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.

Download Full-text

APHACHE Score as a Predictive Indices for Weanability from Mechanical Ventilation

Bangladesh Critical Care Journal ◽

10.3329/bccj.v1i1.14360 ◽

2013 ◽

Vol 1 (1) ◽

pp. 18-22 ◽

Cited By ~ 2

Author(s):

Md Sayedul Islam

Keyword(s):

Mechanical Ventilation ◽

Respiratory Failure ◽

Private Hospital ◽

Total Duration ◽

Apache Ii ◽

Apache Ii Score ◽

P Value ◽

Apache Score ◽

Number Of Patients ◽

Weaning Outcome

Objective: To determine the significance of acute physiology and chronic health evaluation (APACHE) score as an important parameter of weaning outcome for mechanical ventilation. Design: prospective, observational. Setting: The medical ICU of a modernized private hospital, Dhaka. Method: The study was carried out during the period of 2008 to 2009 in a specialized private hospital Dhaka. Critical care physicians were asked to filled up the data sheets having detail problem of the patients including the APACHE II score. The APACHE II score is divided into three steps High score>25, Medium score 20-24 and Low score < 20. The clinicians were suggested to predict whether it would take < 3 days or 4to 7days or >8days to wean each patients from mechanical ventilation. The cause of respiratory failure and total duration of weaning were recorded. The significance was set at p<.05. Result: Total number of patients included in this study were 40. Male were 22 (55%) and female were 18 (45%), the mean age of the patients were 51.1±13.9. The most common cause of respiratory failure were COPD 11(24.5%) and next common were pneumonia and ARDS due to sepsis 8 (20%) each. Among the studied population 20 (50%) having low APACHE score (<20), 12 (30%) were medium score (20-24) and 8 (20%) patients were high score (>25). Total 25 (62.5%) of the patients were successfully weaned from mechanical ventilation, 10 (25%) of the patient died and 5 (12.5%) of the patent were shifted to other low cost hospital. The successfully weaned groups 17 (68%) had lower APACHE II score than the unsuccessfully (failure) group which were statistically significant ÷2 =.8546, df =2, p-value >.005. Conclusions: The overall severity of illness as assessed by APACHE II score correlates better with weaning outcome. DOI: http://dx.doi.org/10.3329/bccj.v1i1.14360 Bangladesh Crit Care J March 2013; 1: 18-22

Download Full-text

Explainable Machine Learning to Predict Successful Weaning Among Patients Requiring Prolonged Mechanical Ventilation: A Retrospective Cohort Study in Central Taiwan

Frontiers in Medicine ◽

10.3389/fmed.2021.663739 ◽

2021 ◽

Vol 8 ◽

Author(s):

Ming-Yen Lin ◽

Chi-Chun Li ◽

Pin-Hsiu Lin ◽

Jiun-Long Wang ◽

Ming-Cheng Chan ◽

...

Keyword(s):

