AI Medical Compendium

Integrating machine learning and single-cell sequencing to reveal the role of kinase-related genes in subtype classification and prognostic significance of lung squamous cell carcinoma.

Discover oncology May 9, 2026

BACKGROUND: Lung squamous cell carcinoma (LUSC) exhibits poor prognosis and a highly complex tumor immune microenvironment (TIME), creating an urgent clinical need for novel biomarkers to guide personalized treatment. Although kinase-related genes (K... read more

The sound of longevity: music and technology for healthy ageing.

Aging clinical and experimental research May 9, 2026

A growing body of research is focusing on how music, technology, and neuroscience can converge to promote healthy ageing and counteract pathological decline. In particular, music interventions for older adults have been garnering increasing attention... read more

Combining single cell and bulk transcriptomics with Mendelian randomization identifies gut microbiota related prognostic genes and mechanisms in thyroid cancer.

Discover oncology May 9, 2026

BACKGROUND: Imbalance in gut microbiota (GM) may play a role in the development of thyroid cancer (TC), but the specific mechanisms remain unclear. This study aimed to identify prognostic genes associated with both TC and GM and investigate the under... read more

Zero-TE MRI-based attenuation correction for bone components on chest [18F] FDG PET/MRI: accuracy, repeatability, and external validation of an unsupervised deep learning approach using unpaired PET/CT data.

Annals of nuclear medicine May 9, 2026

OBJECTIVE: In positron emission tomography (PET)/magnetic resonance imaging (MRI), attenuation correction (AC) for PET of the head is achieved by MRI data to generate pseudo-computed tomography (CT) images. However, for the torso, AC becomes more cha... read more

Protein Language Model Embeddings Improve HIV Drug Resistance Prediction: A Comprehensive Benchmark with Attention-Based Interpretability.

Bioinformatics (Oxford, England) May 9, 2026

MOTIVATION: Accurate prediction of HIV drug resistance from viral sequences is critical for optimising antiretroviral therapy. Traditional machine-learning approaches using binary mutation encoding achieve strong accuracy but may fail to capture epis... read more

3D human body modeling for clothing ergonomics: a review of techniques and applications in human-garment interaction.

Ergonomics May 9, 2026

3D human body modelling offers new opportunities for advancing ergonomic assessment in clothing design, particularly in evaluating fit, comfort, and human-garment interaction. This paper provides a systematic review of recent developments in 3D body ... read more

Feasibility of retrieval-augmented generation for large language models with Japanese input in radiotherapy.

Journal of radiation research May 9, 2026

Large language models (LLMs) have recently gained attention for their potential. However, concerns remain regarding their reliability due to limitations such as hallucinations and insufficient domain-specific knowledge. Retrieval-augmented generation... read more

Fear and Prompting: AI, Originary Technicity, and Colonialism.

Journal of the American Psychoanalytic Association May 9, 2026

This paper examines psychoanalysts' affective and defensive responses to artificial intelligence (AI) through the lens of originary technicity, the philosophical claim that technology is constitutive of the human rather than external to it. Drawing o... read more

Psychosocial Resources and Constraints: Distinct Pathways to Positive and Negative Self-Perceptions of Aging in Diverse Older Adults.

Clinical gerontologist May 9, 2026

OBJECTIVES: Self-perceptions of aging (SPA) predict behavioral health outcomes in later life, yet whether positive and negative attitudes arise from distinct psychosocial pathways remain unclear. This study examined correlates of positive and negativ... read more

Graph neural networks can predict ketosynthase substrate specificity.

Scientific reports May 9, 2026

Modular polyketide synthases are a class of biosynthetic machinery responsible for the production of a chemically diverse range of natural products, including essential medicines. The modular architecture of this system presents as inherently rearran... read more

Artificial Intelligence Medical Compendium