Gender Differences in Prolonged Mechanical Ventilation Patients - A Retrospective Observational Study

Development of a machine learning model for prediction of the duration of unassisted spontaneous breathing in patients during prolonged weaning from mechanical ventilation

PURPOSE

Treatment of patients undergoing prolonged weaning from mechanical ventilation includes repeated spontaneous breathing trials (SBTs) without respiratory support, whose duration must be balanced critically to prevent over- and underload of respiratory musculature. This study aimed to develop a machine learning model to predict the duration of unassisted spontaneous breathing.

MATERIALS AND METHODS

Structured clinical data of patients from a specialized weaning unit were used to develop (1) a classifier model to qualitatively predict an increase of duration, (2) a regressor model to quantitatively predict the precise duration of SBTs on the next day, and (3) the duration difference between the current and following day. 61 features, known to influence weaning, were included into a Histogram-based gradient boosting model. The models were trained and evaluated using separated data sets.

RESULTS

18.948 patient-days from 1018 individual patients were included. The classifier model yielded an ROC-AUC of 0.713. The regressor models displayed a mean absolute error of 2:50 h for prediction of absolute durations and 2:47 h for day-to-day difference.

CONCLUSIONS

The developed machine learning model showed informed results when predicting the spontaneous breathing capacity of a patient in prolonged weaning, however lacking prognostic quality required for direct translation to clinical use.

Sex difference in the risk of extubation failure in ICUs

BACKGROUND

Little attention has been paid to potential differences in prognosis between mechanically ventilated males and females in intensive care units (ICUs). We hypothesized that a sex gap in the risk of extubation failure in ICUs may exist.

METHODS

Post hoc analysis of a large-scale clinical trial including patients at high risk of extubation failure in ICUs, with the aim of assessing the risk of extubation failure according to sex. The primary outcome was reintubation within the 7 days following extubation.

RESULTS

Out of 641 patients, 425 (66%) were males and 216 (34%) were females. Males were more likely to be admitted for cardiac arrest and to have underlying ischemic heart disease whereas females were more likely to be admitted for coma and to have obesity. Whereas the rate of reintubation at 48 h was significantly higher in males than in females (11.0% vs. 6.0%; difference, + 5.0 [95% CI, 0.2 to 9.2]; P = 0.038), the rate of reintubation at day 7 did not significantly differ between males and females (16.7% vs. 11.1%; difference, + 5.6% [95%CI, - 0.3 to 10.8], P = 0.059). Using multivariable logistic regression analysis, male sex was independently associated with reintubation within the 7 days following extubation (adjusted OR 1.70 [95% CI, 1.01 to 2.89]; P = 0.048), even after adjustment on reason for admission, body-mass index, severity score, respiratory rate before extubation, and noninvasive ventilation after extubation.

CONCLUSION

In this post hoc analysis of a clinical trial including a homogeneous subset of patients at high risk of extubation failure, sex was independently associated with reintubation. The role of sex on outcomes should be systematically examined in future studies of critically ill patients.