Machine Learning ◽

Mechanical Ventilation ◽

Prediction Model ◽

Prolonged Mechanical Ventilation ◽

Number Of Patients ◽

Extreme Gradient Boosting ◽

Feature Importance ◽

Successful Weaning ◽

Central Taiwan ◽

Weaning Outcome

Objective: The number of patients requiring prolonged mechanical ventilation (PMV) is increasing worldwide, but the weaning outcome prediction model in these patients is still lacking. We hence aimed to develop an explainable machine learning (ML) model to predict successful weaning in patients requiring PMV using a real-world dataset.Methods: This retrospective study used the electronic medical records of patients admitted to a 12-bed respiratory care center in central Taiwan between 2013 and 2018. We used three ML models, namely, extreme gradient boosting (XGBoost), random forest (RF), and logistic regression (LR), to establish the prediction model. We further illustrated the feature importance categorized by clinical domains and provided visualized interpretation by using SHapley Additive exPlanations (SHAP) as well as local interpretable model-agnostic explanations (LIME).Results: The dataset contained data of 963 patients requiring PMV, and 56.0% (539/963) of them were successfully weaned from mechanical ventilation. The XGBoost model (area under the curve [AUC]: 0.908; 95% confidence interval [CI] 0.864–0.943) and RF model (AUC: 0.888; 95% CI 0.844–0.934) outperformed the LR model (AUC: 0.762; 95% CI 0.687–0.830) in predicting successful weaning in patients requiring PMV. To give the physician an intuitive understanding of the model, we stratified the feature importance by clinical domains. The cumulative feature importance in the ventilation domain, fluid domain, physiology domain, and laboratory data domain was 0.310, 0.201, 0.265, and 0.182, respectively. We further used the SHAP plot and partial dependence plot to illustrate associations between features and the weaning outcome at the feature level. Moreover, we used LIME plots to illustrate the prediction model at the individual level. Additionally, we addressed the weekly performance of the three ML models and found that the accuracy of XGBoost/RF was ~0.7 between weeks 4 and week 7 and slightly declined to 0.6 on weeks 8 and 9.Conclusion: We used an ML approach, mainly XGBoost, SHAP plot, and LIME plot to establish an explainable weaning prediction ML model in patients requiring PMV. We believe these approaches should largely mitigate the concern of the black-box issue of artificial intelligence, and future studies are warranted for the landing of the proposed model.

Download Full-text

Clinical features and predictors of severity in COVID-19 patients with critical illness in Singapore

Scientific Reports ◽

10.1038/s41598-021-81377-3 ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Ser Hon Puah ◽

◽

Barnaby Edward Young ◽

Po Ying Chia ◽

Vui Kian Ho ◽

...

Keyword(s):

Mechanical Ventilation ◽

Clinical Features ◽

Operating Characteristic ◽

Characteristic Curve ◽

Case Series ◽

Plateau Pressure ◽

Apache Ii Score ◽

Multivariable Logistic Regression Model ◽

Reactive Protein ◽

Ventilatory Management

AbstractWe aim to describe a case series of critically and non-critically ill COVID-19 patients in Singapore. This was a multicentered prospective study with clinical and laboratory details. Details for fifty uncomplicated COVID-19 patients and ten who required mechanical ventilation were collected. We compared clinical features between the groups, assessed predictors of intubation, and described ventilatory management in ICU patients. Ventilated patients were significantly older, reported more dyspnea, had elevated C-reactive protein and lactate dehydrogenase. A multivariable logistic regression model identified respiratory rate (aOR 2.83, 95% CI 1.24–6.47) and neutrophil count (aOR 2.39, 95% CI 1.34–4.26) on admission as independent predictors of intubation with area under receiver operating characteristic curve of 0.928 (95% CI 0.828–0.979). Median APACHE II score was 19 (IQR 17–22) and PaO2/FiO2 ratio before intubation was 104 (IQR 89–129). Median peak FiO2 was 0.75 (IQR 0.6–1.0), positive end-expiratory pressure 12 (IQR 10–14) and plateau pressure 22 (IQR 18–26) in the first 24 h of ventilation. Median duration of ventilation was 6.5 days (IQR 5.5–13). There were no fatalities. Most COVID-19 patients in Singapore who required mechanical ventilation because of ARDS were extubated with no mortality.

Download Full-text

Assessment of Outcome over a 10-year Period of Patients Admitted to a Multidisciplinary Adult Intensive Care Unit with Haematological and Solid Tumours

Anaesthesia and Intensive Care ◽

10.1177/0310057x0503300105 ◽

2005 ◽

Vol 33 (1) ◽

pp. 26-35 ◽

Cited By ~ 20

Author(s):

J. L. Moran ◽

P. J. Solomon ◽

P. J. Williams

Keyword(s):

