Critical Care

Machine learning and SHAP-based risk assessment of PICC-related bloodstream infections in premature infants at the time of clinical suspicion.

BACKGROUND: Peripherally inserted central catheter-related bloodstream infections (PICC-CRBSI) pose a serious threat to preterm infants. This study aimed to develop and validate an interpretable machine learning model for risk assessment of PICC-CRBSI at the time of clinical suspicion. METHODS: A total of 490 preterm infants who underwent PICC insertion in a tertiary hospital NICU in China were pr...

Early prediction of in-hospital mortality in ICU patients with heart failure using an interpretable machine learning model: a retrospective study based on MIMIC-IV.

BACKGROUND: Heart failure (HF) remains a major cause of morbidity and mortality worldwide, and acute decompensation frequently necessitates intensive care. Early identification of high-risk patients is essential, yet traditional HF risk scores were developed largely in chronic or ward-based cohorts and often fail to capture early physiologic deterioration in the ICU. Explainable machine-learning (...

Smartphone-based lightweight AI system for real-time multiple anterior segment disease screening: development and real-world validation.

BACKGROUND: Anterior segment diseases are a major global cause of preventable blindness, especially in regions with limited access to specialized opht...

Association between the endothelial activation and stress index and 28-day all-cause mortality in critically ill patients with chronic obstructive pulmonary disease: a retrospective cohort study and predictive model establishment based on machine learning.

BACKGROUND: Chronic obstructive pulmonary disease (COPD) remains a major global health burden and is currently the third leading cause of death worldw...

EXPRESS: Diagnostic Value of Short-Term Longitudinal Clinical and Laboratory Trajectories for Gram-Negative Bacteremia in ICU Patients.

Early identification of gram-negative bacteremia in intensive care units (ICUs) remains challenging at the time of blood culture sampling, when clinic...

A Lightweight LSTM-Transformer Fusion Architecture for Real-Time Sepsis Mortality Prediction.

BackgroundAccurate prediction of short-term mortality in sepsis patients is critical for timely clinical decision-making. However, existing deep learn...

Testing Near-Field Radio-Frequency Sensors to Predict Respiratory Distress in Patients Living With Dementia: A Pilot Feasibility and Acceptability Study.

BackgroundPeople living with dementia (PLWD) with advanced illness are prone to respiratory distress yet often cannot self-report dyspnea, delaying re...

Early sepsis prediction using a hybrid LSTM-GAT model: a study on the PhysioNet 2019 dataset.

OBJECTIVE: Sepsis is a potentially fatal systemic response to infection, in which early clinical intervention is critical to reduce mortality. This st...

Beyond NIHSS and neuroimaging: an interpretable gradient boosting model for predicting in-hospital mortality in ICU patients with acute ischemic stroke.

This study aimed to develop an interpretable machine learning model for predicting in-hospital mortality among acute ischemic stroke (AIS) patients ad...

Research progress on biomarkers for acute kidney injury in children.

Pediatric acute kidney injury (AKI) often presents insidiously and progresses rapidly. Traditional diagnostic criteria based on serum creatinine and u...

Automated full-text screening and accelerated reviews using large language models with context-aware agents: an exploratory analysis in biomarker research.

AIMS: Artificial intelligence (AI) tools utilizing large language models (LLMs) can accelerate scientific literature reviews by automating title, abst...

Global Trends in Postoperative Sepsis After Pancreatoduodenectomy: A Bibliometric Analysis.

INTRODUCTION: Postoperative sepsis after pancreatoduodenectomy (PSPD) remains a major determinant of morbidity and mortality. Although extensive clini...

Combining generative large language models and pretrained language models for predicting acute respiratory distress syndrome progression.

Acute Respiratory Distress Syndrome (ARDS) is a life-threatening condition in which early diagnosis and timely intervention are crucial. Recent resear...

Trusted Multi-View Learning under Noisy Supervision.

Multi-view learning methods often focus on improving decision accuracy while neglecting the decision uncertainty, which significantly restricts their ...

Machine learning-based prediction of ventilator therapeutic pressure for optimized CPAP titration.

BACKGROUND: Accurate prediction of therapeutic pressure for Continuous Positive Airway Pressure (CPAP) therapy is essential for effective treatment of...

Early identification of high-risk individuals for mortality after lung transplantation: A retrospective cohort study with topological feature engineering.

Lung transplantation remains the only definitive treatment for end-stage respiratory failure; however, it has substantial post-operative mortality ris...

Multi-omics-based machine learning model predicts response and guides treatment in Crohn disease: a case study in nutritional therapy.

BACKGROUND: Biomarkers are needed to predict treatment response and guide therapeutic decisions in Crohn disease (CD). We aimed to develop and validat...

Adaptive homomorphic federated learning framework for multi-institutional medical imaging with optimized diagnostic accuracy.

The growing use of artificial intelligence (AI) in medicine has highlighted the imperative for privacy-preserving and high-accuracy diagnostic systems...

Increased Antidepressant Use after Intensive Care for Aneurysmal Subarachnoid Haemorrhage: A Machine-Learning-Enhanced Propensity-Matched Nationwide Cohort Study.

BACKGROUND: Mood disorders after aneurysmal subarachnoid haemorrhage (aSAH) are common. Meanwhile, mood disorders are also common after intensive care...

Development and evaluation of an ontology for non-invasive respiratory support in acute care.

Managing patients with respiratory failure increasingly involves non-invasive respiratory support (NIRS) strategies to support respiration, often prev...