intensive care and critical care medicine papers

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

By extending the Therapeutic Distance framework to incorporate state-dependent parameter relevance across 16 clinical syndromes in 84,176 ICU patients, this study demonstrates that syndrome-specific centroids significantly improve orbit-based mortality prediction (AUC 0.83) over established severity scores and standard machine learning models, while maintaining robustness to temporal drift and hyperparameter variations.

Basilakis, A., Duenser, M. W.2026-04-08📄 intensive care and critical care medicine

Re-evaluation Of Hypo- And Hyperoxemia In Patients With Respiratory Failure And Veno-Venous Extracorporeal Membrane Oxygenation

This retrospective study of 443 severe ARDS patients on VV-ECMO reveals a U-shaped association between mean PaO2 levels and mortality, identifying an optimal oxygenation range of 90–123 mmHg that differs from non-ECMO settings while also highlighting a significant risk associated with high FiO2.

Buenger, V., Russ, M., Hunsicker, O. + 5 more2026-04-07📄 intensive care and critical care medicine

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

This study demonstrates that integrating clinician expertise into the feature engineering process for machine learning models significantly improves the accuracy, efficiency, and interpretability of assigning molecular endotypes in critically ill patients compared to purely data-driven approaches.

Sines, B. J., Hagan, R. S., Jiang, X. + 9 more2026-04-07📄 intensive care and critical care medicine

Observation-process features are associated with larger domain shift in sepsis mortality prediction: a cross-database evaluation using MIMIC-IV and eICU-CRD

This study demonstrates that while incorporating observation-process features like measurement counts improves internal discrimination in sepsis mortality prediction models, it significantly exacerbates domain shift and degrades external calibration and transportability across different ICU databases.

Yamamoto, R., Wu, F., Sprehe, L. K. + 3 more2026-04-06📄 intensive care and critical care medicine

Therapeutic Distance: An Orbit-Based Framework for ICU Decision Support - Initial Validation in 11,627 Sepsis Patients from MIMIC-IV

This paper introduces and validates the "Therapeutic Distance" framework, an orbit-based decision support tool that analyzes 11,627 sepsis patients to identify subgroups with comparable outcomes based on clinical proximity to treatment centroids, thereby enabling individualized signal detection while acknowledging its role as a hypothesis-generating aid rather than a causal inference method.

Basilakis, A.2026-04-04📄 intensive care and critical care medicine

A Foundation Model for Intensive Care: Unlocking Generalization across Tasks and Domains at Scale

This study introduces ICareFM, a transformer-based foundation model pretrained on harmonized multi-continental critical care data that demonstrates superior generalization across diverse hospitals and clinical tasks, often matching or outperforming locally trained models with significantly fewer labeled patient stays.

Burger, M., Chopard, D., Lichtner, G. + 15 more2026-04-02📄 intensive care and critical care medicine

Integrated Bioinformatics Analysis Identifies and Validates Novel Cellular Senescence-Associated Genes in Sepsis and Sepsis-Induced ARDS

This study utilizes integrated bioinformatics and experimental validation to identify six novel cellular senescence-associated hub genes, particularly NFIL3, as promising diagnostic biomarkers and therapeutic targets for sepsis and sepsis-induced ARDS.

Li, P., Yu, Y., Feng, J. + 2 more2026-03-31📄 intensive care and critical care medicine

Physiological subphenotypes of ARDS: Prognostic and predictive enrichment for PEEP strategy

This study externally validates two distinct physiological ARDS subphenotypes, "Efficient" and "Restrictive," demonstrating that the "Restrictive" type predicts higher mortality and that PEEP strategy should be tailored to these subphenotypes, as higher PEEP benefits Restrictive patients while potentially harming Efficient ones.

Meza-Fuentes, G., Delgado, I., Barbe, M. + 11 more2026-03-30📄 intensive care and critical care medicine

Contrastive Transformer-Driven Discovery of Temporal Hemodynamic Subphenotypes in Cardiac Surgery Patients

This study demonstrates that a contrastive transformer framework applied to high-resolution post-operative hemodynamic data identifies three reproducible and clinically significant subphenotypes in cardiac surgery patients, outperforming dynamic time warping in prognostic separation and offering potential for improved risk stratification and personalized management.

Desman, J. M., Sabounchi, M., Oh, W. + 22 more2026-03-30📄 intensive care and critical care medicine

Human Genetic Analysis Reveals Circulating Alpha-1 Antitrypsin Level as a Protective Factor in Sepsis

This study utilizes a proteogenomic framework integrating large-scale human genetics and proteomics to establish a causal, protective role for circulating alpha-1 antitrypsin levels in sepsis, identifying SERPINA1 as a high-priority target for drug repurposing and therapeutic intervention.

Tan, D., Zhang, P., Zheng, T. M. + 11 more2026-03-27📄 intensive care and critical care medicine

A grading system of dynamic fibrinolysis resistance in sepsis associates with ICU outcomes

This prospective observational study of 116 sepsis patients demonstrates that a new point-of-care grading system for dynamic fibrinolysis resistance, derived from viscoelastic testing, effectively stratifies mortality risk and tracks clinical outcomes, where higher grades correlate with increased severity and death, while improvement in grade predicts favorable recovery.

