Sepsis

Characterizing Autonomic Dysfunction during Resuscitation in Sepsis using Multiscale Entropy

Rationale Autonomic dysfunction is a hallmark of sepsis pathophysiology, yet its quantification remains challenging. Multiscale entropy (MSE) derived from heart rate variability (HRV) offers a dynamic measure of physiological complexity and may serve as a biomarker of early deterioration associated with subsequent organ failure, vasopressor escalation, or mortality. Objective To determine whethe...

Cultryx: Precision Diagnostic Stewardship for Blood Cultures Using Machine Learning

Background: The 2024 blood culture bottle shortage brought diagnostic resource allocation to the forefront, reflecting persistent, foundational challenges with low-value testing and empiric treatment approaches under clinical uncertainty. Objective: To determine whether a machine learning approach using electronic medical record data can predict bacteremia more effectively than existing systems an...

NN-Assisted Image Analysis for Quantifying Intracellular Trypanosoma cruzi Infection

Trypanosoma cruzi infection remains a central, yet methodologically challenging step in Chagas disease research and early-stage drug discovery. Curren...

The Causal Impact of Natural Language Processing-Driven Clinical Decision Support on Sepsis Mortality in England: An Augmented Synthetic Control Analysis of NHS Trust-Level Data

Background: Sepsis remains a leading cause of preventable hospital mortality in England, with NHS England reporting over 48,000 sepsis-related deaths ...

Eubiota: Modular Agentic AI for Autonomous Discovery in the Gut Microbiome

The gut microbiome regulates many aspects of human biology, including immunity and inflammatory diseases, yet mechanistic discovery and translation re...

Predicting Multi-Drug Resistance in Bacterial Isolates Through Performance Comparison and LIME-based Interpretation of Classification Models

The rise of Antimicrobial Resistance, particularly Multi-Drug Resistance (MDR), presents a critical challenge for clinical decision-making due to limi...

Deep learning extracts MoA-specific signatures from high-throughput images of chemically and genetically perturbed Corynebacteria

Tuberculosis (TB) is the worldwide leading infectious killer due to a single pathogen and increasing antimicrobial resistance (AMR) makes it imperativ...

Hierarchical Multi-Omics Trajectory Prediction forFecal Microbiota Transplantation: A Novel MachineLearning Framework for Small-Sample LongitudinalMulti-Omics Integration

Fecal microbiota transplantation (FMT) has emerged as a highly effective treatment for recurrent Clostridioides difficile infection and is being activ...

A Statistical Approach for Modeling Irregular Multivariate Time Series with Missing Observations

Irregular multivariate time series with missing values present significant challenges for predictive modeling in domains such as healthcare. While dee...

Genomic-island cassette architecture drives pathogenic Enterococcus cecorum lineages: Cassette2Vec-EC, a structural genomics and machine-learning framework

Mobile genetic elements and genomic islands (GIs) frequently encode antibiotic resistance and host-adaptation cargo, yet routine genome comparison pip...

Cholinergic--dopaminergic interplay underlies prediction error broadcasting

Neuromodulatory systems, notably basal forebrain cholinergic and midbrain dopaminergic pathways, critically influence reinforcement learning (Schultz ...

A ventral tegmental area GABAergic projection to the ventral pallidum regulates value-based decision making in mice

Activity of the mesolimbic system is essential for adaptive performance of reward-related behaviors. Within this system, dopaminergic (DAergic) neuron...

Machine learning-based framework for predicting human infection potential of coronavirus associated with tri-amino acid motifs, KIQ and LEP in spike protein

Assessing the human infection potential of emerging coronaviruses remains a critical challenge for global health preparedness. In this study, we devel...

Formally Verifying and Explaining Sepsis Treatment Policies with COOL-MC

Safe and interpretable sequential decision-making is critical in healthcare, yet reinforcement learning (RL) policies for sepsis treatment optimizatio...

Noradrenergic neuromodulation produces a NMDAR-dependent network state of respiratory rhythmogenesis in the preBotzinger Complex

Norepinephrine (NE) is an important mediator of sympathetic activity that influences breathing. At the level of the inspiratory neural network, the pr...

Inferring unobserved vector dynamics for dengue forecasting using physics-informed neural networks and mechanistic transmission models

Accurately characterising mosquito infection dynamics is essential for effective dengue prevention and control, yet these dynamics are rarely observab...

Deep Learning-Based Missing Value Imputation for Heart Failure Data from MIMIC-III: A Comparative Study of DAE, SAITS, and MICE+LightGBM

Background: Inadequate data in electronic health records can create problems for clinical decision support systems and predictive modelling tools. ICU...

From Robotics to Sepsis Treatment: Offline RL via Geometric Pessimism

Offline Reinforcement Learning (RL) promises the recovery of optimal policies from static datasets, yet it remains susceptible to the overestimation o...

Deep learning enables quantitative subcellular analysis of plant-microbe interfaces

Specialized host-microbe interfaces are central to cellular interactions in plants. Intracellular structures such as haustoria formed by filamentous p...

[Advances in frontier technologies and innovative applications for the prevention and control of hospital infections associated with multidrug-resistant bacteria].

Hospital-acquired infections (HAIs) significantly increase patient mortality and healthcare burden, with multidrug-resistant organisms (MDROs) exacerb...