Latest AI and machine learning research in intensivists for healthcare professionals.
Omni-modal retrieval promises a single embedding space for text, image, video, document, and audio inputs, but building such a unified retriever is difficult since these modalities differ in data distribution, architecture, and optimization dynamics. In this work, we present Conan-embedding-v3, a decouple--fuse--recover framework for omni-modal retrieval. Conan-embedding-v3 first trains modality s...
Diagnosing 802.11 packet captures requires expert protocol knowledge, is slow, inconsistent across engineers, and unscalable. LLM-based approaches sound plausible but fabricate protocol events absent from captures (especially truncated traces), produce uncalibrated confidence scores, and suffer evaluation bias when golden references are co-produced by the model under test. We introduce PROBE (Prot...
Photoplethysmography (PPG), a non-invasive measure of changes in blood volume, is widely used in both wearable devices and clinical settings. Recent P...
How do multi-modal large language models that jointly process natural language and biological sequences (DNA, protein, structural alphabets) actually ...
Objective: To develop, calibrate, and interpret machine learning models for predicting in-hospital mortality among intensive care unit (ICU) patients ...
Introduction: Regulated cell death (RCD) pathways profoundly influence tumor progression and immune modulation. In prior work, we constructed a compre...
Background: Multi-drug resistant Bacterial (MDRB) Infections in the intensive care units (ICUs) substantially elevate patient mortality, prolong hospi...
Early prediction of respiratory failure is critical for timely clinical intervention in intensive care units. Existing electronic health record (EHR)-...
High-fidelity 3D Gaussian head avatar generation is critical for applications such as AR/VR, telepresence, and digital humans. Existing methods depend...
Multi-modality medical vision (MV) foundation models (FM) are fundamentally challenged by pronounced Non-IID feature statistics across heterogeneous i...
Despite strong predictive results in the clinical machine learning literature, the translation of these models into bedside use remains limited by sys...
Autonomous agentic systems are largely static after deployment: they do not learn from user interactions, and recurring failures persist until the nex...
Background Patients worldwide receive healthcare in many languages, yet medical AI systems are validated almost exclusively in high-resource languages...
Delayed diagnosis and poor antiretroviral therapy (ART) adherence remain primary drivers of HIV-related morbidity in low-resource settings, yet real-w...
Ensemble disagreement is widely used as a proxy for epistemic uncertainty in medical image segmentation. In practice, many studies form ensembles via ...
Background: Meningiomas are the most common primary intracranial tumors in adults, and volumetric assessment increasingly guides surveillance and trea...
The mechanical behavior of right ventricular (RV) myocardium is governed by its anisotropic microstructure, yet constitutive models that account for f...
Sepsis management in the ICU requires sequential treatment decisions under rapidly evolving patient physiology. Although large language models (LLMs) ...
Text- and image-conditioned video generation models have achieved strong visual fidelity and temporal coherence, but they often fail to generate motio...
Reconstructing precise clinical timelines is essential for modeling patient trajectories and forecasting risk in complex, heterogeneous conditions lik...