MIMIC-IV
PulseAugur coverage of MIMIC-IV — every cluster mentioning MIMIC-IV across labs, papers, and developer communities, ranked by signal.
11 day(s) with sentiment data
-
New EHR-Complex benchmark tests AI agents on intricate clinical reasoning
Researchers have introduced EHR-Complex, a new benchmark designed to evaluate the clinical reasoning capabilities of AI agents when interacting with complex electronic health record (EHR) data. Unlike previous benchmark…
-
New dataset Insulin4RL enables offline reinforcement learning with irregular clinical data
Researchers have introduced Insulin4RL, a new dataset designed for offline reinforcement learning in healthcare settings. This dataset, derived from MIMIC-IV, contains over 375,000 decisions from 12,209 intensive care u…
-
New benchmark evaluates LLMs for auditing clinical discharge summaries
Researchers have developed a new benchmark called CareTransition-Audit to evaluate how well large language models can audit clinical discharge summaries. The benchmark, which uses the MIMIC-IV database and clinician-pro…
-
New Clin-JEPA framework enables joint-embedding predictive pretraining on EHR data
Researchers have developed Clin-JEPA, a novel multi-phase co-training framework designed for joint-embedding predictive pretraining on electronic health records (EHR). This framework addresses the challenge of creating …
-
New PACE-RAG framework enhances personalized drug recommendations for Parkinson's patients
Researchers have developed PACE-RAG, a novel retrieval-augmented generation framework designed to improve drug recommendations for patients with complex conditions like Parkinson's disease. Unlike existing methods that …
-
New benchmark reveals LLMs struggle with interactive physician assistance
Researchers have developed PhysAssistBench, a new benchmark designed to evaluate the capabilities of Large Language Models (LLMs) in assisting physicians. This benchmark focuses on interactive scenarios involving doctor…
-
New benchmark tests LLMs on multi-turn clinical question answering
Researchers have introduced EHRNote-ChatQA, a novel benchmark designed to evaluate multi-turn clinical question answering over longitudinal patient discharge summaries. This benchmark, derived from de-identified MIMIC-I…
-
New EHR models leverage ICD code hierarchy for improved predictions
Researchers have developed new methods for electronic health record (EHR) foundation models to better utilize the hierarchical structure of ICD diagnosis codes. Current models treat these codes as flat tokens, ignoring …
-
New PERRY method offers reliable uncertainty estimates for RL policy evaluation
A new paper introduces PERRY, a method for constructing valid confidence intervals for off-policy evaluation (OPE) when using auxiliary data, such as that generated by models. This approach is crucial for high-stakes do…
-
Tabular foundation models adapted for clinical survival prediction
Researchers have developed a method to adapt tabular foundation models for clinical survival analysis, a task crucial for predicting time-to-event outcomes like mortality. This approach involves training a survival-awar…
-
LongMoE framework tackles missing data in multimodal clinical learning
Researchers have introduced LongMoE, a novel framework designed to tackle the complexities of multimodal clinical learning. This approach effectively addresses two key challenges: missing data across different patient m…
-
AI predicts cancer complications up to two years in advance
Researchers have developed a transformer model capable of predicting the onset of organ-level complications in cancer patients up to two years in advance. The model analyzes longitudinal laboratory measurements, capturi…
-
New model HoT-SSM enhances medical knowledge graph reasoning
Researchers have developed HoT-SSM, a novel approach for analyzing medical knowledge graphs that incorporates higher-order temporal reasoning. This method constructs hypergraphs to capture complex relationships between …
-
New model offers interpretable anomaly detection for physiological sensors
Researchers have developed a new framework called the Distilled Explanation Model (DEM) for anomaly detection in physiological sensor data. This three-stage model aims to provide both high accuracy and interpretable exp…
-
New method estimates selection bias impact on medical AI models
Researchers have developed a new method to estimate the potential impact of selection bias on machine learning models, particularly in healthcare settings. This approach provides a practical upper bound on worst-case mo…
-
New AI Framework Enhances Safe and Explainable Medication Recommendations
Researchers have developed SafeRx-Agent, a novel multi-agent framework designed to improve the safety and explainability of medication recommendations. This system addresses limitations in traditional methods by groundi…
-
MedCollab framework enhances LLM clinical diagnosis with IBIS and HDRC
Researchers have developed MedCollab, a new multi-agent framework designed to enhance clinical diagnosis and report generation using large language models. MedCollab mimics hospital consultations by recruiting specialis…
-
New framework Vital Trace enhances clinical reasoning with protocol-constrained agents
Researchers have developed Vital Trace, a novel multi-agent framework designed to improve longitudinal clinical reasoning over electronic health records. This system utilizes a protocol-constrained approach with a compa…
-
Federated Learning Research Tackles Privacy, Forgetting, and Heterogeneity
Recent research in federated learning (FL) addresses critical challenges in privacy and data drift. One paper introduces TADI and Fulcrum to protect against topology-aware inference attacks by optimally allocating noise…
-
Schema-Grounded LLM Extracts Patient Data for Digital Twins
Researchers have developed SG-LLM, a novel method for extracting patient data from electronic health records to create digital twins. This approach grounds LLM extraction with schema constraints and a validation loop fo…