Category Ranking

98%

Total Visits

921

Avg Visit Duration

2 minutes

Citations

20

Article Abstract

Criteria to identify patients who are ready to be liberated from mechanical ventilation (MV) are imprecise, often resulting in prolonged MV or reintubation, both of which are associated with adverse outcomes. Daily protocol-driven assessment of the need for MV leads to earlier extubation but requires dedicated personnel. We sought to determine whether machine learning (ML) applied to the electronic health record could predict next-day extubation. We examined 37 clinical features aggregated from 12AM-8AM on each patient-ICU-day from a single-center prospective cohort study of patients in our quaternary care medical ICU who received MV. We also tested our models on an external test set from a community hospital ICU in our health care system. We used three data encoding/imputation strategies and built XGBoost, LightGBM, logistic regression, LSTM, and RNN models to predict next-day extubation. We compared model predictions and actual events to examine how model-driven care might have differed from actual care. Our internal cohort included 448 patients and 3,095 ICU days, and our external test cohort had 333 patients and 2,835 ICU days. The best model (LSTM) predicted next-day extubation with an AUROC of 0.870 (95% CI 0.834-0.902) on the internal test cohort and 0.870 (95% CI 0.848-0.885) on the external test cohort. Across multiple model types, measures previously demonstrated to be important in determining readiness for extubation were found to be most informative, including plateau pressure and Richmond Agitation Sedation Scale (RASS) score. Our model often predicted patients to be stable for extubation in the days preceding their actual extubation, with 63.8% of predicted extubations occurring within three days of true extubation. Our findings suggest that an ML model may serve as a useful clinical decision support tool rather than complete replacement of clinical judgement. However, any ML-based model should be compared with protocol-based practice in a prospective, randomized controlled trial to determine improvement in outcomes while maintaining safety as well as cost effectiveness.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC12307926PMC
http://dx.doi.org/10.1038/s41598-025-12264-4DOI Listing

Publication Analysis

Top Keywords

next-day extubation
16
predict next-day
12
external test
12
test cohort
12
extubation
9
machine learning
8
models predict
8
icu days
8
0870 95%
8
model
6

Similar Publications

Criteria to identify patients who are ready to be liberated from mechanical ventilation (MV) are imprecise, often resulting in prolonged MV or reintubation, both of which are associated with adverse outcomes. Daily protocol-driven assessment of the need for MV leads to earlier extubation but requires dedicated personnel. We sought to determine whether machine learning (ML) applied to the electronic health record could predict next-day extubation.

View Article and Find Full Text PDF

Background: Bronchiolitis obliterans syndrome (BOS) is a rare but severe noninfectious pulmonary complication that typically arises in the context of chronic graft-versus-host disease (cGVHD) following allogeneic hematopoietic stem cell transplantation (HSCT). Characterized by progressive small airflow obstruction and irreversible airflow limitation, it poses significant challenges in managing general anesthesia, especially in pediatric patients. There is currently no established consensus or clinical research on the optimal anesthetic approach for such cases, making this report noteworthy.

View Article and Find Full Text PDF

Hypokalemic periodic paralysis is a hereditary or acquired temporary flaccid paralysis of skeletal muscles, affecting proximal musculature more than distal, as a result of hypokalemia. In this report, we describe a unique case of amphetamine-induced hypokalemic periodic paralysis that has only been described twice in the current literature. A 31-year-old male with a history of substance abuse presented with altered mental status and acute tetraparesis after inhalation of methamphetamine.

View Article and Find Full Text PDF

Unexpected upper airway obstruction after ear flushing in two cats.

Vet Anaesth Analg

May 2025

Department of Clinical Diagnostics and Services, Section of Anaesthesiology, University of Zurich, Zurich, Switzerland.

This case report outlines complications associated with ear flush procedures in two cats. The first case, a female Domestic Short Hair cat, aged 8 years and weighing 3.9 kg, presented with signs of Horner's syndrome and right-sided facial paralysis.

View Article and Find Full Text PDF

Trichloroethylene (TCE) is a hydrocarbon used commercially as a degreasing solvent. It has gradually become obsolete due to its carcinogenic properties, but many industries still use it given its cost-effectiveness. While there have been reports and studies regarding chronic exposures to TCE, very few acute cases of altered mental status requiring intensive care have been reported so far.

View Article and Find Full Text PDF