Artificial Intelligence Medical Compendium

The exponential growth of large vision-language models (VLMs) has created significant opportunities for advancing multimodal artificial intelligence in specialized domains such as ophthalmology. However, progress in ophthalmic VLMs remains limited, p... read more 

PURPOSE: This scoping review maps mobility wearable device hardware and artificial intelligence(AI) software and synthesise socioecological factors influencing device use among older adults aged 65 years and older. METHODS: We followed the Arksey and... read more 

Transcriptional regulation is mediated by enhancers, yet how genetic perturbations alter enhancer activity and gene expression remains unclear. We develop UDI-UMI-STARR-seq, integrating dual indexes and unique molecular identifiers, and combine it wi... read more 

OBJECTIVES: Sarcopenia is associated with an increased risk of frailty, falls, and mortality. Women exhibit distinct characteristics in appendicular lean mass and metabolism compared with men, and hormonal changes may further accelerate appendicular ... read more 

Investigating the dynamics of neural networks, which are governed by connectivity between neurons, is a fundamental challenge in neuroscience. Because passive (spontaneous) activity provides only limited information for estimating connectivity, pertu... read more 

BACKGROUND: Vision-language models (VLMs) may support surgical documentation through operative video narration, but fluent narration may not capture procedural details or safety-critical anatomy. We compared VLM-generated laparoscopic cholecystectomy... read more 

BACKGROUND: Early identification and treatment of high-risk CKD can lower the risk of kidney failure and cardiovascular events. A laboratory-based machine-learning model (Klinrisk) was developed to predict the risk of CKD progression in adults with, ... read more 

INTRODUCTION: Real-time monitoring of apneic events is important to improve treatment and reduce intermittent hypoxemia in preterm infants, but remains challenging. We aimed to develop and test a machine learning (ML) model capable of automatic detec... read more 

To address the issue of data distortion in traditional well log density reconstruction methods caused by harsh borehole environments in complex heterogeneous formations, and the challenge for general machine learning models to capture high-frequency ... read more 

Existing Semantic Web Service (SWS) discovery approaches based on classical machine learning suffer from limited representational capacity in high-dimensional semantic feature spaces and fail to fully exploit structured ontological knowledge for sema... read more