Journal of critical care
-
Journal of critical care · Aug 2024
Development of a machine learning model for prediction of the duration of unassisted spontaneous breathing in patients during prolonged weaning from mechanical ventilation.
Treatment of patients undergoing prolonged weaning from mechanical ventilation includes repeated spontaneous breathing trials (SBTs) without respiratory support, whose duration must be balanced critically to prevent over- and underload of respiratory musculature. This study aimed to develop a machine learning model to predict the duration of unassisted spontaneous breathing. ⋯ The developed machine learning model showed informed results when predicting the spontaneous breathing capacity of a patient in prolonged weaning, however lacking prognostic quality required for direct translation to clinical use.
-
Journal of critical care · Aug 2024
Telemedicine critical care availability and outcomes among mechanically ventilated patients.
Telemedicine Critical Care (TCC) improves adherence to evidence based protocols associated with improved mortality among patients receiving invasive mechanical ventilation (IMV). We sought to evaluate the relationship between hospital availability of TCC and outcomes among patients receiving IMV. ⋯ Hospital TCC availability was not associated with improved outcomes among patients receiving IMV.
-
Journal of critical care · Aug 2024
Development and validation of potential phenotypes of serum electrolyte disturbances in critically ill patients and a Web-based application.
Electrolyte disturbances are highly heterogeneous and severely affect the prognosis of critically ill patients. Our study was to determine whether data-driven phenotypes of seven electrolytes have prognostic relevance in critically ill patients. ⋯ Three different clinical phenotypes were identified that correlated with electrolyte distribution and clinical outcomes. Further validation and characterization of these phenotypes is warranted.
-
Journal of critical care · Aug 2024
Artificial intelligence and machine learning: Definition of terms and current concepts in critical care research.
With increasing computing power, artificial intelligence (AI) and machine learning (ML) have prospered, which facilitate the analysis of large datasets, especially those found in critical care. It is important to define these terminologies, to inform a standardized approach to critical care research. This manuscript hopes to clarify these terms with examples from medical literature. ⋯ ML, a subset of AI, is typically focused on supervised or unsupervised learning tasks in which the output is based on inputs and derived from iterative pattern recognition algorithms, while AI is the overall ability of a machine to "think" or mimic human behavior; and to analyze data free from human influence. Even with successful implementation, advanced AI and ML algorithms have faced challenges in adoption into practice, mainly due to their lack of interpretability, which hinders trust, buy-in, and engagement from clinicians. Consequently, traditional algorithms, such as linear and logistic regression, that may have reduced predictive power but are highly interpretable, continue to be widely used.
-
Journal of critical care · Aug 2024
Cytomegalovirus infection in intensive care unit patients with hematological malignancies: Characteristics and clinical outcomes.
Cytomegalovirus (CMV) infection is associated with poor outcome in ICU patients. However, data on immunocompromised patients are scarce. This study aims to describe characteristics and outcomes of critically ill hematological patients and CMV infection. CMV disease characteristics and relationship between CMV viral load, CMV disease, coinfections by other pathogens and outcomes are described. ⋯ In critically-ill hematological patients, CMV viral load is independently associated with hospital mortality. Conversely, neither CMV disease nor treatment was associated with outcome suggesting viral load to be a surrogate for immune status rather than a cause of poor outcome.