AI Medical Compendium

MedSpectralNet: A lightweight convolutional neural network architecture for multi-modal image classification.

PloS one Apr 27, 2026

Medical image classification requires models that effectively capture both fine-grained local patterns and global anatomical structures while maintaining computational efficiency for clinical deployment. Although state-of-the-art models such as MedMa... read more

Designing a children's health exposomics study protocol: The CHILDREN_FIRST multi-country prospective cohort using multi-omics and personalized prevention approaches.

PloS one Apr 27, 2026

Non-communicable diseases (NCDs) account for ~71% of all deaths globally, including 15 million premature deaths each year (deaths between 30-69 years of age). Instead of waiting until disease manifestation, focusing on the origins of NCDs during chil... read more

Automated Eosinophil Quantification Using Deep Learning to Predict Therapy Escalation in Pediatric Ulcerative Colitis.

Clinical and translational gastroenterology Apr 27, 2026

BACKGROUND: Emerging evidence implicates eosinophils as important modulators of disease activity and therapeutic response in ulcerative colitis. Automated image analysis provides a scalable and reproducible approach to their evaluation, overcoming th... read more

Integration of Continuous Glucose Monitoring With HbA1c to Improve the Detection of Prediabetes in Asian Individuals: Model Development Study.

JMIR diabetes Apr 27, 2026

BACKGROUND: Glycated hemoglobin (HbA1c) is a convenient tool to evaluate glycemic status but its ability to detect individuals at risk for type 2 diabetes is limited. OBJECTIVE: Exploiting the glycemic variability captured in continuous glucose monit... read more

Unsupervised Semantic Segmentation Models for Region of Interest Identification.

Journal of the American Society for Mass Spectrometry Apr 27, 2026

Spatial omics technologies, such as mass spectrometry imaging (MSI), can capture biomolecular distributions and their spatial locations directly from a tissue, but these distributions are not easily associated with tissue morphology without additiona... read more

Integrating AI Into Governmental Public Health Decision Making: Challenges, Considerations, and a Path Forward.

JMIR public health and surveillance Apr 27, 2026

Public health emergencies such as pandemics, natural disasters, and epidemics may require rapid, high-stakes decisions often made by elected officials with limited public health training. Artificial intelligence (AI) holds significant promise to enha... read more

Increased Pre-Activation and Co-Contraction in ACL-Reconstructed Athletes: Insights from AI-based EMG Analysis.

Medicine and science in sports and exercise Apr 27, 2026

INTRODUCTION: Anterior Cruciate Ligament (ACL) tears disrupt the neural structures within the ligament, impairing the neuromuscular control of knee-stabilizing muscles. Consequently, muscle activity patterns are a crucial area of research in return-t... read more

Comparing Perceptions of ChatGPT Use in Health Attitude Contexts Among Users and Nonusers: Cross-Sectional Study.

JMIR formative research Apr 27, 2026

BACKGROUND: In light of the growing use of artificial intelligence (AI) in health care, individuals' access to and use of health information are transforming. ChatGPT, an AI chatbot, provides immediate responses to health queries, with the potential ... read more

AI in Point-of-Care Imaging for Clinical Decision Support: Systematic Review of Diagnostic Accuracy, Task-Shifting, and Explainability.

JMIR AI Apr 27, 2026

BACKGROUND: Artificial intelligence (AI) integrated with point-of-care imaging is a promising approach to expand access in settings with limited specialist availability. However, no systematic review has comprehensively evaluated AI-assisted clinical... read more

Accurate and scalable deep Maxwell solvers.

Proceedings of the National Academy of Sciences of the United States of America Apr 27, 2026

Neural networks have promise as surrogate partial differential equation (PDE) solvers, but it remains a challenge to use these concepts to solve problems with high accuracy and scalability. In this work, we show that neural network surrogates can com... read more

Artificial Intelligence Medical Compendium