Tag
Researchers developed and deployed LLENS, an on-premises clinical support LLM agent platform running inside Hokkaido University Hospital's closed network using the open-weight Kimi K2.6 model on 8 NVIDIA H200 GPUs, achieving 97.2% accuracy on hospital document questions via interactive tool-based access compared to 81.3% with fixed retrieval.
This paper introduces RASC+, a retrieval-constrained LLM adjudication method for clinical value set authoring that improves candidate-pool recall and selection precision over prior RASC baselines, demonstrating that blinded LLM adjudication with Qwen3-based retrieval significantly outperforms direct generation.
Introduces BrainG3N, a dual-purpose tokenizer for 3D brain MRI latent diffusion using a frozen masked autoencoder encoder for clinically informative embeddings and a CNN decoder for reconstruction, achieving state-of-the-art performance on a 23-task benchmark and enabling controllable generation and longitudinal forecasting.
This paper proposes a method for curating a Cardiology Interface Terminology (CIT) to highlight details in electronic health record notes using a machine learning technique. The approach involves three phases, including deriving training data and training an ML model to identify candidate concepts, achieving high completeness and coverage on test data.