Dataset Information

Revisiting Unplanned Endotracheal Extubation and Disease Severity in Intensive Care Units.

ABSTRACT: Most reports regarding unplanned extubation (UE) are case-control studies with matching age and disease severity. To avoid diminishing differences in matched factors, this study with only matching duration of mechanical ventilation aimed to re-examine the risk factors and the factors governing outcomes of UE in intensive care units (ICUs). This case-control study was conducted on 1,775 subjects intubated for mechanical ventilation. Thirty-seven (2.1%) subjects with UE were identified, and 156 non-UE subjects were randomly selected as the control group. Demographic data, acute Physiological and Chronic Health Evaluation II (APACHE II) scores, and outcomes of UE were compared between the two groups. Logistic regression analysis was used to identify the risk factors of UE. Milder disease, younger age, and higher Glasgow Coma Scale (GCS) scores with more frequently being physically restrained (all p<0.05) were related to UE. Logistic regression revealed that APACHE II score (odds ratio (OR) 0.91, p<0.01), respiratory infection (OR 0.24, p<0.01), physical restraint (OR 5.36, p<0.001), and certain specific diseases (OR 3.79-5.62, p<0.05) were related to UE. The UE patients had a lower ICU mortality rate (p<0.01) and a trend of lower in-hospital mortality rate (p = 0.08). Cox regression analysis revealed that in-hospital mortality was associated with APACHE II score, age, shock, and oxygen used, all of which were co-linear, but not UE. The results showed that milder disease with higher GCS scores thereby requiring a higher use of physical restraints were related to UE. Disease severity but not UE was associated with in-hospital mortality.

SUBMITTER: Chuang ML

PROVIDER: S-EPMC4617893 | biostudies-literature | 2015

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Revisiting Unplanned Endotracheal Extubation and Disease Severity in Intensive Care Units.

Chuang Ming-Lung ML Lee Chai-Yuan CY Chen Yi-Fang YF Huang Shih-Feng SF Lin I-Feng IF

PloS one 20151020 10

Most reports regarding unplanned extubation (UE) are case-control studies with matching age and disease severity. To avoid diminishing differences in matched factors, this study with only matching duration of mechanical ventilation aimed to re-examine the risk factors and the factors governing outcomes of UE in intensive care units (ICUs). This case-control study was conducted on 1,775 subjects intubated for mechanical ventilation. Thirty-seven (2.1%) subjects with UE were identified, and 156 no ...[more]

PMID: 26484674

Similar Datasets

Project description:BackgroundPatient safety in the intensive care unit (ICU) is one of the most critical issues, and unplanned extubation (UE) is considered the most adverse event for patient safety. Prevention and early detection of such an event is an essential but difficult component of quality care.ObjectiveThis study aimed to develop and validate prediction models for UE in ICU patients using machine learning.MethodsThis study was conducted in an academic tertiary hospital in Seoul, Republic of Korea. The hospital had approximately 2000 inpatient beds and 120 ICU beds. As of January 2019, the hospital had approximately 9000 outpatients on a daily basis. The number of annual ICU admissions was approximately 10,000. We conducted a retrospective study between January 1, 2010, and December 31, 2018. A total of 6914 extubation cases were included. We developed a UE prediction model using machine learning algorithms, which included random forest (RF), logistic regression (LR), artificial neural network (ANN), and support vector machine (SVM). For evaluating the model's performance, we used the area under the receiver operating characteristic curve (AUROC). The sensitivity, specificity, positive predictive value, negative predictive value, and F1 score were also determined for each model. For performance evaluation, we also used a calibration curve, the Brier score, and the integrated calibration index (ICI) to compare different models. The potential clinical usefulness of the best model at the best threshold was assessed through a net benefit approach using a decision curve.ResultsAmong the 6914 extubation cases, 248 underwent UE. In the UE group, there were more males than females, higher use of physical restraints, and fewer surgeries. The incidence of UE was higher during the night shift as compared to the planned extubation group. The rate of reintubation within 24 hours and hospital mortality were higher in the UE group. The UE prediction algorithm was developed, and the AUROC for RF was 0.787, for LR was 0.762, for ANN was 0.763, and for SVM was 0.740.ConclusionsWe successfully developed and validated machine learning-based prediction models to predict UE in ICU patients using electronic health record data. The best AUROC was 0.787 and the sensitivity was 0.949, which was obtained using the RF algorithm. The RF model was well-calibrated, and the Brier score and ICI were 0.129 and 0.048, respectively. The proposed prediction model uses widely available variables to limit the additional workload on the clinician. Further, this evaluation suggests that the model holds potential for clinical usefulness.

