The use of APACHE II prognostic system in difficult-to-wean patients after long-term mechanical ventilation

Prediction prolonged mechanical ventilation in trauma patients of the intensive care unit according to initial medical factors: a machine learning approach

The goal of this study was to develop a predictive machine learning model to predict the risk of prolonged mechanical ventilation (PMV) in patients admitted to the intensive care unit (ICU), with a focus on laboratory and Arterial Blood Gas (ABG) data. This retrospective cohort study included ICU patients admitted to Rajaei Hospital in Shiraz between 2016 and March 20, 2022. All adult patients requiring mechanical ventilation and seeking ICU admission had their data analyzed. Six models were created in this study using five machine learning models (PMV more than 3, 5, 7, 10, 14, and 23 days). Patients' demographic characteristics, Apache II, laboratory information, ABG, and comorbidity were predictors. This study used Logistic regression (LR), artificial neural networks (ANN), support vector machines (SVM), random forest (RF), and C.5 decision tree (C.5 DT) to predict PMV. The study enrolled 1138 eligible patients, excluding brain-dead patients and those without mechanical ventilation or a tracheostomy. The model PMV > 14 days showed the best performance (Accuracy: 83.63-98.54). The essential ABG variables in our two optimal models (artificial neural network and decision tree) in the PMV > 14 models include FiO₂, paCO₂, and paO₂. This study provides evidence that machine learning methods outperform traditional methods and offer a perspective for achieving a consensus definition of PMV. It also introduces ABG and laboratory information as the two most important variables for predicting PMV. Therefore, there is significant value in deploying such models in clinical practice and making them accessible to clinicians to support their decision-making.

Nutritional support for successful weaning in patients undergoing prolonged mechanical ventilation

Successful weaning from ventilators not only improves the quality of life of patients, but also reduces medical expenses. The aim of this study was to explore the association between nutritional provision and successful ventilator weaning. In this retrospective study data from the Respiratory Care Center of Chung Shan Medical University Hospital between October, 2017 and July, 2019 on patient characteristics, amount of nutrition delivered, and clinical outcomes were retrieved. A total of 280 ventilated patients were enrolled and divided into successful extubation and failed weaning groups. There were 178 males (63.6%) and 102 females (36.4%) with a mean age of 67.3 ± 16.9 years. The successful extubation group consisted of patients who tended towards ideal body weight during the weaning process (BMI 23.9 ± 5.0 versus 22.7 ± 4.8 kg/m², p < 0.001). Patients from both groups initially received the same nutritional intervention, while patients of successful extubation received significantly more calories and protein after weaning (23.8 ± 7.8 kcal versus 27.8 ± 9.1 kcal, p < 0.001 and 0.97 ± 0.36 g versus 1.14 ± 0.42 g, p < 0.001). Successful weaning was associated with higher survival rate (p = 0.016), shortened hospital stay (p = 0.001), and reduced medical costs (p < 0.001). Overall, nutritional support with high calories and protein was associated with the probability of successful ventilator weaning in patients undergoing prolonged mechanical ventilation. Adequate nutrition is a determinant of successful ventilator weaning.

Early prediction of extubation failure in patients with severe pneumonia: a retrospective cohort study

Backgroud: Severe pneumonia is one of the most common causes for mechanical ventilation. We aimed to early identify severe pneumonia patients with high risk of extubation failure in order to improve prognosis.

Methods: From April 2014 to December 2015, medical records of intubated patients with severe pneumonia in intensive care unit were retrieved from database. Patients were divided into extubation success and failure groups, and multivariate logistic regressions were performed to identify independent predictors for extubation failure.

Results: A total of 125 eligible patients were included, of which 82 and 43 patients had extubation success and failure, respectively. APACHE II score (odds ratio (OR) 1.141, 95% confident interval (CI) 1.022–1.273, P = 0.019, cutoff at 17.5), blood glucose (OR 1.122, 95%CI 1.008–1.249, P = 0.035, cutoff at 9.87 mmol/l), dose of fentanyl (OR 3.010, 95%CI 1.100–8.237, P = 0.032, cutoff at 1.135 mg/d), and the need for red blood cell (RBC) transfusion (OR 2.774, 95%CI 1.062–7.252, P = 0.037) were independent risk factors for extubation failure.

Conclusion: In patients with severe pneumonia, APACHE II score > 17.5, blood glucose > 9.87 mmol/l, fentanyl usage > 1.135 mg/d, and the need for RBC transfusion might be associated with higher risk of extubation failure.

APACHE II score cannot predict successful weaning from prolonged mechanical ventilation

At least 5% of all intensive care unit patients require prolonged respiratory support. Multiple factors have been suggested as possible predictors of successful respiratory weaning so far. We sought to verify whether the Acute Physiology and Chronic Health Evaluation II (APACHE II) can predict freedom from prolonged mechanical ventilation (PMV) in patients treated in a regional weaning centre. The study group comprised 130 consecutive patients (age; median (interquartile range): 71 (62–77) years), hospitalized between 1 January 2012, and 31 December 2013. APACHE II score was assessed based on the worst values taken during the first 24 hours after admission. Glasgow coma scale was excluded from calculations due to the likely influence of sedative agents. The outcome was defined as freedom from mechanical ventilation, with or without tracheostomy on discharge. Among survivors (n = 115), 88.2% were successfully liberated from mechanical ventilation and 60.9% from tracheostomy. APACHE II failed to predict freedom from mechanical ventilation (area under the receiver–operating characteristic curve [AUROC] = 0.534; 95% confidence interval [CI]: 0.439–0.628; p = 0.65) and tracheostomy tube removal (AUROC = 0.527; 95% CI: 0.431–0.621; p = 0.63). Weaning outcome was unrelated to the aetiology of respiratory failure on admission (p = 0.41). APACHE II cannot predict weaning outcome in patients requiring PMV.

Characteristics and mortality of elderly patients admitted to the Intensive Care Unit of a district hospital

AIM

To study all the elderly patients (≥75 years) who were admitted in an Intensive Care Unit (ICU) of a Spanish hospital and identify factors associated with mortality.

PATIENTS AND METHODS

A retrospective, observational data collected prospectively in patients ≥75 years recruited from the ICU in the period of January 2004 to December 2010.

RESULTS

During the study period, 1661 patients were admitted to our unit, of whom 553 (33.3%) were older than 75 years. The mean age was 79.9 years, 317 (57.3%) were male, and the overall in-hospital mortality was 94 patients (17% confidence interval 14-20.3%). When comparing patients who survived to those who died, we found significant differences in mean age (P = 0.001), Acute Physiologic Assessment and Chronic Health Evaluation II and Simplified Acute Physiology Scoring II (SAPS II) on admission (P < 0.0001, postoperative patients (P = 0.001), and need for mechanical ventilation (P < 0.0001). Comparing age groups, we found statistically significant differences in SAPS II (P = 0.007), diagnosis of non-ST-segment elevation myocardial infarction (P = 0.014), complicated postoperative period (P = 0.001), and pacemaker (P = 0.034). Mortality between the groups was statistically significant (P = 0.004). The survival between the group of 65 and 74 years and patients >75 years was not significant (P = 0.1390).

CONCLUSIONS

The percentage of elderly patients in our unit is high, with low mortality rates. The age itself is not the sole determinant for admission to the ICU and other factors should be taken into account.