Pediatrics

ClimateVID -- Social Media Videos Analysis and Challenges Involved

The pervasive growth of digital content, specifically short videos on social media platforms, has significantly altered how topics are discussed and understood in public discourse. In this work, we advance automated visual theme detection by assessing zero-shot and clustering capabilities on social media data. (1) We evaluated the capabilities of notable VLMs such as VideoChatGPT, PandaGPT, and Vi...

Adolescent Astrocyte Dysregulation Impairs Prefrontal Interneuron Maturation and Adult Cognition

The prefrontal cortex (PFC), a brain region critical for executive and cognitive functions, is characterized by its protracted maturation extending through adolescence until early adulthood. During adolescence, the PFC undergoes substantial rearrangements, creating a window of heightened plasticity allowing experience-dependent refinement of neural networks. While this extended plasticity supports...

Domain-Adapted Small Language Models for Reliable Clinical Triage

Accurate and consistent Emergency Severity Index (ESI) assignment remains a persistent challenge in emergency departments, where highly variable free-...

Detection of bronchopulmonary dysplasia in infants and prediction of school-age lung function from tidal breathing data using recurrent neural networks

Objective: To test whether machine learning (ML) models trained on tidal breathing flow time series can discriminate between individuals with and with...

Exploring Remote Photoplethysmography for Neonatal Pain Detection from Facial Videos

Unaddressed pain in neonates can lead to adverse effects, including delayed development and slower weight gain, emphasising the need for more objectiv...

Pediatric HIV Hotspots in Kenya: Machine Learning and Geostatistical Analysis for Enhanced Case Finding

Background Although Kenya's HIV programme has long prioritized high-burden counties for intensified paediatric interventions, a critical evidence gap ...

Uncovering Latent Patterns in Social Media Usage and Mental Health: A Clustering-Based Approach Using Unsupervised Machine Learning

The widespread adoption of social media has heightened interest in its psychological effects, particularly on mental health indicators such as anxiety...

Generalizing intensive care AI across time scales in resource-limited settings

Temporal resolution of physiological monitoring in intensive care varies widely across healthcare systems. Artificial intelligence models assume a uni...

Attention-based multiple instance learning for predominant growth pattern prediction in lung adenocarcinoma wsi using foundation models

Lung adenocarcinoma (LUAD) grading depends on accurately identifying growth patterns, which are indicators of prognosis and can influence treatment de...

Clinically-Informed Modeling for Pediatric Brain Tumor Classification from Whole-Slide Histopathology Images

Accurate diagnosis of pediatric brain tumors, starting with histopathology, presents unique challenges for deep learning, including severe data scarci...

AI Approach for MRI-only Full-Spine Vertebral Segmentation and 3D Reconstruction in Paediatric Scoliosis

MRI is preferred over CT in paediatric imaging because it avoids ionising radiation, but its use in spine deformity assessment is largely limited by t...

Mass cytometry data integration methods reveal rural-urban gradient of immune profiles across geography

The human immune system strongly varies across populations and is shaped by a wide range of host and environmental factors. As such, a rural compared ...

A Machine Learning Based Causal Interface for Time-Varying Environmental Predictors of Substance Use Initiation in the ABCD Study

Background: The Adolescent Brain Cognitive Development (ABCD) Study provides rich longitudinal data on environmental, genetic, and behavioral factors ...

Evaluating Large Language Models for Transparent Quality-of-Care Measurement in Children with ADHD

ImportanceGuideline-concordant care for young children with attention-deficit/hyperactivity disorder (ADHD) includes recommending parent training in b...

Beyond Independent Frames: Latent Attention Masked Autoencoders for Multi-View Echocardiography

Echocardiography is a widely used modality for cardiac assessment due to its non-invasive and cost-effective nature, but the sparse and heterogeneous ...

Latent neural network representations of the brain reflect broad-scale adolescent phenotypic variation

The adolescent brain is attuned to social and environmental exploration, allowing behavioral adaptation as experiences shape lasting patterns of morph...

Multi-Stain Fusion of Histopathology Images Using Deep Learning for Pediatric Brain Tumor Classification

The classification of pediatric brain tumors is investigated using deep learning on hematoxylin and eosin (H&E) and antigen Ki-67 (Ki-67) whole slide ...

A Scalable High-Density Microwell Assay for Single-Cell Clonal Expansion Profiling

Traditional clonogenic assays remain central to evaluating the self-renewal capacity of tumor cells. However, the assay relies on subjective endpoint ...

No One Left Behind: Adaptive Tablet Modalities for Digitally Excluded Emergency Department Patients Design, Implementation, and Social Evidence for an Impairment-First Interface

Background: The urgent care departments in Europe face a structural paradox: accelerating digitalisation is accompanied by a patient population that i...

Toward Accountable AI-Generated Content on Social Platforms: Steganographic Attribution and Multimodal Harm Detection

The rapid growth of generative AI has introduced new challenges in content moderation and digital forensics. In particular, benign AI-generated images...