Mechanical Ventilation ◽

Cox Model ◽

Severity Of Illness ◽

Cohort Effect ◽

Solid Tumours ◽

Apache Ii ◽

Apache Ii Score ◽

Adult Intensive Care Unit ◽

Icu Admission ◽

Over Time

The risk factors for time to mortality, censored at 30 days, of patients admitted to an adult teaching hospital ICU with haematological and solid malignancies were assessed in a retrospective cohort study. Patients, demographics and daily ICU patient data, from admission to day 8, were identified from a prospective computerized database and casenote review in consecutive admissions to ICU with haematological and solid tumours over a 10-year period (1989–99). The cohort, 108 ICU admissions in 89 patients was of mean age (±SD) 55±14 years; 43% were female. Patient diagnoses were leukaemia (35%), lymphoma (38%) and solid tumours (27%). Median time from hospital to ICU admission was five days (range 0–67). On ICU admission, 50% had septic shock and first day APACHE II score was 28±9. Forty-six per cent of patients were ventilated. ICU and 30-day mortality were 39% and 54% respectively. Multivariate Cox model predictors (P<0.05), using only ICU admission day data were: Charlson comorbidity index (CCI), time to ICU admission (days) and mechanical ventilation. For daily data (admission through day 8), predictors were: cohort effect (2nd vs 1st five-year period); CCI; time to ICU admission (days); APACHE II score and mechanical ventilation. Outcomes were considered appropriate for severity of illness and demonstrated improvement over time. Ventilation was an independent outcome determinant. Controlling for other factors, mortality has improved over time (1st vs 2nd five year period). Analysis restricted to admission data alone may be insensitive to particular covariate effects.

Download Full-text

Clinical Characteristics in Patients with Hospital-Acquired Pneumonia Caused by Extensively Drug-Resistant Acinetobacter baumannii, A Multicenter Retrospective Study

10.21203/rs.3.rs-116166/v1 ◽

2020 ◽

Author(s):

Yujun Li ◽

Xiaomei Huang ◽

Yuyao Wang ◽

Chuzhi Pan ◽

Zexun Mo ◽

...

Keyword(s):

Risk Factors ◽

Mechanical Ventilation ◽

Hospital Mortality ◽

Apache Ii ◽

Apache Ii Score ◽

Drug Resistant ◽

Central Venous ◽

Hospital Acquired Pneumonia ◽

Hospital Acquired ◽

Lactamase Inhibitor

Abstract Background Extremely drug-resistant (XDR) Acinetobacter baumannii （A. baumannii）has been of a great concern. The relationship between XDR and patient outcomes remains unclear. We investigated the clinical features, risk factors, and outcomes of Hospital-acquired pneumonia (HAP)caused by XDR A. baumannii. Methods A multicenter retrospective case-control study was performed to determine factors associated with XDR A. baumannii pneumonia from 5 teaching hospitals in Guangzhou, China. Results 76 patients were enrolled in the study. XDR A. baumannii pneumonia patients were tend to be smoker (11.9% vs 3.9%, P = 0.130) and older (76.5±11.2 vs 70.3±16.4, P = 0.007) and had more comorbid diseases including chronic obstructive pulmonary disease (COPD) (48.7% vs 21.1%, P = 0.001) and renal failure (21.1% vs 3.9%, P = 0.002) and had higher APACHE II score (65.8% vs 47.4%, P = 0.033). Invasive procedures including insertion of urinary catheter, nasogastric tube, central venous/arterial catheter, bronchoscopy and mechanical ventilation along with using β-lactam/β-lactamase inhibitor and carbapenem were also risk factors for XDR A. baumannii pneumonia. Multivariate analysis showed the APACHE II score >=20 (OR, 2.1; 95% CI: 1.1–4.1, P = 0.023), COPD (OR, 9.6; 95% CI: 2.0–45.5, P = 0.004), central venous/arterial catheter placement (OR,11.5; 95% CI: 1.1-117.8, P = 0.040), low albumin levels (OR, 1.2; 95% CI: 1.1-1.4, P = 0.001) and using β-lactam/β-lactamase inhibitor (OR,15.9; 95% CI: 2.7-94.2, P = 0.002) were independent risk factors for XDR A. baumannii pneumonia. Compared with the non-XDR A. baumannii patients, the XDR A. baumannii pneumonia increased length of mechanical ventilation (11.1±12.3 vs 5.1±5.6, P = 0.000), hospital stay (42.2±24.3 vs 34.8±18.0, P = 0.036) and ICU (Intensive Care Unit) stay (27.5±19.0 vs 20.0±20.5, P = 0.020), but it did not increase in-hospital mortality (47.4% vs 32.9%, P = 0.137). Conclusions XDR A. baumannii pneumonia was strongly related to systemic illnesses, invasive procedure, low albumin levels and the APACHE II score and increasing the length of mechanical ventilation and hospital stay. But it did not increase in-hospital mortality.