Project description:Background: Extubation failure (EF) can lead to an increased chance of ventilator-associated pneumonia, longer hospital stays, and a higher mortality rate. This study aimed to develop and validate an accurate machine-learning model to predict EF in intensive care units (ICUs). Methods: Patients who underwent extubation in the Medical Information Mart for Intensive Care (MIMIC)-IV database were included. EF was defined as the need for ventilatory support (non-invasive ventilation or reintubation) or death within 48 h following extubation. A machine-learning model called Categorical Boosting (CatBoost) was developed based on 89 clinical and laboratory variables. SHapley Additive exPlanations (SHAP) values were calculated to evaluate feature importance and the recursive feature elimination (RFE) algorithm was used to select key features. Hyperparameter optimization was conducted using an automated machine-learning toolkit (Neural Network Intelligence). The final model was trained based on key features and compared with 10 other models. The model was then prospectively validated in patients enrolled in the Cardiac Surgical ICU of Zhongshan Hospital, Fudan University. In addition, a web-based tool was developed to help clinicians use our model. Results: Of 16,189 patients included in the MIMIC-IV cohort, 2,756 (17.0%) had EF. Nineteen key features were selected using the RFE algorithm, including age, body mass index, stroke, heart rate, respiratory rate, mean arterial pressure, peripheral oxygen saturation, temperature, pH, central venous pressure, tidal volume, positive end-expiratory pressure, mean airway pressure, pressure support ventilation (PSV) level, mechanical ventilation (MV) durations, spontaneous breathing trial success times, urine output, crystalloid amount, and antibiotic types. After hyperparameter optimization, our model had the greatest area under the receiver operating characteristic (AUROC: 0.835) in internal validation. Significant differences in mortality, reintubation rates, and NIV rates were shown between patients with a high predicted risk and those with a low predicted risk. In the prospective validation, the superiority of our model was also observed (AUROC: 0.803). According to the SHAP values, MV duration and PSV level were the most important features for prediction. Conclusions: In conclusion, this study developed and prospectively validated a CatBoost model, which better predicted EF in ICUs than other models.

Project description:BackgroundExtubation is the process of removing tracheal tubes so that patients maintain oxygenation while they start to breathe spontaneously. However, hypoxemia after extubation is an important issue for critical care doctors and is associated with patients' oxygenation, circulation, recovery, and incidence of postoperative complications. Accuracy and specificity of most related conventional models remain unsatisfactory. We conducted a predictive analysis based on a supervised machine-learning algorithm for the precise prediction of hypoxemia after extubation in intensive care units (ICUs).MethodsData were extracted from the Medical Information Mart for Intensive Care (MIMIC)-IV database for patients over age 18 who underwent mechanical ventilation in the ICU. The primary outcome was hypoxemia after extubation, and it was defined as a partial pressure of oxygen <60 mmHg after extubation. Variables and individuals with missing values greater than 20% were excluded, and the remaining missing values were filled in using multiple imputation. The dataset was split into a training set (80%) and final test set (20%). All related clinical and laboratory variables were extracted, and logistics stepwise regression was performed to screen out the key features. Six different advanced machine-learning models, including logistics regression (LOG), random forest (RF), K-nearest neighbors (KNN), support-vector machine (SVM), eXtreme Gradient Boosting (XGBoost), and Light Gradient Boosting Machine (LightGBM), were introduced for modelling. The best performance model in the first cross-validated dataset was further fine-tuned, and the final performance was assessed using the final test set.ResultsA total of 14,777 patients were included in the study, and 1,864 of the patients' experienced hypoxemia after extubation. After training, the RF and LightGBM models were the strongest initial performers, and the area under the curve (AUC) using RF was 0.780 [95% confidence interval (CI), 0.755-0.805] and using LightGBM was 0.779 (95% CI, 0.752-0.806). The final AUC using RF was 0.792 (95% CI, 0.771-0.814) and using LightGBM was 0.792 (95% CI, 0.770-0.815).ConclusionsOur machine learning models have considerable potential for predicting hypoxemia after extubation, which help to reduce ICU morbidity and mortality.

