common parasitic skin disease caused by Sarcoptes scabiei var. hominis, presents diagnostic challenges because of its diverse clinical manifestations and the limited sensitivity of traditional methods, such as skin scraping. Here, we developed a loop-mediated isothermal amplification (LAMP) assay targeting two S. scabiei-specific genes, Sarcoptes scabiei allergen Sar s 3 (Sars3) and Internal Transcribed Spacer 2 (ITS2). To enhance operational simplicity, a direct lysis protocol was employed, enabling rapid template DNA acquisition from skin scraping specimens without conventional DNA extraction. Primer sets were optimized for amplification speed and specificity; reaction temperatures were determined to be 67 °C for Sars3 and 61 °C for ITS2. The assay achieved detection within 35 min, with limits of detection of 103 copies for Sars3 and 102 copies for ITS2. No false-positive signals were observed across the 144 negative control reactions for each target. The assay demonstrated high specificity for non-target DNA from humans and house dust mites. Clinical validation using skin scrapings from patients with classic and crusted scabies yielded consistently positive results, whereas samples from non-scabies controls yielded negative results. These findings indicate that the developed LAMP assay provides a diagnostic platform for scabies, requiring minimal and portable equipment, making it suitable for clinical or point-of-care settings.

In engineering practice, intelligent fault diagnosis for high-end equipment often involves small-sample, multi-class imbalanced data with noise and complex intra- and inter-class distributions. Existing sampling methods may generate low-quality samples, amplify noise, and depend heavily on hyperparameters. To address these issues, this paper proposes an interpretable fault diagnosis framework, termed Adapted Oversampling-based Multi-layer Support Vector Machines (AM-SVMs). The framework embeds a Multi-mechanism Adaptive Oversampling Technique (MAOTE) into a multi-layer LSSVM architecture. MAOTE adaptively determines sampling strategies according to data characteristics and employs a Newton-Raphson-inspired evolutionary mechanism to search for high-quality candidate solutions guided by multi-class classification performance. The optimized solutions are reorganized into diverse and representative fault samples, and a classifier-feedback-based evaluation mechanism improves distributional consistency and interpretability between generated and real samples. Finally, balanced feature samples are used to train a multi-class LSSVM classifier, yielding a robust and generalizable diagnostic model. Experiments on public bearing datasets and self-collected data show that AM-SVMs outperforms ten data augmentation methods and eight multi-class classifiers in diagnostic accuracy and robustness, demonstrating its effectiveness for imbalanced fault diagnosis in intelligent manufacturing.

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) and arboviruses represent major global public health threats, each with distinct epidemiological and pathogenic profiles that often overlap in endemic regions. Reports of co-infection and cross-reactivity between these viruses highlight the need for deeper understanding of their interactions. Co-infections pose diagnostic challenges due to overlapping clinical symptoms and immune modulation, which may exacerbate disease severity. Moreover, antibodies generated from prior virus infections may influence the outcome of subsequent infections through mechanisms such as cross-reactivity and antibody-dependent enhancement (ADE). This review summarises current knowledge on the clinical manifestations and immunological consequences of co- and subsequent infections involving SARS-CoV-2 and arboviruses. Emphasis is placed on underlying pathophysiological mechanisms, including cross-reactivity and ADE, that shape host immune responses. Understanding these interactions is essential for improving diagnostic accuracy and guiding public health strategies to mitigate the risks associated with co-infections and sequential viral infections.

Discrete dynamical models underpin systems biology, but we still lack substrate-agnostic diagnostics for identifying finite-horizon dynamical signatures that may be relevant to open-ended evolution (OEE), such as the recurrent production of novel phenotypic states rather than rapid settling or unstructured noise. We introduce a simple, model-independent metric, Ω, that summarizes the residence-time-weighted contribution of attractor cycle lengths across the sequence of recurrent episodes realized within a finite observation window. Ω is zero for single-attractor dynamics and also vanishes for pure novelty without recurrence, while increasing when trajectories repeatedly enter multiple persistent cyclic phenotypes. Using Random Boolean Networks (RBNs) as a controlled testbed, we compare classical Boolean dynamics with biologically motivated non-classical mechanisms (probabilistic context switching, annealed rule mutation, paraconsistent logic, modal necessary/possible gating, and quantum-inspired superposition/paired-state coupling) under homogeneous and heterogeneous updating schemes. Our results support the view that undecidability-adjacent, state-dependent mechanisms-implemented as probabilistic context switching, modal necessity/possibility gating, paraconsistent logic, or quantum-inspired correlated branching-are enabling conditions for sustained novelty. At the end of our manuscript we outline a practical extension of Ω to continuous/hybrid state spaces, positioning Ω as a portable proxy for OEE in biological modeling and a guide for engineering evolvable synthetic circuits.

