Search

Successful weaning from prolonged mechanical ventilation (MV) is an important issue in respiratory care centers (RCCs). Delayed or premature extubation increases both the risk of adverse outcomes and healthcare costs. However, the accurate evaluation of the timing of successful weaning from MV is very challenging in RCCs. This study aims to utilize artificial intelligence algorithms to build predictive models for the successful timing of the weaning of patients from MV in RCCs and to implement a dashboard with the best model in RCC settings. A total of 670 intubated patients in the RCC in Chi Mei Medical Center were included in the study. Twenty-six feature variables were selected to build the predictive models with artificial intelligence (AI)/machine-learning (ML) algorithms. An interactive dashboard with the best model was developed and deployed. A preliminary impact analysis was then conducted. Our results showed that all seven predictive models had a high area under the receiver operating characteristic curve (AUC), which ranged from 0.792 to 0.868. The preliminary impact analysis revealed that the mean number of ventilator days required for the successful weaning of the patients was reduced by 0.5 after AI intervention. The development of an AI prediction dashboard is a promising method to assist in the prediction of the optimal timing of weaning from MV in RCC settings. However, a systematic prospective study of AI intervention is still needed. [ABSTRACT FROM AUTHOR]

Acute respiratory failure requiring mechanical ventilation is a major indicator of intensive care unit (ICU) admissions in cirrhotic patients and is an independent risk factor for ICU mortality. This retrospective study aimed to investigate the outcome and mortality risk factors in patients with liver cirrhosis (LC) who required prolonged mechanical ventilation (PMV) between 2006 and 2013 from two databases: Taiwan's National Health Insurance Research Database (NHIRD) and a hospital database. The hospital database yielded 58 LC patients (mean age: 65.3 years; men: 65.5%). The in-hospital mortality was significantly higher than in patients without LC. Based on the NHIRD database of PMV cases, patients were age-gender matched in a ratio of 1:2 for patients with and without LC. Model for End-Stage Liver Disease (MELD) score was calculated. The mortality was higher in patients with LC (19.5%) than those without LC (18.12%), though not statistically significant (p = 0.0622). Based on the hospital database, risk factor analysis revealed that patients who died had significant higher MELD score than the survivors (18.9 vs 13.7, p = 0.036) and patients with MELD score of >23 had higher risk of mortality than patients with MELD score of ≤23 (adjusted OR:9.26, 95% CI: 1.96–43.8). In conclusion, the in-hospital mortality of patients with high MELD scores who required PMV was high. MELD scores may be useful predictors of mortality in these patients. [ABSTRACT FROM AUTHOR]

Introduction: Patients with end-stage renal disease (ESRD(Pos)) usually have multiple comorbidities and are predisposed to acute organ failure and in-hospital mortality. We assessed the effect of ESRD on the poorly understood long-term mortality risk after a first-ever mechanical ventilation (1-MV) for acute respiratory failure.Methods: The data source was Taiwan's National Health Insurance (NHI) Research Database. All patients given a 1-MV between 1999 and 2008 from one million randomly selected NHI beneficiaries were identified (n = 38,659). Patients with or without ESRD (ESRD(Neg)) after a 1-MV between 1999 and 2008 were retrospectively compared and followed from the index admission date to death or the end of 2011. ESRD(Pos) patients (n = 1185; mean age: 65.9 years; men: 51.5 %) were individually matched to ESRD(Neg) patients (ratio: 1:8) using a propensity score method. The primary outcome was death after a 1-MV. The effect of ESRD on the risk of death after MV was assessed. A Cox proportional hazard regression model was used to assess how ESRD affected the mortality risk after a 1-MV.Results: The baseline characteristics of the two cohorts were balanced, but the incidence of mortality was higher in ESRD(Pos) patients than in ESRD(Neg) patients (342.30 versus 179.67 per 1000 person-years; P <0.001; covariate-adjusted hazard ratio: 1.43; 95 % confidence interval: 1.31-1.51). For patients who survived until discharge, ESRD was not associated with long-term (>4 years) mortality.Conclusions: ESRD increased the mortality risk after a 1-MV, but long-term survival seemed similar. [ABSTRACT FROM AUTHOR]

Summary: Background: Weaning off the ventilator and removal of the endotracheal tube requires appropriate timing and supportive care in order to avoid reintubation. In this study, the incidence, outcome, and factors predictive of failed extubation (reintubation within 48 hours), as well as the associated mortality in critically ill patients on mechanical ventilation in the adult intensive care unit (ICU), were studied. Methods: The medical records of all patients who experienced planned extubation in the ICUs of Chi-Mei Medical Center in 2008 were reviewed. The primary endpoints were factors predicting failed extubation and mortality. The secondary endpoint was the outcome of failed extubation. Results: Among the 1794 patients experiencing planned extubation, 167 patients (9.3%) required reintubation within 48 hours. The overall mortality rate was 8.1%. Using multivariate analyses, the factors predicting failed extubation were age ≥65 years and medical patients. The predictors of mortality included age ≥65 years, higher Acute Physiology and Chronic Health Evaluation II scores, and failed extubation. The patients with failed extubation had significantly longer ICU and hospital stays (15.2 vs. 6.6 days, and 40.3 vs. 24.0 days, respectively), increased incidence of tracheostomy (21.6% vs. 1.5%), a higher hospital mortality (45.5% vs. 4.2%), and higher hospital costs (52.3 vs. 30.4×104 New Taiwan dollars) when compared with patients who had successful extubation. Conclusion: Our study indicated that patients with failed extubation experienced significantly increased admission expenditure, increased tracheostomy rate, and higher hospital mortality. Advanced age should be considered an important risk factor for failed extubation and overall mortality when planning extubation in critically ill ICU patients. [ABSTRACT FROM AUTHOR]

Objectives: Interactions between mechanical ventilation (MV) and carbapenem interventions were investigated for the risk of Clostridium difficile infection (CDI) in critically ill patients undergoing concurrent carbapenem therapy. Methods: Taiwan’s National Intensive Care Unit Database (NICUD) was used in this analytical, observational, and retrospective study. We analyzed 267,871 intubated patients in subgroups based on the duration of MV support: 7–14 days (n = 97,525), 15–21 days (n = 52,068), 22–28 days (n = 35,264), and 29–60 days (n = 70,021). The primary outcome was CDI. Results: Age (>75 years old), prolonged MV assistance (>21 days), carbapenem therapy (>15 days), and high comorbidity scores were identified as independent risk factors for developing CDI. CDI risk increased with longer MV support. The highest rate of CDI was in the MV 29–60 days subgroup (adjusted hazard ratio (AHR) = 2.85; 95% confidence interval (CI) = 1.46–5.58; p < 0.02). Moreover, higher CDI rates correlated with the interaction between MV and carbapenem interventions; these CDI risks were increased in the MV 15–21 days (AHR = 2.58; 95% CI = 1.12–5.91) and MV 29–60 days (AHR = 4.63; 95% CI = 1.14–10.03) subgroups than in the non-MV and non-carbapenem subgroups. Conclusions: Both MV support and carbapenem interventions significantly increase the risk that critically ill patients will develop CDI. Moreover, prolonged MV support and carbapenem therapy synergistically induce CDI. These findings provide new insights into the role of MV support in the development of CDI. [ABSTRACT FROM AUTHOR]