AI Medical Compendium

Molecular characterisation of progressive pulmonary sarcoidosis: protocol for a longitudinal multi-centre study to develop peripheral blood circulating biomarkers for predicting pulmonary sarcoidosis progression.

BMJ open Apr 29, 2026

INTRODUCTION: Sarcoidosis is a heterogeneous granulomatous disease with highly variable clinical trajectories, yet no validated biomarkers exist to distinguish progressive sarcoidosis (P-sarcoidosis) from non-progressive disease (NP-sarcoidosis). Thi... read more

Evolution and forecasting of antiretroviral therapy utilisation in British Columbia: a population-level analysis of provincial drug treatment programme data, 2014-2024.

BMJ open Apr 29, 2026

OBJECTIVE: To characterise temporal trends in antiretroviral therapy (ART) utilisation and forecast short-term changes in regimen distribution within a provincial HIV treatment programme. DESIGN: Population-level longitudinal analysis of administrati... read more

MOFSynth-ADV: An Open-Source Engine for Synthesizability Evaluation of Metal-Organic Frameworks.

Journal of chemical information and modeling Apr 29, 2026

We present MOFSynth-ADV, an advanced iteration of the MOFSynth tool designed to evaluate the synthetic feasibility of Metal-Organic Frameworks (MOFs). By integrating the Atomic Simulation Environment (ASE) to leverage extended tight-binding (xTB) and... read more

Artificial intelligence pathways to abortion care: a regional analysis of ChatGPT referrals to Women on Web.

BMJ sexual & reproductive health Apr 29, 2026

Advances in Cell Therapy for Neural Repair.

The Journal of neuroscience : the official journal of the Society for Neuroscience Apr 29, 2026

Neural repair remains one of the foremost challenges in modern neuroscience, as damage to the central nervous system caused by injury or neurodegenerative disease often leads to irreversible loss of function. The advent and rapid evolution of utilizi... read more

Structural and Electronic Features-Integrated Machine Learning Framework for High-Throughput Prediction of Organic Pollutant Reactivity.

Environmental science & technology Apr 29, 2026

Understanding and predicting the reactivity of organic pollutants toward reactive species is crucial for designing efficient and targeted degradation strategies for advanced oxidation processes. However, the structural complexity and chemical diversi... read more

Rethinking Link Prediction for Directed Graphs.

IEEE transactions on pattern analysis and machine intelligence Apr 29, 2026

Link prediction for directed graphs is a crucial task with diverse real-world applications. Recent advances in embedding methods and Graph Neural Networks (GNNs) have shown promising improvements. However, these methods often lack a thorough analysis... read more

From Convergence to Generalization: Stability of Stationary-Point Learning Algorithms.

IEEE transactions on pattern analysis and machine intelligence Apr 29, 2026

Algorithmic stability is a fundamental concept in learning theory for studying the generalization guarantees of learning algorithms. A notable limitation of classical stability analyses is that they often require convexity assumptions to obtain nontr... read more

EEG-VLM: A Hierarchical Vision-Language Model With Multi-Level Feature Alignment and Visually Enhanced Language-Guided Reasoning for EEG Image-Based Sleep Stage Prediction.

IEEE journal of biomedical and health informatics Apr 29, 2026

Sleep stage classification based on electroencephalography (EEG) is fundamental for assessing sleep quality and diagnosing sleep-related disorders. However, most traditional machine learning methods rely heavily on prior knowledge and handcrafted fea... read more

Bias Alleviation through Network Pruning for Sparse and Debiased Models.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society Apr 29, 2026

Pruning is a highly effective method for reducing the size of neural networks with negligible impact on their average performance. However, recent studies have revealed that pruning actually amplifies the bias in the models, leading to decreased perf... read more

Artificial Intelligence Medical Compendium