Project description:Northern Italy has been the first European area affected by the COVID-19 pandemic and related social restrictive measures. We sought to evaluate the impact of the COVID-19 outbreak on PICU admissions in Northern Italy, using data from the Italian Network of Pediatric Intensive Care Units Registry. We included all patients admitted to 4 PICUs from 8-weeks-before to 8-weeks-after February 24th, 2020, and those admitted in the same period in 2019. Incidence rate ratios (IRR) evaluating incidence rate differences between pre- and post-COVID-19 periods in 2020 (IRR-1), as well as between the post-COVID-19-period with the same period in 2019 (IRR-2), were computed using zero-inflated negative binomial or Poisson regression modeling. A total of 1001 admissions were included. The number of PICU admissions significantly decreased during the COVID-19 outbreak compared to pre-COVID-19 and compared to the same period in 2020 (IRR-1 0.63 [95%CI 0.50-0.79]; IRR-2 0.70 [CI 0.57-0.91]). Unplanned and medical admissions significantly decreased (IRR-1 0.60 [CI 0.46-0.70]; IRR-2 0.67 [CI 0.51-0.89]; and IRR-1 0.52, [CI 0.40-0.67]; IRR-2 0.77 [CI 0.58-1.00], respectively). Intra-hospital, planned (potentially delayed by at least 12 h), and surgical admissions did not significantly change. Patients admitted for respiratory failure significantly decreased (IRR-1 0.55 [CI 0.37-0.77]; IRR-2 0.48 [CI 0.33-0.69]).Conclusions: Unplanned and medical PICU admissions significantly decreased during COVID-19 outbreak, especially those for respiratory failure. What is Known: • Northern Italy has been the first European area affected by the COVID-19 pandemic. • Although children are relatively spared from the severe COVID-19 disease, the pediatric care system has been affected by social restrictive measures, with a reported 73-88% reduction in pediatric emergency department admissions. What is New: • Unplanned and medical PICU admissions significantly decreased during the COVID-19 outbreak compared to pre-COVID-19 and to the same period in 2019, especially those for respiratory failure. Further studies are needed to identify associated factors and new prevention strategies.

Project description:BackgroundAssessment of preparedness of weaning has been recommended before extubation for mechanically ventilated patients. We aimed to understand the association of a structured assessment of weaning preparedness with successful liberation.MethodsWe retrospectively investigated patients with acute respiratory failure who experienced an extubation trial at the medical intensive care units of a medical center and compared the demographic and clinical characteristics between those patients with successful and failed extubation. A composite score to assess the preparedness of weaning, the WEANSNOW score, was generated consisting of eight components, including Weaning parameters, Endotracheal tube, Arterial blood gas analysis, Nutrition, Secretions, Neuromuscular-affecting agents, Obstructive airway problems and Wakefulness. The prognostic ability of the WEANSNOW score for extubation was then analyzed.ResultsOf the 205 patients included, 138 (67.3%) patients had successful extubation. Compared with the failure group, the success group had a significantly shorter duration of MV before the weaning attempt (11.2 ± 11.6 vs. 31.7 ± 26.2 days, p < 0.001), more with congestive heart failure (42.0% vs. 25.4%, p = 0.020), and had different distribution of the types of acute respiratory failure (p = 0.037). The failure group also had a higher WEANSNOW score (1.22 ± 0.85 vs. 0.51 ± 0.71, p < 0.001) and worse Rapid Shallow Breathing Index (93.9 ± 63.8 vs. 56.3 ± 35.1, p < 0.001). Multivariate logistic regression analysis showed that a WEANSNOW Score = 1 or higher (OR = 2.880 (95% CI [1.291-6.426]), p = 0.010) and intubation duration >21 days (OR = 7.752 (95% CI [3.560-16.879]), p < 0.001) were independently associated with an increased probability of extubation failure.ConclusionAssessing the pre-extubation status of intubated patients in a checklist-based approach using the WEANSNOW score might provide valuable insights into extubation failure in patients in a medical ICU for acute respiratory failure. Further prospective studies are warranted to elucidate the practice of assessing weaning preparedness.

Dataset Information

Revisiting Unplanned Endotracheal Extubation and Disease Severity in Intensive Care Units.

Publications

Revisiting Unplanned Endotracheal Extubation and Disease Severity in Intensive Care Units.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets