Predictors of Prolonged Mechanical Ventilation After On-pump Coronary Artery Bypass Grafting

Natarajan, Kanagarajan; Patil, Sachin; Lesley, Nancy; Ninan, Benjamin

doi:10.4103/0971-9784.37894

Cited by 18 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(11,16,29,42) The studies outlined in Table 3 incorporated traditional statistical modeling to evaluate predictors of PMV; however, the majority of studies that evaluated medication use found that variable nonsignificant in multivariate analysis. (28,31,33,37) Notably, one study evaluating use of common sedatives, vasopressors, steroids, and neuromuscular blocking agents found the duration of vasopressor support to be an independent predictor of PMV. (11)…”

Section: Discussionmentioning

confidence: 99%

“…Following a literature review of prolonged mechanical ventilation in the ICU, a total of 30 potential predictor variables were identified by investigator consensus to include in each PMV regression model. (5,10,26–33) These variables included the following: 1) ICU baseline: age, sex, admission to medical ICU, and primary ICU admission diagnosis (cardiac, chronic kidney disease, heart failure, hepatic, pulmonary, sepsis, trauma); 2) 24 hours after ICU admission: APACHE II and SOFA score (using worst values in the 24 hour period); presence of acute kidney injury; 3) Flowsheet and laboratory values at time of intubation: duration of oxygen support devices prior to intubation, pulse, arterial blood gas values, and ventilator settings (positive end expiratory pressure (PEEP) and fraction of inspired oxygen (FiO 2 ); fluid overload. The fourth category was added to assess the role of medications at 24 hours and included: MRC-ICU score at 24 hours after ICU admission, time of intubation, and 24 hours after intubation, dichotomized MRC-ICU less than or greater than or equal to 10 at the same three time points, and certain medications (bumetanide, clonazepam, dexamethasone, dexmedetomidine, dobutamine, ertapenem, lorazepam, norepinephrine) selected by the investigators following univariate analysis.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Machine learning based prediction of prolonged duration of mechanical ventilation incorporating medication data

Sikora,

Zhao,

Kong

et al. 2023

Preprint

View full text Add to dashboard Cite

Rationale: Duration of mechanical ventilation is associated with adverse outcomes in critically ill patients and increased use of resources. The increasing complexity of medication regimens has been associated with increased mortality, length of stay, and fluid overload but has never been studied specifically in the setting of mechanical ventilation. Objective: The purpose of this analysis was to develop prediction models for mechanical ventilation duration to test the hypothesis that incorporating medication data may improve model performance. Methods: This was a retrospective cohort study of adults admitted to the ICU and undergoing mechanical ventilation for longer than 24 hours from October 2015 to October 2020. Patients were excluded if it was not their index ICU admission or if the patient was placed on comfort care in the first 24 hours of admission. Relevant patient characteristics including age, sex, body mass index, admission diagnosis, morbidities, vital signs measurements, severity of illness, medication regimen complexity as measured by the MRC-ICU, and medical treatments before intubation were collected. The primary outcome was area under the receiver operating characteristic (AUROC) of prediction models for prolonged mechanical ventilation (defined as greater than 5 days). Both logistic regression and supervised learning techniques including XGBoost, Random Forest, and Support Vector Machine were used to develop prediction models. Results: The 318 patients [age 59.9 (SD 16.9), female 39.3%, medical 28.6%] had mean 24-hour MRC-ICU score of 21.3 (10.5), mean APACHE II score of 21.0 (5.4), mean SOFA score of 9.9 (3.3), and ICU mortality rate of 22.6% (n=72). The strongest performing logistic model was the base model with MRC-ICU added, with AUROC of 0.72, positive predictive value (PPV) of 0.83, and negative prediction value (NPV) of 0.92. The strongest overall model was Random Forest with an AUROC of 0.78, a PPV of 0.53, and NPV of 0.90. Feature importance analysis using support vector machine and Random Forest revealed severity of illness scores and medication related data were the most important predictors. Conclusions: Medication regimen complexity is significantly associated with prolonged duration of mechanical ventilation in critically ill patients, and prediction models incorporating medication information showed modest improvement in this prediction.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Machine learning based prediction of prolonged duration of mechanical ventilation incorporating medication data

Sikora,

Zhao,

Kong

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Of those, 8 were also excluded due to the incompleteness of the data and contents. 15 articles were eligible for the final analysis[ 6 9 10 11 12 13 14 15 16 17 18 19 20 21 22 ] [ Table 1 ].…”

Section: Methodsmentioning

confidence: 99%

The Overall Prevalence and Main Determinants of Prolonged Mechanical Ventilation in Patients Undergoing Coronary Artery Bypass Grafting

Shahsanaei,

Behrooj,

Petrudi

et al. 2023

Heart Views

View full text Add to dashboard Cite

Background: Although respiratory support is necessary to maintain hemodynamic stability in patients undergoing major surgeries, prolonging the time of mechanical ventilation is considered a major complication following these procedures. The identification of potential factors related to this phenomenon should be identified. In the present systematic review, we first assess the pooled prevalence of prolonged mechanical ventilation (PMV) in patients undergoing coronary artery bypass grafting (CABG) surgery and also determine the main predictors for PMV by deeply reviewing the literature. Materials and Methods: The manuscript databases including Medline, Web of Knowledge, Google Scholar, Scopus, and Cochrane were deeply searched by the two blinded investigators for all eligible studies based on the relevant keywords. Based on the titles and abstracts, 88 records were initially included and of those, 15 articles were eligible for the final analysis. Results: The pooled prevalence of PMV in the studies that defined PMV as ventilation >24 h was 6.5% (95% confidence interval [CI]: 4.1%–10.2%) and in the studies, PMV as ventilation >48 h was 2.8% (95% CI: 1.7%–4.7%). Demographics (gender and advanced age), obesity, underlying comorbidities (hypertension, chronic kidney disease, cerebrovascular accident, high New York Heart Association class, history of chronic obstructive pulmonary disease, and history of acute coronary syndrome), emergency surgery, intraoperative characteristics (needing intra-aortic balloon pump, increased peak airway pressure, using cardiopulmonary bypass, the type of dose of anesthetics, cross-clamp time, increased units of blood transfusion, occurring cardiac ischemic events within an operation, fluid imbalance, and some anastomoses), and some postoperative outcome such as lowering O2 saturation, sequential organ failure assessment score, inotrope use, pleural effusion, delirium, and prolonged intensive care unit stay were found to be the main determinants for PMV. Conclusion: Depending on the definition of PMV, the prevalence of PMV varied from 1.7% to 10.2%. Various factors before, during, and after surgery are the predictors of PMV in these patients, which can be used to design new scoring systems to predict it.

show abstract

Development and validation of a clinical prediction model for early ventilator weaning in post-cardiac surgery

Xie,

Wang,

Lin

et al. 2024

Heliyon

View full text Add to dashboard Cite

Predictors of Prolonged Mechanical Ventilation After On-pump Coronary Artery Bypass Grafting

Cited by 18 publications

References 0 publications

Machine learning based prediction of prolonged duration of mechanical ventilation incorporating medication data

Machine learning based prediction of prolonged duration of mechanical ventilation incorporating medication data

The Overall Prevalence and Main Determinants of Prolonged Mechanical Ventilation in Patients Undergoing Coronary Artery Bypass Grafting

Development and validation of a clinical prediction model for early ventilator weaning in post-cardiac surgery

Contact Info

Product

Resources

About