intensive care unit
PulseAugur coverage of intensive care unit — every cluster mentioning intensive care unit across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
Review paper details trustworthy AI for digital health
A new review paper published on arXiv synthesizes recent advancements in trustworthy artificial intelligence, focusing specifically on robustness and explainability within the digital health domain. The paper outlines k…
-
New LLM4EHR model aligns clinical data for improved EHR analysis
Researchers have developed LLM4EHR, a novel clinical foundation model designed to better align clinical time series data with medical event sequences. This model combines domain-adapted large language models with a Tran…
-
New EHR-MPC framework uses generative patient twins for sepsis treatment optimization
Researchers have developed EHR-MPC, a novel framework designed to optimize sepsis treatment in intensive care units. This system utilizes generative patient digital twins, built from electronic health records, to predic…
-
New framework enhances ICU risk prediction using ontology and cross-modal learning
Researchers have developed OC-Distill, a novel two-stage framework designed for improved ICU risk prediction using machine learning. The first stage employs an ontology-aware contrastive objective that leverages the ICD…
-
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…
-
EEG Foundation Models show promise for ICU burst suppression detection
A new study evaluates the effectiveness of EEG Foundation Models (FMs) for detecting burst suppression (BS) patterns in intensive care unit (ICU) electroencephalography (EEG) data. The research, which did not require pa…
-
AI models predict ICU delirium using ambient sound and light data
Researchers have developed sequential neural network models to predict Intensive Care Unit (ICU) delirium using ambient sensing data, specifically light intensity and sound pressure levels. A convolutional model demonst…
-
New study design tackles unobserved confounding in observational data
Researchers have introduced a novel study design called "confounder detection via treatment intent" to address unobserved confounding in observational data. This method involves querying human experts to identify unobse…
-
Report on AI Risk Assessment and Math Weapons
A report was written at ITU for the course "Digitalisation and Public Sector Transformation" concerning AI risk assessment and weapons of math destruction. The report's author was reminded of this work.
-
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…
-
New causal framework analyzes fairness in survival analysis
Researchers have developed a new causal framework to analyze fairness in time-to-event (TTE) analysis, a type of statistical modeling often used in healthcare and other high-stakes domains. This framework allows for the…
-
AI framework improves personalized medicine by resolving bias-precision paradox
Researchers have developed a new framework for personalized medicine that addresses the bias-precision paradox in causal representation learning. This framework utilizes a novel stochastic alignment strategy called samp…
-
New benchmark tests AI model transportability across diverse ICU data domains
Researchers have developed a new benchmark to evaluate how well machine learning models can adapt to different regional patient data after being initially trained on data from a single hospital. This addresses the chall…
-
New Bayesian method learns dynamics from near-optimal expert trajectories
Researchers have developed a new method called Bayesian Inverse Transition Learning to estimate system dynamics from near-optimal expert trajectories. This approach leverages the fact that the expert is near-optimal to …