Erratum to: Do heart and respiratory rate variability improve prediction of extubation outcomes in critically ill patients?

Prediction of extubation outcome in critically ill patients: a systematic review and meta-analysis

BACKGROUND

Extubation failure is an important issue in ventilated patients and its risk factors remain a matter of research. We conducted a systematic review and meta-analysis to explore factors associated with extubation failure in ventilated patients who passed a spontaneous breathing trial and underwent planned extubation. This systematic review was registered in PROPERO with the Registration ID CRD42019137003.

METHODS

We searched the PubMed, Web of Science and Cochrane Controlled Register of Trials for studies published from January 1998 to December 2018. We included observational studies involving risk factors associated with extubation failure in adult intensive care unit patients who underwent invasive mechanical ventilation. Two authors independently extracted data and assessed the validity of included studies.

RESULTS

Sixty-seven studies (involving 26,847 participants) met the inclusion criteria and were included in our meta-analysis. We analyzed 49 variables and, among them, we identified 26 factors significantly associated with extubation failure. Risk factors were distributed into three domains (comorbidities, acute disease severity and characteristics at time of extubation) involving mainly three functions (circulatory, respiratory and neurological). Among these, the physiological respiratory characteristics at time of extubation were the most represented. The individual topic of secretion management was the one with the largest number of variables. By Bayesian multivariable meta-analysis, twelve factors were significantly associated with extubation failure: age, history of cardiac disease, history of respiratory disease, Simplified Acute Physiologic Score II score, pneumonia, duration of mechanical ventilation, heart rate, Rapid Shallow Breathing Index, negative inspiratory force, lower PaO2/FiO2 ratio, lower hemoglobin level and lower Glasgow Coma Scale before extubation, with the latest factor having the strongest association with extubation outcome.

CONCLUSIONS

Numerous factors are associated with extubation failure in critically ill patients who have passed a spontaneous breathing trial. Robust multiparametric clinical scores and/or artificial intelligence algorithms should be tested based on the selected independent variables in order to improve the prediction of extubation outcome in the clinical scenario.

Dynamic data monitoring improves predictive analytics for failed extubation in the ICU

OBJECTIVE

Predictive analytics monitoring that informs clinicians of the risk for failed extubation would help minimize both the duration of mechanical ventilation and the risk of emergency re-intubation in ICU patients. We hypothesized that dynamic monitoring of cardiorespiratory data, vital signs, and lab test results would add information to standard clinical risk factors.

METHODS

We report model development in a retrospective observational cohort admitted to either the medical or surgical/trauma ICU that were intubated during their ICU stay and had available physiologic monitoring data (n  =  1202). The primary outcome was removal of endotracheal intubation (i.e. extubation) followed within 48 h by reintubation or death (i.e. failed extubation). We developed a standard risk marker model based on demographic and clinical data. We also developed a novel risk marker model using dynamic data elements-continuous cardiorespiratory monitoring, vital signs, and lab values.

RESULTS

Risk estimates from multivariate predictive models in the 24 h preceding extubation were significantly higher for patients that failed. Combined standard and novel risk markers demonstrated good predictive performance in leave-one-out validation: AUC of 0.64 (95% CI: 0.57-0.69) and 1.6 alerts per week to identify 32% of extubations that will fail. Novel risk factors added significantly to the standard model.

CONCLUSION

Predictive analytics monitoring models can detect changes in vital signs, continuous cardiorespiratory monitoring, and laboratory measurements in both the hours preceding and following extubation for those patients destined for extubation failure.