Critical Care

Cross-sequence semi-supervised learning for multi-parametric MRI-based visual pathway delineation.

Objective.Accurately delineating the visual pathway (VP) is crucial for understanding the human visual system and diagnosing related disorders. Exploring multi-parametric MR imaging data has been identified as an important way to delineate VP. However, due to the complex cross-sequence relationships, existing methods cannot effectively model the complementary information from different MRI sequenc...

Optimizing sepsis mortality prediction using hybrid federated learning and explainable AI framework.

A Novel Hybrid Model Based on GAN and Stacking for Improving Minority Class Detection in an Imbalanced Dataset of Endotracheal Tubes Position Errors.

Endotracheal tube (ETT) abnormal positioning diagnosis based on chest X-ray images can lead to errors, such as misclassifying malpositioned tubes as n...

Integrating single-cell and bulk transcriptomes with machine learning reveals a CAF signature for immunotherapy response in dMMR endometrial cancer.

BACKGROUND: Cancer-associated fibroblasts (CAFs) are key players in the tumor microenvironment (TME), but their roles in prognosis and immunotherapy r...

Ridge-structured PANI with interfacial stress-concentrating: reversible protonation driven high sensitivity over wide pressures.

In research on pressure-sensitive electronic skin (e-skin) for motion and physiological signal monitoring, balancing sensitivity with a broad pressure...

Machine learning to assess correlated sociodemographic and socioeconomic community-level data and association with sepsis incidence.

Communicable diseases platform (CDP): Real-Time clinical analytics for infections.

OBJECTIVE: Communicable diseases, especially seasonal respiratory illnesses, contribute significantly to paediatric hospital presentations and admissi...

Development of a new tool for prediction of hospital length of stay and intensive care needs in trauma patients using Machine Learning.

BACKGROUND: Trauma is a major global health burden leading to significant morbidity, disability, and mortality. Predictive models in trauma care tradi...

Multi-scale heart simulation augments the explainability of artificial intelligence-enabled electrocardiogram through provision of an electrocardiogram database labelled with cellular pathologies.

BACKGROUND AND OBJECTIVES: Although artificial-intelligence-enhanced electrocardiograms (AI-ECGs) offer prediction and diagnosis capabilities superior...

A multi-target therapeutic framework for Alzheimer's disease: an integrative mechanistic review.

BACKGROUND: Alzheimer's disease (AD) is increasingly recognized as a multifactorial network disorder in which amyloid and tau pathology interact with ...

Impact of continuing renin-angiotensin-aldosterone system inhibitors before surgery on intraoperative hypotensive events: a secondary analysis of the STOP-or-NOT Trial.

BACKGROUND: The multicentre STOP-or-NOT trial has shown that continuation of renin-angiotensin-aldosterone inhibitors (RAASis) before major noncardiac...

A multi-layer hypergraph framework for drug-drug interaction prediction based on transformer and hypergraph convolution.

Drug-drug interactions represent a key problem for drug research, development, and clinical practice. It is crucial to accurately predict interactions...

Association between the platelet to white blood cell ratio and short term mortality in critically ill patients with atherosclerotic cardiovascular disease: A retrospective study and machine learning with external validation.

BACKGROUND: The platelet to white blood cell ratio (PWR) has shown prognostic value in many diseases. Yet its predictive utility for patients with ath...

Comparing ACES AP0 and AP1 color primaries for smartphone colorimetry in detecting soil CO2 leakage with a beetroot (Beta vulgaris) biosensor.

Effective monitoring of CO2 leaks from carbon capture and storage (CCS) sites is vital to mitigate environmental risks, including soil acidification a...

Integrating Mendelian randomization and multi-omics analysis unravels gut microbiota-driven metabolic mechanisms in sepsis and identifies diagnostic biomarkers through experimental validation.

Sepsis, a life-threatening systemic inflammatory syndrome, remains a leading cause of global mortality due to its complex pathophysiology and the lack...

Co-classification network analysis reveals nodal dysfunction and dimension-specific alterations in obstructive sleep apnea-hypopnea syndrome.

BACKGROUND: Obstructive sleep apnea-hypopnea syndrome (OSAHS) is a prevalent sleep disorder linked to brain alterations, but its brain network pattern...

A machine learning-driven app for predicting the need for post-operative respiratory support in liver transplant recipients.

BACKGROUNDS: Liver transplantation (LT) is a life-saving procedure for patients with end-stage liver disease, yet post-operative complications, partic...

The role of AI-driven communication in delirium prevention, detection, and care for critically ill ICU patients: A systematic review with inductive thematic synthesis.

BACKGROUND: Delirium remains one of the most consequential complications among critically ill patients in ICUs, exerting profound effects on morbidity...

Synergistic integration of clinical and multi-omics data for early MCI diagnosis using an attention-based graph fusion network.

BACKGROUND: Mild cognitive impairment (MCI), a precursor to Alzheimer's disease (AD), requires precise early diagnosis. Single-omics approaches often ...

Vulnerabilities of feature clustering in EIT radiomics.

BACKGROUND: We aimed to determine whether unsupervised machine learning was able to discover latent and possibly clinically-relevant clusters, hidden ...