The gut microbiota acts as a critical driver influencing the pathogenesis, therapeutic response, and clinical outcomes across various cancer types. This study aimed to investigate the prognostic value of human gut microbes and microbial metabolites related genes (HGMMMRGs) in head and neck squamous cell carcinoma (HNSCC). We constructed a prognostic risk model comprising 19 core HGMMMRGs using LASSO penalized regression and a multivariate Cox proportional hazards model. The predictive performance of the model was evaluated through Kaplan-Meier analysis, receiver operating characteristic (ROC) curves, nomograms, and concordance index. In addition, functional enrichment analysis was performed on the differentially expressed risk genes. Furthermore, the relationship between the immune microenvironment of HNSCC and the risk diagnostic model was examined. Western blot analysis was used to assess the expression levels of IL10 in both HNSCC tissues and adjacent normal tissues. Finally, the correlation between IL10 and the gut microbiota was explored. This study developed a risk score model integrating 19 HGMMMRG genes, which can serve as a tool to guide prognosis and immune microenvironment assessment in HNSCC patients. Survival analysis showed that patients in the high-risk group had significantly worse outcomes (P&#x2009;<&#x2009;0.05). Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) analysis revealed significant enrichment of differentially expressed genes (DRLs) and immune-related pathways. Western blot analysis further confirmed that IL10 was highly expressed in HNSCC, and the abundance of Faecalibacterium prausnitzii and Enterococcus durans colonies was correlated with IL10 expression. We developed a prognostic model for HGMMMRGs that can be effectively used to predict OS in patients with HNSCC. Second, Faecalibacterium prausnitzii and Enterococcus durans can influence the prognosis of patients with HNSCC by mediating the expression IL10 and thereby affecting the prognosis of HNSCC patients. Thus, human gut microbes and microbial metabolite-related genes may be another promising strategy for the treatment of patients with HNSCC.

Automated electrocardiogram (ECG) arrhythmia classification remains challenging due to morphological complexity, severe class imbalance, and poor model generalization across heterogeneous datasets acquired under varying clinical conditions. To address these challenges, this paper proposes CaReS-BiNet, a Convolutional and Residual Squeeze-and-Excitation Bidirectional-LSTM Network that integrates parallel multi-scale one-dimensional convolutional branches, residual connections, lightweight Squeeze-and-Excitation channel attention, and bidirectional LSTM temporal modelling into a unified end-to-end framework. This design enables joint learning of local morphological features and long-range temporal dependencies directly from ECG heartbeat segments, with Gaussian noise injection employed to improve robustness to class imbalance and signal variability. Evaluated on the MIT-BIH Arrhythmia Database under the AAMI EC57 five-class protocol, CaReS-BiNet achieves an accuracy of 98.74%, precision of 98.70%, recall of 98.73%, and F1-score of 98.71%, outperforming the majority of compared state-of-the-art methods on recall and F1-score. Independent evaluation on the PTB Diagnostic ECG Database yields 99.31% accuracy, 99.27% precision, 99.16% F1-score, and an AUC of 0.999, demonstrating superior performance across all reported metrics against a recently proposed hybrid architecture evaluated on the same dataset. This robustness is further supported by consistent performance on an additional heterogeneous ECG dataset, achieving 98.08% accuracy. Binary ventricular ectopic beat (VEB) and supraventricular ectopic beat (SVEB) detection further confirms clinical reliability, with SVEB precision of 97.99% substantially exceeding existing methods. A systematic ablation study validates the individual contribution of each architectural component across both datasets. These results establish CaReS-BiNet as an effective framework for automated arrhythmia classification across diverse ECG datasets.

The clinical and biological heterogeneity of major depressive disorder (MDD) may reflect the aggregation of different conditions with distinct pathologies under a single diagnostic label. Neuroanatomical heterogeneity in MDD was examined using a harmonized, age- and sex-matched sample from the ENIGMA MDD consortium (N&#x2009;=&#x2009;5146; age range: 9-82 years; 64% female). Analyses of global neurostrucutral variability revealed greater cortical thickness heterogeneity in MDD compared with healthy controls (Cohen's d = -0.26). Regionally, increased variability in cortical thickness was most prominent in the cingulate (+6.1 to +6.6% more variation in MDD) and insular (+5.8%) cortices, as well as in the frontal (+5.7 to +6.8%) and temporal (+6.1 to +6.8%) lobes. Heterogeneity in cortical thickness was more pronounced among patients using antidepressant medication (Cohen's d = -0.39). Patient-specific analyses further showed that individuals with markedly increased cortical thickness variability (<5th percentile relative to the normative range) exhibited greater depressive symptom severity than those within the normative range (5th-95th percentile; Cohen's d&#x2009;=&#x2009;0.19-0.36). Overall, the results indicate that neuroanatomical heterogeneity in MDD is primarily expressed in cortical thickness, offering refined insights into the neurobiological complexity of structural alterations associated with depression. These findings could guide future stratification efforts examining whether regionally confined changes in cortical thickness within areas of pronounced variability reflect clinically meaningful patient subgroups.