Download Full-text

Analysis of Factors Affecting the Weaning of Mechanical Ventilation at ICU RSUD Prof.Dr.Margono Soekarjo Purwokerto

Padjadjaran Acute Care Nursing Journal ◽

10.24198/pacnj.v1i1.23981 ◽

2019 ◽

Vol 1 (1) ◽

Author(s):

Etika Emaliyawati ◽

Esti Dwi Anani ◽

Ayu Prawesti

Keyword(s):

Mechanical Ventilation ◽

Hospital Costs ◽

Sampling Technique ◽

Influential Factor ◽

Apache Ii ◽

Apache Ii Score ◽

Cross Sectional ◽

Weaning Failure ◽

Ventilation Weaning ◽

Mechanical Ventilation Weaning

The weaning of mechanical ventilation is a complex process and depends on many factors. The failure to wean mechanical ventilation may lead to prolonged duration of mechanical ventilation, which may increase the risk of ventilator associated pneumonia (VAP), morbidity, mortality, increased hospital costs and lower quality of hospital services. In the year 2016, in ICU RSUD Prof.Dr.Margono Soekarjo Purwokerto, in average there is a 20% failure of mechanical ventilation, if not followed up will adversely affect the patient. Factors investigated in this study included patient, nurses, collaboration and organization. The purpose of this study is to analyze the factors that affect implementation of the weaning of mechanical ventilation in ICU Room Prof.Dr.Margono Soekarjo General Hospital Purwokerto.The method used in this research was descriptive quantitative analytic design with cross sectional approach on 47 mechanical ventilation weaning activities. The sample selection was conducted by accidental sampling technique. Measurements for nurses were carried out using validated values including knowledge, experience and collaboration. While the observation sheet included the implementation of standard operating procedures for mechanical ventilation weaning, collaboration, patients APACHE II score and weaning results.The result of bivariate test showed that there were influence of patient (0.000), nurse (0,021), collaboration (0,024) and organization (0,011) to mechanical ventilation weaning activity. The result of logistic regression test showed that the patient was the most influential factor on mechanical ventilation weaning activity with 87% probability.Nurses should pay more attention to patients especially with high APACHE II scores (≥20) because of the risk of mechanical ventilation weaning failure. Assessment of weaning readiness must be carried out daily with appropriate assessment. While hospitals need to revise policies on mechanical ventilation weaning procedure and continue education and training programme related to patients criticality and collaboration.

Download Full-text

Effect Of Renal Failure On Weaning Outcome In Patients Requiring Prolonged Mechanical Ventilation

10.1164/ajrccm-conference.2011.183.1_meetingabstracts.a3200 ◽

2011 ◽

Author(s):

Matthew J. Baugh ◽

Lisa A. Duffner ◽

Eileen G. Collins ◽

Leslie Hoffman ◽

Dorothy M. Lanuza ◽

...

Keyword(s):

Mechanical Ventilation ◽

Renal Failure ◽

Prolonged Mechanical Ventilation ◽

Weaning Outcome

Download Full-text

Feasibility, tolerance and effectiveness of enteral feeding in critically ill patients in prone position

Journal of the Intensive Care Society ◽

10.1177/1751143719900100 ◽

2020 ◽

pp. 175114371990010 ◽

Cited By ~ 1

Author(s):

Raymond Dominic Savio ◽

Rajalakshmi Parasuraman ◽

Daphnee Lovesly ◽

Bhuvaneshwari Shankar ◽

Lakshmi Ranganathan ◽

...

