AI Medical Compendium

Circuit explained: How does a transformer perform compositional generalization.

PloS one Feb 4, 2026

Compositional generalization-the systematic combination of known components into novel structures-is fundamental to flexible human cognition, yet the mechanisms that enable it in neural networks remain poorly understood in both machine learning and c... read more

Construction of a depression risk prediction model for hepatitis B patients based on machine learning strategy.

PloS one Feb 4, 2026

BACKGROUND: Hepatitis B (HBV) is a chronic viral infection that can lead to cirrhosis, liver failure, and liver cancer, and has a profound impact on the patient's mental health. However, current depression screening mainly relies on self-filled scale... read more

Perception of AI Symptom Models in Oncology Nursing: Mixed Methods Evaluation Study.

JMIR nursing Feb 4, 2026

BACKGROUND: Patients undergoing cancer treatment experience a significant symptom burden. The standard process of symptom management includes patient reporting and clinical response following symptom escalation. Emerging predictive symptom models use... read more

Prediction of First and Multiple Antiretroviral Therapy Interruptions in People Living With HIV: Comparative Survival Analysis Using Cox and Explainable Machine Learning Models.

JMIR medical informatics Feb 4, 2026

BACKGROUND: The Cox proportional hazards (CPH) model is a common choice for analyzing time-to-treatment interruptions in patients on antiretroviral therapy (ART), valued for its straightforward interpretability and flexibility in handling time-depend... read more

Targeted Extracellular Vesicles Deliver Asiaticoside to Inhibit AURKB/DRP1-Mediated Mitochondrial Fission and Attenuate Hypertrophic Scar Formation.

Advanced science (Weinheim, Baden-Wurttemberg, Germany) Feb 4, 2026

Hypertrophic scars (HS) are fibroproliferative lesions arising from aberrant wound healing, their high incidence is countered by a lack of effective interventions owing to an incomplete understanding of pathogenesis. Here, we identify dysregulated mi... read more

Cation-Driven Valence Change Mechanism in 2D AgCrS2 for Ultralow-Power and Reliable Memristors.

Advanced science (Weinheim, Baden-Wurttemberg, Germany) Feb 4, 2026

Memristive devices are promising building blocks for next-generation memory and neuromorphic circuits in artificial intelligence. Among them, filamentary memristors offer great potential for high-performance and densely integrated systems. However, a... read more

Digital Phenotyping for Adolescent Mental Health: Feasibility Study Using Machine Learning to Predict Mental Health Risk From Active and Passive Smartphone Data.

Journal of medical Internet research Feb 4, 2026

BACKGROUND: Adolescents are particularly vulnerable to mental disorders, with over 75% of lifetime cases emerging before the age of 25 years. Yet most young people with significant symptoms do not seek support. Digital phenotyping, leveraging active ... read more

Rapid, label-free cancer detection in fresh pancreatic tissue using deep learning and multispectral Mueller matrix polarimetry.

IEEE transactions on bio-medical engineering Feb 4, 2026

BACKGROUND: Frozen section (FS) tissue assessment is essential for guiding intraoperative surgical decision-making in oncology, particularly in procedures such as pancreatic ductal adenocarcinoma (PDAC) resections, where margin status critically impa... read more

Robust Distance Estimation with Out-of-distribution Detection in Ophthalmic Surgery.

IEEE transactions on bio-medical engineering Feb 4, 2026

OBJECTIVE: Micrometer-scale precision is vital for patient safety in ophthalmic surgery. Recent advancements in instrument-integrated optical sensors aim to accurately measure instrument-to-tissue distances. However, the reliability of these measurem... read more

A High-Accuracy Probabilistic-Based Sigmoid Approximator Incorporating Memory-Saving and Time-Efficient Strategies.

IEEE transactions on neural networks and learning systems Feb 4, 2026

The sigmoid function, as a widely used activation function in neural networks, has gained much attention for its approximation and associated usage in edge devices. A recent study applied the Gaussian cumulative function to approximate the sigmoid fu... read more

Artificial Intelligence Medical Compendium