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 electronic health records 90%
- used by FedAvg 90%
- used by MIMIC-III, a freely accessible critical care database 70%
- used by DagsHub 70%
- used by Gotit.pub 70%
- used by alphaXiv 70%
- other MIMIC-III, a freely accessible critical care database 70%
- used by ScienceCast 70%
- instance of electronic health records 70%
- used by CatalyzeX 70%
- used by ICD-10 70%
14 day(s) with sentiment data
-
New foundation model SepsisFlow enhances ICU sepsis risk prediction
Researchers have developed SepsisFlow, a new foundation model designed to provide continuous risk assessment and trajectory modeling for sepsis in intensive care units. This model integrates a Mamba-based foundation mod…
-
New framework tackles missing data in multimodal clinical records
Researchers have developed a novel causal representation learning framework designed to handle missing data in multimodal clinical records. This framework addresses the challenge of non-random modality missingness, wher…
-
EviDrug framework enhances medication recommendation with clinical evidence
Researchers have developed EviDrug, a novel framework for medication recommendation that leverages clinical evidence and residual learning. This system integrates a patient-specific prescription by combining a self-trai…
-
New research reveals flaws in AI benchmarking for medical image and EHR data
A new paper published on arXiv highlights significant issues with the evaluation of class-imbalance strategies in multimodal medical classification tasks. The research found that benchmarks using record-level splits on …
-
AI model learns patient dynamics for ICU simulation
Researchers have developed a novel patient world model using neural networks trained on longitudinal electronic health records (EHRs) to simulate intensive care unit (ICU) operations. This model aims to provide a unifie…
-
AI model learns patient dynamics for intensive care simulation
Researchers have developed a patient world model using neural networks to simulate health system dynamics in intensive care units. This model, trained on the MIMIC-IV dataset, can provide a shared clinical representatio…
-
Hawkes processes match neural TPPs on event timing, study finds
A new research paper re-evaluates the performance of Hawkes processes and neural temporal point processes (TPPs) on event sequence data. The study found that the performance gap between classical Hawkes processes and mo…
-
New agent framework streamlines virtual clinical trial operations
Researchers have developed VirtualTrialHarness (VTHarness), an agent framework designed to streamline the operationalization of virtual clinical trials. This system coordinates the selection of procedural skills for eac…
-
AI models for ICU mortality prediction show varying transportability across datasets
A new research paper explores the transportability of predictive models for ICU mortality. The study found that physiological trajectories transferred more consistently across different datasets and hospitals than obser…
-
New NECA method improves ICU patient deterioration prediction
Researchers have developed NECA, a novel method for predicting patient deterioration in intensive care units (ICUs). NECA augments existing predictive models by incorporating data from similar historical patients, speci…
-
New Research: Clinical AI Multi-Agent Systems Launder Bias, Don't Remove It
A new research paper titled "Disparity Laundering" reveals that multi-agent clinical AI systems, even when designed to average out errors, do not eliminate bias and can even amplify it. Experiments on MIMIC-IV data show…
-
Open MedJev model offers efficient zero-shot clinical decision support
Researchers have introduced MedJev, an open-source System One model designed for efficient clinical decision support. This model operates in a single forward pass without generating text, making it computationally effic…
-
New M4Bench benchmark tests AI agents on clinical EHR data derivation
Researchers have developed M4Bench, a new benchmark designed to evaluate the ability of AI coding agents to derive variables from clinical electronic health records. The benchmark consists of 28 tasks across 15 families…
-
AI clinical systems launder bias against Black patients, study finds
A new research paper titled "Disparity Laundering: Consensus Without Fairness in Clinical Multi-Agent Systems" published on arXiv explores the issue of bias in clinical AI systems. The study found that even when using m…
-
New M4Bench benchmark tests AI agents on clinical EHR data derivation
Researchers have developed M4Bench, a new benchmark designed to evaluate the ability of AI coding agents to accurately derive variables from clinical electronic health records (EHRs). The benchmark consists of 28 tasks …
-
JEV model shows promise in clinical trial assessment, outperforming Qwen Flash on MIMIC-III
A new research paper introduces JEV, a non-generative decision model designed for clinical trial criteria assessment. In comparative tests against Qwen Flash on datasets derived from MIMIC-III, MIMIC-IV, and TrialGPT, J…
-
New ECG Foundation Model Uses Language Learning for Cardiac Diagnosis
Researchers have developed QECGBERT, a novel foundation model for electrocardiogram (ECG) analysis that leverages self-supervised learning inspired by language models. This model explicitly encodes physiological wavefor…
-
New DIGOM framework enhances multimodal healthcare outcome prediction
Researchers have developed DIGOM, a novel graph-based framework designed to improve outcome prediction in multimodal healthcare data. DIGOM explicitly models three types of interactions: within-patient cross-modal, cros…
-
New iAUC framework enhances risk prediction evaluation with uncertainty awareness
Researchers have developed a new framework for evaluating risk prediction models that incorporate uncertainty. This interval-based AUC (iAUC) method extends traditional ROC analysis to handle interval-valued predictions…
-
New research questions JEPA effectiveness for EHR representation learning
A new research paper explores the effectiveness of Joint-Embedding Predictive Architectures (JEPAs) for learning representations from longitudinal electronic health records (EHRs). Despite stable training, the JEPA form…