intensive care unit
PulseAugur coverage of intensive care unit — every cluster mentioning intensive care unit across labs, papers, and developer communities, ranked by signal.
4 day(s) with sentiment data
-
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…
-
New audit method reveals prediction model miscalibrations and demographic disparities
A new auditing method has been developed to identify where prediction models are miscalibrated and for whom, particularly concerning demographic disparities. This approach uses random forests to group similar observatio…
-
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…
-
Applied Research Associates patents AI for predicting circulatory shock
Applied Research Associates (ARA) has received a patent for an artificial intelligence model designed to predict circulatory shock in intensive care units. The AI model was developed using historical patient data and cl…
-
New LLM prompting method improves fairness in ICU mortality prediction
Researchers have developed a new framework called Case-Based Prompting (CAP) to improve the fairness of large language models (LLMs) used for predicting mortality risk in intensive care units. This training-free method …
-
AI model learns to mimic clinical conditions from healthy vital signs
Researchers have developed a deep generative model using conditional variational autoencoders to augment vital sign data from healthy individuals, mimicking patterns of specific clinical conditions. This model was train…
-
AI models show promise for detecting atrial fibrillation in ICU patients
Researchers have developed a new dataset and benchmarks for detecting atrial fibrillation (AF) in intensive care unit (ICU) patients using electrocardiograms (ECGs). The study compared three AI approaches: feature-based…
-
Developer releases Unicode string corpus to expose text handling flaws
A developer has created a corpus of 300 Unicode strings designed to expose flaws in naive text handling functions, particularly `len()`. The corpus includes various complex Unicode features like ZWJ sequences and astral…
-
New framework tackles missing data in EHRs for ICU patient monitoring
Researchers have developed a new multimodal prompt-learning framework designed to improve the accuracy of predicting patient outcomes in intensive care units (ICUs) by effectively handling missing data in electronic hea…
-
Offline RL optimizes sepsis treatment using MIMIC-IV data
Researchers have developed a novel approach using offline reinforcement learning to optimize the management of sepsis in intensive care units. By analyzing historical patient data from the MIMIC-IV database, the study m…
-
AI, Tariffs, and Global News Roundup
This news roundup covers a diverse range of topics including AI, alcohol, tariffs, trade, and political figures. It also touches upon the critical minerals sector, international currency exchange rates, and public healt…
-
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.