Artificial Intelligence Medical Compendium

Explore the latest research on artificial intelligence and machine learning in medicine.

Showing 22,861 to 22,870 of 216,842 articles

Synthetic Data Generation for Long-Tail Medical Image Classification: A Case Study in Skin Lesions

arXiv
Long-tailed class distributions are pervasive in multi-class medical datasets and pose significant challenges for deep learning models which typically underperform on tail classes with limited samples. This limitation is particularly problematic in m... read more 

Sparse Memory Finetuning as a Low-Forgetting Alternative to LoRA and Full Finetuning

arXiv
Adapting a pretrained language model to a new task often hurts the general capabilities it already had, a problem known as catastrophic forgetting. Sparse Memory Finetuning (SMF) tries to avoid this by adding key-value memory layers to the model and,... read more 

Anatomical deformation prediction using artificial intelligence for fusion imaging during aortic endovascular procedures.

Journal of vascular surgery cases and innovative techniques
Placement of an aortic stent graft induces anatomical deformations, particularly at the iliac level, because of the introduction of rigid devices. Anticipating these changes may improve the accuracy of fusion guidance during endovascular procedures. ... read more 

AI-driven integration of genomic and exposome data for cancer risk: the combined risk score (CRS).

Human genomics
Polygenic risk scores (PRS) have emerged as important tools for quantifying inherited susceptibility to cancer, and are increasingly combined with environmental and lifestyle factors into composite risk scores (CRS). In this context, environmental in... read more 

Surgical and hormonal gender-affirming care: cross-domain determinants and artificial intelligence-enabled expansion.

International journal for equity in health
Gender-affirming surgery (GAS) and gender-affirming hormone therapy (GAHT) and are evidence-based components of care that support the health and well-being of transgender and gender-diverse (TGD) individuals, with extensive evidence linking them to r... read more 

Utilizing generative artificial intelligence to create simulated patient for history taking in gynecology.

BMC medical education
INTRODUCTION: This study aimed to evaluate the effectiveness of a generative artificial intelligence based simulated patient model in improving gynecological history-taking skills among medical students, compared with traditional clinical teaching me... read more 

Framework for evaluating explainable AI in antimicrobial drug discovery.

Journal of cheminformatics
Explainable artificial intelligence (XAI) methods for molecular property prediction lack standardized evaluation criteria, preventing widespread deployment in drug development and hit optimisation, where proper understanding of structure-activity rel... read more 

Microbial succession from nursery to vineyard highlights the role of beneficial and pathogenic microbes in young vineyard yield.

Environmental microbiome
BACKGROUND: The grapevine microbiome plays a central role in shaping vineyard performance, yet the influence of nursery inherited microbes on vineyard establishment and early productivity remains poorly understood. Our goals were to study the endosph... read more 

An Integrated AIVIVE-PBPK-QIVIVE Framework with HTTK Validation for Probabilistic Risk Assessment of Neodymium Nitrate.

Chemical research in toxicology
Rare earth elements (REEs) are critical to modern industries but pose growing health risks due to increasing environmental release, and neodymium nitrate (Nd(NO3)3), a representative REE compound, lacks comprehensive toxicological data. To address th... read more 

Adaptive Deep Learning for High-Fidelity Quantitative Single-Molecule Imaging.

Analytical chemistry
Accurate quantification of molecular dynamics in live cells is critical for elucidating receptor signaling and guiding therapeutic strategies. Yet current deep learning methods for fluorescence imaging often distort intensity and lack robustness unde... read more