Sepsis

A Tissue Microenvironment Analogous to Certain Tumor Microenvironments Facilitates HIV Persistence

The HIV reservoir that establishes early upon infection and persists in tissues remains the primary barrier to a functional cure. While progress has been made to study the reservoir in blood compartments and specific cell types, knowledge gaps remain on the tissue microenvironment that facilitates persistence. The development of a novel immunoPET/CT-guided spatial transcriptomics pipeline has enab...

Development and Validation of a Two-Stage NLP-LLM System for Automated Extraction of Deprescribing Recommendations from Discharge Summaries

Introduction: Polypharmacy in older adults is associated with increased risks of adverse drug events and functional decline. Discharge summaries often contain deprescribing recommendations, but these are frequently overlooked due to documentation complexity. Objective: To develop and validate a two-stage hybrid system combining rule-based natural language processing (NLP) and large language model ...

A biologically annotated neural network for proteomic discovery in Parkinsons disease

Machine learning models that can utilize high-dimensional data to make predictions and derive biological insights can improve understanding of disease...

Sniffing Shapes Dopamine Signals for Reward Prediction

Adaptive behaviors depend on predicting outcomes from sensory evidence. Dopamine neurons in the ventral tegmental area (VTA) broadcast reward-predicti...

TxConformal: Controlling False Discoveries in AI-Driven Therapeutic Discovery

Artificial Intelligence (AI) is transforming therapeutic discovery by scoring a large set of promising candidates and prioritizing a shortlist for fur...

Differentiable latent structure discovery for interpretable forecasting in clinical time series

Background: Timely, uncertainty-aware forecasting from irregular electronic health records (EHR) can support critical-care decisions, yet most approac...

Artificial Intelligence, LLM-based generation of synthetic patients with Parkinson's Disease: towards a digital twin paradigm for in silico studies

Heterogeneity in sporadic Parkinson's Disease (PD) is a critical problem that drives variable rates of progression and treatment response and complica...

Generative Augmentation Reveals Previously Overlooked Signals in Transcriptomic Datasets

Identifying robust gene expression signatures from transcriptomic studies with small sample sizes remains one of the most persistent challenges in com...

Deep Learning-Guided Holotomography Reveals Early Structural Remodelling During Pluripotency Exit

Real-time assessment of human pluripotent stem cell (hPSC) quality is critical for reproducibility and safety in regenerative medicine, yet current me...

From Protocol to Practice: Graded Sepsis Bundle Compliance and Actionable Insights from Real-World ICU Data

Sepsis is a leading cause of in-hospital mortality, yet systematically evaluating temporal adherence to the Surviving Sepsis Campaign (SSC) bundle acr...

Tuberculosis in households with infectious cases in Kampala city: Harnessing health data science for new insights on an ancient disease with persistent, unresolved problems (DS-IAFRICA TB) study protocol

Tuberculosis (TB) is prevalent in Uganda and overlaps with a high rate of HIV/TB coinfection. While nearly all hospital-based TB cases in Kampala, the...

Learning temporal structure engages hippocampus and guides value-based behaviour

The ability to learn and exploit structured relationships between events is fundamental to adaptive behaviour and episodic-like memory, yet the neural...

Learning Dynamic Representations and Policies from Multimodal Clinical Time-Series with Informative Missingness

Multimodal clinical records contain structured measurements and clinical notes recorded over time, offering rich temporal information about the evolut...

Clinically Interpretable Sepsis Early Warning via LLM-Guided Simulation of Temporal Physiological Dynamics

Timely and interpretable early warning of sepsis remains a major clinical challenge due to the complex temporal dynamics of physiological deterioratio...

Infection-Reasoner: A Compact Vision-Language Model for Wound Infection Classification with Evidence-Grounded Clinical Reasoning

Assessing chronic wound infection from photographs is challenging because visual appearance varies across wound etiologies, anatomical locations, and ...

CSRA: Controlled Spectral Residual Augmentation for Robust Sepsis Prediction

Accurate prediction of future risk and disease progression in sepsis is clinically important for early warning and timely intervention in intensive ca...

Representation over Routing: Overcoming Surrogate Hacking in Multi-Timescale PPO

Temporal credit assignment in reinforcement learning has long been a central challenge. Inspired by the multi-timescale encoding of the dopamine syste...

In-silico cell sorting revealed granulocyte-specific single-cell-type gene expression from peripheral blood bulk expression data and its application as host response biomarkers to discriminate bacterial and viral infections

Peripheral Blood transcriptome analysis evaluated the bulk transcript abundance (TA) covering all leukocyte cell populations. However, there are 2 mai...

State-Dependent Parameter Relevance in Intensive Care: Syndrome-Specific Centroids Improve Orbit-Based Mortality Prediction from AUC 0.59 to 0.83 in 59,362 Predictions

Background: The Therapeutic Distance framework (Paper 1) achieved AUC 0.61 for orbit-based mortality prediction in 11,627 sepsis patients. We hypothes...

Clinician-Informed Feature Engineering Improves Machine Learning Assignment of Molecular Endotypes in the Intensive Care Unit

Objective: To develop a workflow that transforms electronic health record data into machine learning-ready features for molecular endotype assignment ...