MIMIC-IV
PulseAugur coverage of MIMIC-IV — every cluster mentioning MIMIC-IV across labs, papers, and developer communities, ranked by signal.
5 天有情绪数据
-
New JAX framework enables exact Archimedean copula inference
Researchers have developed a new JAX-native framework called \"acopula\" that can infer Archimedean copulas with exact parameter gradients and handle arbitrary censoring. This framework overcomes limitations of existing…
-
LLMs simplify clinical data access with M3 system
Researchers have developed M3, a system that uses conversational LLMs to simplify access and analysis of complex clinical databases like MIMIC-IV. M3 allows users to query the data using natural language, translating qu…
-
New framework aligns clinical text with EHR data for precise timelines
Researchers have developed a new framework to improve the accuracy of clinical timelines extracted from text by aligning it with structured electronic health record (EHR) data. This retrieval-augmented multimodal approa…
-
Croissant Baker tool automates ML dataset metadata generation
Researchers have introduced Croissant Baker, an open-source command-line tool designed to automatically generate metadata for machine learning datasets. This tool adheres to the Croissant standard, which is increasingly…
-
LLM agent with clinical world model improves sepsis treatment recommendations
Researchers have developed SepsisAgent, an LLM-based system designed to recommend sepsis treatment strategies in ICUs. This agent utilizes a learned Clinical World Model to simulate patient responses to interventions li…
-
LLM agent with clinical world model improves sepsis treatment
Researchers have developed SepsisAgent, a novel system that integrates a clinical world model with large language models (LLMs) to improve sepsis management in intensive care units. This agent uses the world model to si…
-
New estimators boost EHR foundation model efficiency
Researchers have developed two new estimators, SCOPE and REACH, to improve the efficiency of generative foundation models used with electronic health records (EHRs). These models typically predict clinical outcomes by s…
-
New RealICU benchmark tests LLM agents on long-context ICU data
Researchers have developed RealICU, a new benchmark designed to evaluate the reasoning capabilities of large language model agents in intensive care unit (ICU) settings. Unlike previous benchmarks that relied on clinici…
-
Clin-JEPA framework enhances EHR data prediction and risk assessment
Researchers have developed Clin-JEPA, a novel framework for joint-embedding predictive pretraining specifically designed for electronic health record (EHR) patient trajectories. This method addresses challenges in apply…
-
Neuro-symbolic AI advances offer explainability and reasoning beyond pure neural networks
Researchers are developing neuro-symbolic AI models that combine neural networks with symbolic reasoning to improve explainability and performance. Gyan, a novel non-transformer architecture, aims to overcome limitation…
-
LLMs enhance medical concept representation with text-attributed knowledge graphs
Researchers have developed MedCo, a framework that uses large language models to enhance medical concept representation within knowledge graphs. This approach addresses limitations in existing medical ontologies by infe…
-
New Gaussian Process Model Enhances Interpretable Clinical Time Series Forecasting
Researchers have developed StructGP, a novel Gaussian process model designed for interpretable forecasting in clinical time series. This model couples process convolutions with differentiable structure learning to uncov…
-
Tree-of-Evidence algorithm enhances multimodal AI interpretability
Researchers have developed a new method called Tree-of-Evidence (ToE) to improve the interpretability of Large Multimodal Models (LMMs). ToE frames model interpretability as an optimization problem, using lightweight "E…
-
New framework uses conditional diffusion models for multimodal federated learning
Researchers have developed a new framework called CondI to address missing data in multimodal federated learning, particularly in clinical settings. This approach uses conditional diffusion models to explicitly impute u…
-
FastOMOP architecture enables reliable, safe, and auditable agentic real-world evidence generation.
Researchers have introduced FastOMOP, an open-source multi-agent architecture designed to automate the generation of real-world evidence (RWE) from large healthcare datasets. The system separates governance, observabili…
-
Agentic AI system matches expert consensus in clinical reasoning for myeloma patients
A new study evaluated an agentic reasoning system for synthesizing longitudinal clinical records in multiple myeloma management. The system achieved 79.6% concordance with expert consensus, outperforming standard retrie…
-
CURA framework improves clinical LM risk prediction and uncertainty calibration
Researchers have introduced CURA, a novel framework designed to enhance the reliability of clinical language models in risk prediction. CURA aligns the models' uncertainty estimates with both individual error probabilit…
-
An Integrated Framework for Explainable, Fair, and Observable Hospital Readmission Prediction: Development and Validation on MIMIC-IV
Researchers have developed a new gradient-regularized Newton scheme to ensure global convergence for Gradient Boosting Decision Trees (GBDTs), a technique widely used in tabular machine learning. This method introduces …
-
Sparse Autoencoder Decomposition of Clinical Sequence Model Representations: Feature Complexity, Task Specialisation, and Mortality Prediction
Researchers have developed several novel approaches to improve clinical prediction using machine learning on electronic health records (EHRs). One method, Risk Horizons, uses a geometry-aware framework with hyperbolic e…
-
New AI frameworks enhance causal discovery and forecasting with neural assemblies and ODEs
Researchers have developed new methods for causal inference and discovery, addressing challenges posed by latent variables and continuous-time sequential data. One approach, Observable Neural ODEs (ObsNODEs), enables ca…