Coupland, L. A., Frost, S. A., Lin, J. + 13 more2026-03-27📄 intensive care and critical care medicine

Inter-individual variability in lipoprotein proteomics reveals distinct patient clusters informative for disease pathogenesis and severity

This study analyzes lipoprotein proteomics in over 1,000 sepsis patients to identify three distinct sub-phenotypes reflecting disease severity and mortality, ultimately developing a validated quantitative score and machine learning models to enable precision medicine approaches for lipoprotein-based therapeutics.

Nguyen, M., Timouma, S., Qin, H. + 5 more2026-03-27📄 intensive care and critical care medicine

AKI-twinX: explainable organ structured digital twin for sepsis AKI trajectory forecasting

The paper introduces AKI-twinX, an explainable, organ-structured digital twin model trained on sepsis data that jointly forecasts acute kidney injury onset, trajectory, and mortality risk while capturing cardio-renal interactions and enabling clinically auditable counterfactual analysis.

Cai, J., Gatz, A. E., Li, J. + 6 more2026-03-22📄 intensive care and critical care medicine

Under-recognized or Under-reported? A Global Bibliometric Analysis (1994-2025) of Neurological Assessment in Pediatric Intensive Care Units

This global bibliometric analysis of 128 studies from 1994 to 2025 reveals a critical gap between the high neurological vulnerability of children in PICUs and the limited, inconsistent, and often underreported assessment strategies in the literature, highlighting an urgent need to expand structured neurological evaluations to all critically ill children regardless of their primary diagnosis.

Rodrigues, J. C. M., da Conceicao, B. C., Pantoja, L. V. P. S. + 10 more2026-03-13📄 intensive care and critical care medicine

Evaluation of SOFA-2 Score Performance Across Demographic Subgroups: An External Validation Study Using MIMIC-IV

This external validation study of the SOFA-2 score in the MIMIC-IV database reveals that while the model performs acceptably overall for predicting ICU mortality, its discrimination significantly declines with advancing age and among non-English speakers, highlighting critical demographic disparities that necessitate routine equity evaluations before widespread clinical implementation.

Ellen, J. G., Hao, S., Gao, C. A. + 9 more2026-03-11📄 intensive care and critical care medicine

CarpeDiem, a per-day clinical parameters and pneumonia adjudication dataset for critically ill patients with suspected pneumonia

The CarpeDiem dataset provides a unique, de-identified resource of 21,931 patient-hospital days from 704 critically ill, mechanically ventilated patients with suspected pneumonia, featuring daily clinical parameters and physician-adjudicated pneumonia episodes to enable detailed analysis of clinical trajectories beyond traditional admission and discharge metrics.

Gao, C. A., Markov, N. S., Kang, M. + 18 more2026-03-11📄 intensive care and critical care medicine

Efficacy of external diaphragm pacing combined with high-flow oxygen via tracheostomy for weaning in patients requiring prolonged mechanical ventilation: a study protocol for a randomized controlled trial

This randomized controlled trial protocol outlines a study in a Chinese rehabilitation hospital to evaluate whether combining external diaphragm pacing with high-flow oxygen via tracheostomy improves weaning outcomes and mitigates ventilator-induced diaphragmatic dysfunction in adult patients requiring prolonged mechanical ventilation.

Yang, L., Zheng, K., Li, N. + 2 more2026-03-09📄 intensive care and critical care medicine

Characterizing Autonomic Dysfunction during Resuscitation in Sepsis using Multiscale Entropy

This retrospective study demonstrates that Multiscale Entropy (MSE) features derived from heart rate variability during the first 24 hours of ICU admission predict 7-day mortality and 28-day organ dysfunction in sepsis patients with significantly higher accuracy than traditional severity of illness scores, particularly in those requiring vasopressors.

Krishnan, P., Sikora, A., Murray, B. + 8 more2026-03-05📄 intensive care and critical care medicine

Behavioral Telemetry for ICU Mortality Prediction: Documentation Pattern Analysis in 46,002 Low-Acuity MIMIC-IV Patients

This study demonstrates that analyzing behavioral telemetry signals derived from EHR documentation patterns significantly improves the prediction of ICU mortality in low-acuity patients, revealing that increased charting activity in discordant care cases reflects active clinical engagement rather than neglect.

Born, G.2026-03-02📄 intensive care and critical care medicine

Clinical and virological characteristics of critically ill patients with influenza in France during the 2025/26 season, marked by the emergence of influenza A(H3N2) clade K

This prospective, nationwide French cohort study of 685 critically ill influenza patients found that while the emergence of the A(H3N2) subclade K during the 2025/26 season was initially associated with higher mortality in univariable analysis, this increased risk was not significant after adjusting for host-related factors such as age and clinical frailty.

de Prost, N., Bay, P., Le Goff, M. + 33 more2026-02-28📄 intensive care and critical care medicine