Keyword(s):

Mechanical Ventilation ◽

Enteral Nutrition ◽

Critically Ill ◽

Prone Position ◽

Supine Position ◽

Critically Ill Patients ◽

Invasive Mechanical Ventilation ◽

Apache Ii ◽

Apache Ii Score ◽

The Mean

Aim To assess the feasibility, tolerance and effectiveness of enteral nutrition in critically ill patients receiving invasive mechanical ventilation in the prone position for severe Acute Respiratory Distress Syndrome (ARDS). Methods Prospective observational study conducted in a multidisciplinary critical care unit of a tertiary care hospital from January 2013 until July 2015. All patients with ARDS who received invasive mechanical ventilation in prone position during the study period were included. Patients’ demographics, severity of illness (Acute Physiology and Chronic Health Evaluation (APACHE II) score), baseline markers of nutritional status (subjective global assessment (SGA) and body mass index), details of nutrition delivery during prone and supine hours and outcomes (Length of stay and discharge status) were recorded. Results Fifty-one patients met inclusion criteria out of whom four patients were excluded from analysis since they did not receive any enteral nutrition due to severe hemodynamic instability. The mean age of patients was 46.4 ± 12.9 years, with male:female ratio of 7:3. On admission, SGA revealed moderate malnutrition in 51% of patients and the mean APACHE II score was 26.8 ± 9.2. The average duration of prone ventilation per patient was 60.2 ± 30.7 h. All patients received continuous nasogastric/orogastric feeds. The mean calories (kcal/kg/day) and protein (g/kg/day) prescribed in the supine position were 24.5 ± 3.8 and 1.1 ± 0.2 while the mean calories and protein prescribed in prone position were 23.5 ± 3.6 and 1.1 ± 0.2, respectively. Percentage of prescribed calories received by patients in supine position was similar to that in prone position (83.2% vs. 79.6%; P = 0.12). Patients received a higher percentage of prescribed protein in supine compared to prone position (80.8% vs. 75%, P = 0.02). The proportion of patients who received at least 75% of the caloric and protein goals was 37 (78.7%) and 37 (78.7%) in supine and 32 (68.1%) and 21 (44.6%) in prone position. Conclusion In critically ill patients receiving invasive mechanical ventilation in the prone position, enteral nutrition with nasogastric/orogastric feeding is feasible and well tolerated. Nutritional delivery of calories and proteins in prone position is comparable to that in supine position.

Download Full-text

Duration of Mechanical Ventilation in an Adult Intensive Care Unit After Introduction of Sedation and Pain Scales

American Journal of Critical Care ◽

10.4037/ajcc2008.17.4.349 ◽

2008 ◽

Vol 17 (4) ◽

pp. 349-356 ◽

Cited By ~ 21

Author(s):

Teresa Ann Williams ◽

Suzanne Martin ◽

Gavin Leslie ◽

Linda Thomas ◽

Timothy Leen ◽

...

Keyword(s):

Intensive Care Unit ◽

Mechanical Ventilation ◽

Intensive Care ◽

Pain Scale ◽

Apache Ii ◽

Apache Ii Score ◽

Adult Intensive Care Unit ◽

Before And After ◽

Behavioral Pain Scale ◽

Sedation And Analgesia

Background Sedation and analgesia scales promote a less-distressing experience in the intensive care unit and minimize complications for patients receiving mechanical ventilation. Objectives To evaluate outcomes before and after introduction of scales for sedation and analgesia in a general intensive care unit. Method A before-and-after design was used to evaluate introduction of the Richmond Agitation-Sedation Scale and the Behavioral Pain Scale for patients receiving mechanical ventilation. Data were collected for 6 months before and 6 months after training in and introduction of the scales. Results A total of 769 patients received mechanical ventilation for at least 6 hours (369 patients before and 400 patients after implementation). Age, scores on the Acute Physiology and Chronic Health Evaluation (APACHE) II, and diagnostic groups were similar in the 2 groups, but the after group had more men than did the before group. Duration of mechanical ventilation did not change significantly after the scales were introduced (median, 24 vs 28 hours). For patients who received mechanical ventilation for 96 hours or longer (24%), mechanical ventilation lasted longer after implementation of the scales (P =.03). Length of stay in the intensive care unit was similar in the 2 groups (P = .18), but patients received sedatives for longer after implementation (P=.01). By logistic regression analysis, APACHE II score (P <.001) and diagnostic group (P <.001) were independent predictors of mechanical ventilation lasting 96 hours or longer. Conclusion Sedation and analgesia scales did not reduce duration of ventilation in an Australian intensive care unit.

Download Full-text