Intensivists

A novel, standardised approach to balancing effectiveness, efficiency and utility of surveillance AI prediction models for hospitalised patients using sepsis prediction as an exemplar.

OBJECTIVE: To introduce a novel, standardised approach to evaluating AI prediction models in balancing effectiveness, efficiency and utility, using a sepsis prediction model case study. MATERIALS AND METHODS: Retrospective patient data from electronic medical records of 7 public hospitals was used to retrain and evaluate a machine learning sepsis prediction model. Four conventional metrics-area un...

A tandem reinforcement learning framework for localized prostate cancer treatment planning and machine parameter optimization.

BACKGROUND: Volumetric modulated arc therapy (VMAT) machine parameter optimization (MPO) is a complex, high-dimensional problem typically solved with inverse planning solutions that are both temporally and computationally expensive. While machine learning techniques have been explored to automate this process, they often supplement rather than replace conventional optimizers and are fundamentally ...

Timing matters: a machine learning-driven comparison of community and hospital-onset sepsis.

Automated bond valence sum analysis for crystallographic database quality assessment: a systematic study of rock salt oxides, halides, and chalcogenides.

Crystallographic databases are vital for research and increasingly serve as training data for machine learning in materials discovery, yet systematic ...

The Emerging Role of Olfactory Receptors: From Genomics to Precision Medicine.

Olfactory receptors (ORs), once considered peripheral to sensory biology, are now recognized as functionally important components of precision medicin...

Early prediction of colonization by carbapenemase-producing enterobacterales at ICU admission using machine learning.

Colonization by carbapenemase-producing Enterobacterales (CPE) on admission to an intensive care unit (ICU) poses a serious threat to infection contro...

A tri-omics and machine learning framework identifies prognostic biomarkers and metabolic signatures in sepsis.

Sepsis is a complex systemic inflammatory syndrome that currently lacks stable and specific biomarkers. Multi-omics integration combined with machine ...

Metabolic Syndrome and a Broken Heart: Trust Your Gut or Risk Your Heart.

Gut dysbiosis is increasingly recognized as a contributor to heart failure; however, its specific role in the development of metabolic syndrome-induce...

[Magnetically Controlled Capsule Endoscopy for Upper Gastrointestinal Examination].

Esophagogastroduodenoscopy (EGD) is the standard diagnostic modality for upper gastrointestinal (UGI) diseases, but its invasive nature and the risk o...

Infection-targeted innovations in anastomotic leak management: endoscopic advances, antimicrobial biomaterials, and precision strategies.

Anastomotic leakage (AL) is a devastating complication of gastrointestinal surgery and a critical source of hospital-acquired infections. This review ...

Derivation and validation of a clinical prediction score for ICU utilization at trauma intake.

BACKGROUND: Delayed admission to the intensive care unit (ICU) after trauma can lead to tripling of in-hospital mortality. Accurate ICU resource predi...

Evaluating the efficacy of large language models in predicting intensive care unit admission needs.

BACKGROUND: Timely identification and transfer of critically ill patients to intensive care units (ICUs) are crucial to reducing morbidity and mortali...

A wearable monitoring system for running gait analysis by diffusion transformer.

Conventional wearable monitoring devices often suffer from insufficient data accuracy and low posture recognition rates, making them inadequate for th...

A machine learning-based prediction model for poor prognosis in sepsis using lymphocyte count: a national, multicenter prospective cohort.

Sepsis-induced immunosuppression leads to poor prognosis. Circulating lymphocyte count (LC), as an easily accessible clinical marker, closely reflects...

Assessing in-hospital mortality risk in ICU lung cancer patients using machine learning: An analysis based on the MIMIC-IV database.

BACKGROUND: Patients with advanced lung cancer admitted to the intensive care unit (ICU) face a substantially elevated risk of in-hospital mortality. ...

Integrative analysis identifies lactylation-related biomarkers in sepsis via bioinformatics and machine learning.

BACKGROUND: Protein lactylation is a novel post-translational modification driven by lactate and has emerged as a critical link between cellular metab...

Temperature-Dependent Infrared Engineering for Extreme Environments: All-Dielectric Thermal Photonic Metamaterials Stable at 1873 K in Air.

The development of infrared engineering technologies for extreme environments remains a formidable challenge due to the inherent trade-offs among opti...

Multidisciplinary artificial intelligence systems versus single-model approaches for the diagnosis and management of ileus and volvulus.

BACKGROUND AND AIMS: The accurate and timely diagnosis of ileus versus volvulus is essential in emergency care, as treatment choices directly influenc...

Dharma: A novel, clinically grounded machine learning framework for pediatric appendicitis-Diagnosis, severity assessment and evidence-based clinical decision support.

Acute appendicitis is a common but diagnostically challenging surgical emergency in children. Existing linear scoring systems lack sufficient accuracy...

Contrastive learning enhanced retrieval-augmented few-shot framework for multi-label patent classification.

The rapid expansion of patent databases poses increasing challenges for multi-label patent classification, particularly for inventions spanning multip...