COVID-19

Comparing the Use of Measured and Smoothed Data in Forecasting Visual Field Tests Using Deep Learning.

OBJECTIVE: To evaluate the impact of training and testing deep learning (DL) models for visual field (VF) forecasting using input-target pairs in which the target is either the measured VF test result, or its smoothed counterpart constructed via linear regression. DESIGN: A retrospective data analysis study evaluating DL models for VF forecasting under multiple training and testing configurations....

Multi-omics precision diagnosis of brucellosis: Advances in biomarker discovery and clinical application.

Brucellosis, a neglected zoonosis caused by intracellular Brucella bacteria, remains a formidable global public health challenge, especially in developing regions. The notorious ability of Brucella to evade host immunity and establish chronic focal infections limits the utility of traditional diagnostic methods like bacterial culture and serology for early detection, therapeutic monitoring, and di...

Railway carbon emission scenario prediction in four regions of China based on machine learning.

Understanding carbon emissions of the railway transportation industry in China is critical for effective climate action. This study applied machine le...

Transfer learning for Multi-institutional Classification of Intussusception and Splenomegaly in Pediatric Abdominal Radiographs.

To address diagnostic delays in pediatric abdominal emergencies, this study aimed to develop and validate multi-institutional deep learning models for...

Development and Validation of a SHAP-Interpretable Machine Learning Model for Stroke Risk Prediction Using Circulating MicroRNA Biomarkers.

BACKGROUND/OBJECTIVE: Stroke remains a leading cause of morbidity and mortality worldwide. Circulating microRNAs (miRNAs) have emerged as promising no...

Screening of new detection targets and virulence factors in Cronobacter using pan-genome and machine learning.

Cronobacter species are emerging foodborne pathogens, and species identification is essential because the virulence of different species is diverse, w...

Decoding Parkinson's progression: A multi-modal SuStaIn ensemble approach validated on real-world PPMI data.

BACKGROUND: Parkinson's disease (PD) exhibits substantial heterogeneity in clinical presentation and longitudinal progression, complicating prognosis,...

Identifying potential relationships between air pollutants and neutrophil extracellular traps formation in metabolic dysfunction-associated fatty liver disease by integrating computational toxicology and multi-omics data.

Metabolic dysfunction-associated fatty liver disease (MASLD) is a highly prevalent liver condition with a complex etiology increasingly linked to air ...

M-protein interference in laboratory diagnostics: a comprehensive narrative review of mechanisms and management strategies.

Monoclonal proteins (M-proteins) serve as critical biomarkers for plasma cell dyscrasias, yet their unique physicochemical properties paradoxically co...

Combining Machine Learning Models and Screening to Enhance Suicide Risk Identification for American Indian Patients: Retrospective Cohort Study.

BACKGROUND: American Indian and Alaska Native communities experience disproportionately high suicide rates. While machine learning (ML) models leverag...

Noninvasive neurophysiological diagnostics of delayed cerebral ischemia in aneurysmal subarachnoid hemorrhage: a scoping review.

BACKGROUND: Delayed cerebral ischemia (DCI) is a major complication following aneurysmal subarachnoid hemorrhage (aSAH), affecting outcomes. Given its...

The evolving global landscape of first-in-class oncology drug innovation.

First-in-class (FIC) oncology drugs-defined by their novel mechanisms of action or targeting of previously unaddressed molecular targets-have emerged ...

Disentangling the Network Structure of Online Social Support: A Multilayer Network Analysis of a Twitter Long COVID Community.

Online social support has been shown to be an important resource for people experiencing chronic illnesses. Although numerous studies have examined on...

Precision theranostics in oncology: integrating antibody-drug conjugates, radioimmunotherapy, and immuno‑PET for adaptive cancer care.

The century-old vision of a "magic bullet" in oncology is being realized through the paradigm of precision theranostics, which formally integrates tar...

Integrative analysis of single-cell and transcriptomic data with RT-qPCR validation explores TRPM4-associated gene signatures in osteoarthritis synovium.

Osteoarthritis (OA) is a chronic, disabling condition whose pathogenesis remains unclear. TRPM4 is closely associated with OA, but its specific roles ...

Machine learning predictions of IgG1 and IgG4 self-association and high-concentration solution properties.

To meet the widespread demand for subcutaneous delivery of antibody therapeutics, candidates with low viscosity, high solubility, and/or low aggregati...

Artificial intelligence in the assessment of epilepsy-related genetic mutations: Learned from GABAA receptors and GABA transporter 1.

This review examines how recent genetic and technological advances have transformed our understanding and treatment of genetic epilepsies (GEs), with ...

Mapping the Research Landscape and Emerging Trends in Hashimoto's Encephalopathy: A CiteSpace-Based Visualization Analysis.

INTRODUCTION: Hashimoto's thyroiditis is the leading cause of hypothyroidism in iodine-sufficient regions and is often accompanied by various comorbid...

FourierAN-m1A: A Novel Fourier-Domain Adaptive Feature Extraction Framework for m1A RNA Modification Prediction.

RNA modifications play a pivotal role in regulating gene expression. Among them, N1-methyladenosine (m1A), as a crucial post-transcriptional modificat...

An integrated AI-driven vaccine design process: a systematic review of workflows from generative design to translational prediction.

Traditional vaccine development faced significant hurdles, including lengthy timelines and high costs, which hindered rapid responses to pathogens. Al...