Conectar
To develop and validate a prediction model for high-flow nasal cannula (HFNC) failure in patients with acute hypoxaemic respiratory failure (AHRF).
AHRF accounts for a major proportion of intensive care unit (ICU) admissions and is associated with high mortality. HFNC is a non-invasive respiratory support technique that can improve patient oxygenation. However, HFNC failure, defined as the need for escalation to invasive mechanical ventilation, can lead to delayed intubation, prolonged mechanical ventilation and increased risk of mortality. Timely and accurate prediction of HFNC failure has important clinical implications. Machine learning (ML) can improve clinical prediction.
Multicentre observational study.
This study analysed 581 patients from an academic medical centre in Boston and 180 patients from Guangzhou, China treated with HFNC for AHRF. The Boston dataset was randomly divided into a training set (90%, n = 522) and an internal validation set (10%, n = 59), and the model was externally validated using the Guangzhou dataset (n = 180). A random forest (RF)-based feature selection method was used to identify predictive factors. Nine machine learning algorithms were selected to build the predictive model. The area under the receiver operating characteristic curve (AUC) and performance evaluation parameters were used to evaluate the models.
The final model included 38 features selected using the RF method, with additional input from clinical specialists. Models based on ensemble learning outperformed other models (internal validation AUC: 0.83; external validation AUC: 0.75). Important predictors of HFNC failure include Glasgow Coma Scale scores and Sequential Organ Failure Assessment scores, albumin levels measured during HFNC treatment, ROX index at ICU admission and sepsis.
This study developed an interpretable ML model that accurately predicts the risk of HFNC failure in patients with AHRF.
Clinicians and nurses can use ML models for early risk assessment and decision support in AHRF patients receiving HFNC.
TRIPOD checklist for prediction model studies was followed in this study.
Patients were involved in the sample of the study.
To investigate whether a low Braden Skin Score (BSS), reflecting an increased risk of pressure injury, could predict the risk of delirium in older patients in the intensive care unit (ICU).
Delirium, a common acute encephalopathy syndrome in older ICU patients, is associated with prolonged hospital stay, long-term cognitive impairment and increased mortality. However, few studies have explored the relationship between BSS and delirium.
Multicenter cohort study.
The study included 24,123 older adults from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database and 1090 older adults from the eICU Collaborative Research Database (eICU-CRD), all of whom had a record of BSS on admission to the ICU. We used structured query language to extract relevant data from the electronic health records. Delirium, the primary outcome, was primarily diagnosed by the Confusion Assessment Method for the ICU or the Intensive Care Delirium Screening Checklist. Logistic regression models were used to validate the association between BSS and outcome. A STROBE checklist was the reporting guide for this study.
The median age within the MIMIC-IV and eICU-CRD databases was approximately 77 and 75 years, respectively, with 11,195 (46.4%) and 524 (48.1%) being female. The median BSS at enrollment in both databases was 15 (interquartile range: 13, 17). Multivariate logistic regression showed a negative association between BSS on ICU admission and the prevalence of delirium. Similar patterns were found in the eICU-CRD database.
This study found a significant negative relationship between ICU admission BSS and the prevalence of delirium in older patients.
The BSS, which is simple and accessible, may reflect the health and frailty of older patients. It is recommended that BSS assessment be included as an essential component of delirium management strategies for older patients in the ICU.
This is a retrospective cohort study, and no patients or the public were involved in the design and conduct of the study.
FreshRSS