Latest AI and machine learning research in critical care for healthcare professionals.
Sepsis remains one of the most complex and heterogeneous syndromes in intensive care, characterized by diverse physiological trajectories and variable responses to treatment. While deep learning models perform well in the early prediction of sepsis, they often lack interpretability and ignore latent patient sub-phenotypes. In this work, we propose a machine learning framework by opening up a new a...
BACKGROUND Medical large language models (LLMs) achieving high benchmark accuracy exhibit unexplained variability in clinical tasks, producing errors that clinicians cannot safeguard against. Sparse autoencoders offer a mechanistic interpretability approach to reveal how models represent medical knowledge and why they fail. METHODS We evaluated clinical reasoning stability in GPT-5, MedGemma-27B-T...
Echocardiography is a cornerstone for managing heart failure (HF), with Left Ventricular Ejection Fraction (LVEF) being a critical metric for guiding ...
Background: Delayed or missed diagnosis of congenital heart disease (CHD) contributes to excess pediatric mortality worldwide. Echocardiography (echo)...
Due to silence in early stages, lung cancer has been one of the most leading causes of mortality in cancer patients world-wide. Moreover, major sympto...
We investigate whether temporal embedding models trained on longitudinal electronic health records can learn clinically meaningful representations wit...
Accurate clinical prognosis requires synthesizing structured Electronic Health Records (EHRs) with real-time physiological signals like the Electrocar...
Accurate assessment of patient-ventilator interaction is critical for optimizing respiratory support and detecting harmful dyssynchronies linked to ad...
Foundation models trained on patient electronic health records (EHRs) hold promise for transforming clinical care by enabling effective decision suppo...
Background Stress cardiomyopathy (SCM) shares features with acute myocardial infarction (AMI) which may lead to misdiagnosis and misaligned management...
Systematic identification of functional non-coding regulatory variants remains a major challenge in human genetics. Conventional approaches such as la...
Background: We previously published a literature based pipeline for sepsis gene prioritization (PS3 and candidate genes) using an LLM enabled retrieva...
Automated respiratory sound classification supports the diagnosis of pulmonary diseases. However, many deep models still rely on cycle-level analysis ...
For architectural design, representation across multiple Levels of Details (LoD) is essential for achieving a smooth transition from conceptual massin...
Modern Vision-Language Models (VLMs) remain poorly characterized in multi-step visual interactions, particularly in how they integrate perception, mem...
Effective management of Bovine Respiratory Disease Complex (BRDC) requires timely, non-invasive diagnostic tools to protect calf health and welfare. A...
Art technological investigations of historical panel paintings rely on acquiring multi-modal image data, including visual light photography, infrared ...
The recent surge in popularity of Nano-Banana and Seedream 4.0 underscores the community's strong interest in multi-image composition tasks. Compared ...
Healthcare visitation patterns are influenced by a complex interplay of hospital attributes, population socioeconomics, and spatial factors. However, ...
Sepsis remains one of the leading causes of mortality in intensive care units, where timely and accurate treatment decisions can significantly impact ...