Artificial Intelligence Medical Compendium

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

Showing 1,341 to 1,350 of 213,568 articles

SMFF-Net: Spatiotemporal-frequency Multi-domain Feature Fusion Network for EEG-based brain state detection.

Neuroscience
The timely and reliable detection of driver fatigue is crucial for reducing driving risks and improving traffic safety. EEG-based deep learning approaches for brain state detection suffer from insufficient cross-domain feature interaction and limited... read more 

Utilizing Large Language Models to Enhance Patient-Reported Outcome Measures: Application to the EQ-5D-5L and Bolt-ons.

Value in health : the journal of the International Society for Pharmacoeconomics and Outcomes Research
OBJECTIVES: Large language models (LLMs) may be useful tools for the development/adaptation of patient-reported outcome measures (PROMs). As a methodological proof-of-concept, we evaluated the use of LLMs to support the identification of potential EQ... read more 

BiGranMolNet: A deep learning method for predicting blood-brain barrier permeability based on Bi-Granularity Molecular Graphs.

Journal of biomedical informatics
OBJECTIVE: The selective permeability of the blood-brain barrier (BBB) hinders the delivery of central nervous system (CNS) drugs to brain targets. It is therefore crucial to determine BBB permeability during CNS drug development. METHODS: We propose... read more 

WFUMB Liver Ultrasound Fusion Imaging Technical Review and Position Statement: Focus on CT/MRI-Based Fusion.

Ultrasound in medicine & biology
OBJECTIVE: Ultrasound fusion imaging is a hybrid technique that combines real-time ultrasonography (US) with pre-acquired computed tomography (CT) or magnetic resonance imaging (MRI), using electromagnetic (EM) tracking to enable precise spatial corr... read more 

Wavelength-encoded neuromorphic inference enabled by microcavity MoS2 photodetector arrays.

Nature communications
Biological vision systems tightly couple spectral sensing with temporal integration to extract task-relevant information with minimal data movement. In contrast, conventional optoelectronic vision hardware typically separates photodetection from elec... read more 

Learning ordinality-aware multimodal representations for composite materials design.

Nature communications
Composite materials design requires understanding complex microstructural characteristics, necessitating the integration of heterogeneous data sources with artificial intelligence. Current multimodal learning frameworks are mostly developed for cryst... read more 

Engineering microbial consortia for distributed signal processing.

Nature communications
A central goal in biology is to infer input signals from measurable readouts. Engineered biosensors are usually built to respond selectively to single inputs, so crosstalk between sensors must be removed through laborious, context-specific orthogonal... read more 

Convergent genomic trajectories shape adaptation to life on land across animal lineages.

Nature communications
How animals repeatedly adapted to life on land is a central question in evolutionary biology. While terrestrialisation occurred independently across animal phyla, it remains unclear whether shared genomic mechanisms underlie these transitions. Here, ... read more 

Human imprints on global riverfronts.

Nature communications
Rivers are profoundly shaped by human activity along their water-land interfaces (riverfronts), yet the global distribution and drivers of these imprints remain poorly understood. Here we present a high-resolution global map of 7.52 million kilometer... read more 

Reinforcement learning for treatment decision-making in sepsis: a scoping review.

NPJ digital medicine
This scoping review summarizes the progress of reinforcement learning (RL) in clinical decision-making for sepsis at the intersection of medicine and artificial intelligence (AI). All 72 included studies were retrospective, with the majority using th... read more