MIMIC-IV
PulseAugur coverage of MIMIC-IV — every cluster mentioning MIMIC-IV across labs, papers, and developer communities, ranked by signal.
- instance of MIMIC-III, a freely accessible critical care database 90%
- used by MIMIC-III, a freely accessible critical care database 70%
- used by electronic health records 70%
- used by ScienceCast 70%
- used by DagsHub 70%
- used by CatalyzeX 70%
- used by alphaXiv 70%
- used by Gotit.pub 70%
- used by Ehrs 70%
- used by Qwen3_8B 70%
- used by XGBoost 60%
15 day(s) with sentiment data
-
New Smooth Flow Matching framework generates functional data for healthcare research
Researchers have developed a new framework called Smooth Flow Matching (SFM) for generating functional data, which is data observed over a continuous domain. This method is designed to address challenges such as privacy…
-
New benchmark reveals mixed clinical utility for EHR foundation models
A new benchmark called FoMoH has been developed to evaluate foundation models (FMs) for structured electronic health records (EHRs). This benchmark includes 14 clinically meaningful prediction tasks and was tested on ov…
-
New ORCA framework adapts anomaly detection for wearable sensor data
Researchers have developed ORCA, a novel agentic framework for anomaly detection in multimodal wearable time series data. ORCA dynamically adapts its temporal receptive field during inference, eliminating the need for d…
-
New benchmark evaluates LLM clinical reasoning on EHR data
Researchers have introduced CliniCARE-Bench, a new benchmark designed to evaluate the clinical reasoning capabilities of large language models when processing electronic health records (EHRs). This benchmark utilizes 75…
-
New Graph Transformer Model Enhances EHR Data Analysis for Clinical Predictions
Researchers have developed MiGHT-EHR, a novel Multi-task Graph Transformer designed to process heterogeneous temporal Electronic Health Records (EHRs). This method constructs a graph where nodes represent clinical entit…
-
Quantum-Agentic AI Framework Predicts Cardiac Arrest Mortality
Researchers have developed QuanTiMedAI, a novel framework that combines agentic AI with quantum computing for predicting cardiac arrest mortality. This system utilizes a large language model for feature discovery and a …
-
EvtGraph framework optimizes multimodal temporal data learning with event-adaptive compression
Researchers have introduced EvtGraph, a novel framework designed to improve the efficiency of learning from multimodal temporal data. This approach addresses the challenge of irregular data density by using event-adapti…
-
New LM-GNN Framework Enhances Clinical Prediction with Patient Cohort Insights
Researchers have developed a novel framework called Patients-like-me (PLM) that combines language models (LMs) and graph neural networks (GNNs) for improved clinical prediction using electronic health records (EHRs). Th…
-
New EHR2Path framework models complete patient hospital pathways from multimodal data
Researchers have developed EHR2Path, a new multimodal framework designed to model and predict complete patient pathways within a hospital setting using electronic health records (EHRs). This system integrates diverse cl…
-
New benchmark EarlyDx tests AI diagnostic inference from limited clinical data
Researchers have developed EarlyDx, a new benchmark designed to evaluate how well AI models can generate diagnoses from limited, admission-time clinical data. Unlike previous benchmarks, EarlyDx uses free-text notes and…
-
New framework analyzes AI model failures when clinical data is missing
Researchers have developed a new framework to analyze the failure modes of multimodal clinical AI models. This framework, named Loud or Silent, assesses how model accuracy changes when specific modalities are removed, d…
-
Metamorphic testing framework proposed for clinical AI models
Researchers have proposed a new framework called metamorphic testing (MT) to evaluate the behavioral correctness of clinical machine learning models. This method assesses if models align with established medical knowled…
-
Harmonized ECG features improve cross-dataset clinical prediction
Researchers have developed a harmonized and interpretable feature representation for electrocardiogram (ECG) waveforms to improve cross-dataset clinical prediction. This approach, called FeatureDB, aims to reduce perfor…
-
New MedLoCoMo benchmark tests LLMs on long-context medical dialogue
Researchers have introduced MedLoCoMo, a new benchmark designed to evaluate the long-context medical dialogue capabilities of large language models. This benchmark, derived from MIMIC-IV and MIMIC-IV-Note records, focus…
-
LLMs enhance clinical causal inference by extracting hidden confounders from EHR data
A new research paper explores how large language models (LLMs) can improve causal inference from electronic health records (EHR) by extracting previously unmeasured clinical confounders from free-text notes. The study, …
-
Federated Learning Strategies Compared for Clinical Mortality Prediction
Researchers have benchmarked several federated learning strategies for predicting in-hospital mortality using the MIMIC-IV dataset. The study found that FedProx performed best in terms of AUC-ROC and AUC-PR, outperformi…
-
New framework integrates multimodal clinical data for EHR foundation models
Researchers have developed a new framework for autoregressive foundation models that can process multimodal clinical data, including ECG waveforms, chest X-ray images, and clinical notes, alongside structured electronic…
-
New Patient Sampling method improves EHR foundation models
A new pretraining method called Patient Sampling has been developed for autoregressive foundation models used with electronic health records (EHRs). This method addresses biases that can arise from standard language mod…
-
New MissHyper Model Improves Clinical Time Series Forecasting
Researchers have developed MissHyper, a novel forecasting model designed to improve the accuracy of clinical irregular multivariate time series. This model addresses a representation bottleneck by restoring co-timestamp…
-
LLMs boosted for clinical prediction via knowledge injection · arXiv paper
Researchers have developed a novel knowledge-injection framework designed to enhance the zero-shot adaptation of large language models for specialized tasks like delirium prediction in clinical settings. This method aug…