MIMIC-III, a freely accessible critical care database
PulseAugur coverage of MIMIC-III, a freely accessible critical care database — every cluster mentioning MIMIC-III, a freely accessible critical care database across labs, papers, and developer communities, ranked by signal.
4 day(s) with sentiment data
-
Clinical NLP datasets shape suicidality detection, study finds
A new paper argues that the way clinical text datasets are constructed significantly influences the accuracy and interpretation of suicidality detection in Natural Language Processing (NLP). The research highlights that…
-
New diffusion model generates synthetic clinical data, capturing informative missingness
Researchers have developed a novel diffusion-based method to generate synthetic clinical time series data, which effectively models both laboratory values and their irregular observation patterns. This approach, detaile…
-
New benchmark REMEDI evaluates AI unlearning for clinical data
Researchers have introduced REMEDI, a new benchmark designed to evaluate machine unlearning techniques specifically for multi-label clinical disease inference. Existing unlearning methods are often unsuitable for medica…
-
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 framework enables scalable quantum neural network training on hardware
Researchers have developed a new framework for training quantum neural networks (QNNs) on quantum hardware, significantly reducing the computational cost of gradient estimation. This method lowers the required circuit e…
-
LLMs fine-tuned for clinical note summarization show scale-dependent gains
Researchers have developed a new pipeline for categorizing clinical provenance in hospital notes using fine-tuned large language models. The study adapted Llama-3 models to a dataset of ICU notes, achieving high accurac…
-
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…
-
New LLM framework enhances EHR data consistency for patient safety
Researchers have developed EHR-Inspector, a new framework designed to improve the accuracy of Electronic Health Records (EHRs). This system focuses on verifying consistency between unstructured clinical notes and struct…
-
New federated framework generates synthetic EHRs across hospitals
Researchers have developed FedEHR-Gen, a novel federated learning framework for generating synthetic Electronic Health Records (EHRs). This approach addresses the challenge of data privacy by enabling cross-hospital mod…
-
New AI framework enhances medication recommendation with dual attention
Researchers have developed GraphDiffMed, a new framework for recommending medication combinations from electronic health records. This system uses a dual-scale Differential Attention mechanism to filter out noise within…
-
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…
-
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…
-
Researchers combine physics models with ML for better noninvasive blood pressure monitoring
Researchers have developed a novel hybrid approach combining Windkessel models with machine learning to improve noninvasive blood pressure monitoring. This method integrates physical principles into data-driven models, …
-
Zero-shot LLMs show promise for clinical text segmentation beyond MIMIC-III
Researchers have developed a new method for segmenting clinical notes into sections, which can aid in decision-making and NLP tasks. They created a new obstetrics dataset to supplement existing ones like MIMIC-III, enab…