Prostate cancer (PCa) is common world-wide. Current diagnostics based on testing for circulating levels of prostate specific antigen (PSA) is unspecific, and novel prognostic markers are needed for personalized therapeutic strategies. Pro-neuropeptide Y (pro-NPY) has been reported as a tissue marker for PCa related to poor prognosis. This study explored the prognostic value of circulating pro-NPY in PCa. Plasma samples were obtained from two patient cohorts: (1) men examined due to increased PSA levels in 2003-2011 (n&#x2009;=&#x2009;796) and (2) patients treated for PCa in 2013-2016 (n&#x2009;=&#x2009;92). Cohort 2 also provided plasma samples collected&#x2009;~&#x2009;3&#xa0;months after therapy. For plasma pro-NPY assessment, a sandwich immunoassay was developed. In cohort 1, 315 patients were diagnosed with PCa at the time for blood sampling, 137 were diagnosed during follow-up, and 344 remained disease-free. Plasma pro-NPY provided independent prognostic information from PSA regarding time to metastasis and PCa death. In cohort 2, high plasma pro-NPY levels were confirmed associated with metastatic disease and poor survival. Plasma pro-NPY levels were normalized after androgen-deprivation therapy, suggesting androgen-regulation. In conclusion, high circulating pro-NPY levels are associated with metastasis and poor outcome in PCa. Prospective validation is needed before suggesting pro-NPY for clinical use. The underlying biology and consequences of pro-NPY overexpression remain to be understood.

Infertility represents a growing global health challenge, intensifying the demand for advanced assisted reproductive technology (ART). Artificial intelligence (AI) is emerging as a transformative force in reproductive medicine, offering novel solutions to augment clinical success and optimize patient-centered care. This review comprehensively synthesizes AI advancements across the continuum of ART, including sperm and oocyte evaluation, embryo selection, pregnancy prediction, fertility assessment, and supportive nursing. Through the integration of multimodal data, extraction of discriminative features, and construction of predictive models, AI introduces unprecedented objectivity and precision into gamete and embryo analysis, thereby facilitating personalized treatment strategies. Furthermore, intelligent consultation and management systems powered by large language models are redefining reproductive healthcare delivery by enhancing clinician-patient communication and improving engagement. While challenges pertaining to data privacy and model generalizability remain, the deep integration of AI with reproductive medicine is an irreversible trend poised to overcome existing ART bottlenecks and forge a more efficient, humane diagnostic and therapeutic ecosystem.

Structural heterogeneity strongly influences forest ecological function, yet zone-specific spectral diagnostics remain limited. This study integrated Sentinel-2 imagery (2016, 2020, 2024) with field-observed ecological attributes across Foreground Area Density (FAD)-based structural zones in the Tuchola Forest Biosphere Reserve, Poland. The aim was to evaluate whether open Sentinel-2 vegetation indices can capture ecological variation across structurally distinct forest zones using interpretable machine-learning models. Correlation and cluster analyses of 17 vegetation indices revealed substantial multicollinearity, supporting the selection of a reduced set of spectrally distinct indices for modelling. Extra Trees (ET) and LightGBM (LGBM) produced comparable predictive performance, although ET achieved equal or lower RMSE values in most zone&#x2009;&#xd7;&#x2009;year combinations and was retained for interpretation. Test-set RMSE remained below one degradation class (0.70-0.96), 2.04 moisture units, 2.35 site-type categories, and 34.4&#xa0;years for stand age. Permutation importance and partial dependence analyses revealed clear zone-specific spectral-ecological relationships. Rare zones exhibited stronger stress-related spectral responses and greater variability in moisture and stand-age-related patterns, whereas Core zones displayed more stable response surfaces across years. NDRE emerged as the most consistent predictor across ecological attributes, while MCARI, NDMI, and CVI provided complementary information depending on the response variable. By combining FAD-based structural stratification, cluster-driven multicollinearity reduction, and interpretable ensemble learning, this framework provides a reproducible approach for linking spectral traits to ecological gradients across fragmentation contexts and supports open-data monitoring of fragmented forest landscapes.