Predictors for extubation failure in COVID-19 patients using a machine learning approach

Abstract

Introduction Determining the optimal timing for extubation can be challenging in the intensive care. In this study, we aim to identify predictors for extubation failure in critically ill patients with COVID-19. Methods We used highly granular data from 3464 adult critically ill COVID patients in the multicenter Dutch Data Warehouse, including demographics, clinical observations, medications, fluid balance, laboratory values, vital signs, and data from life support devices. All intubated patients with at least one extubation attempt were eligible for analysis. Transferred patients, patients admitted for less than 24 h, and patients still admitted at the time of data extraction were excluded. Potential predictors were selected by a team of intensive care physicians. The primary and secondary outcomes were extubation without reintubation or death within the next 7 days and within 48 h, respectively. We trained and validated multiple machine learning algorithms using fivefold nested cross-validation. Predictor importance was estimated using Shapley additive explanations, while cutoff values for the relative probability of failed extubation were estimated through partial dependence plots. Results A total of 883 patients were included in the model derivation. The reintubation rate was 13.4% within 48 h and 18.9% at day 7, with a mortality rate of 0.6% and 1.0% respectively. The grandient-boost model performed best (area under the curve of 0.70) and was used to calculate predictor importance. Ventilatory characteristics and settings were the most important predictors. More specifically, a controlled mode duration longer than 4 days, a last fraction of inspired oxygen higher than 35%, a mean tidal volume per kg ideal body weight above 8 ml/kg in the day before extubation, and a shorter duration in assisted mode (< 2 days) compared to their median values. Additionally, a higher C-reactive protein and leukocyte count, a lower thrombocyte count, a lower Glasgow coma scale and a lower body mass index compared to their medians were associated with extubation failure. Conclusion The most important predictors for extubation failure in critically ill COVID-19 patients include ventilatory settings, inflammatory parameters, neurological status, and body mass index. These predictors should therefore be routinely captured in electronic health records.

Machine learning to predict intubation in COVID-19 patients

“…On the other hand, several studies have shown lately that patients with COVID-19 infection and neurological comorbidities and illnesses such as history of prior strokes and cerebrovascular events, are more likely to be intubated, as the neurological status of these patients is considered to be a strong predictor of adverse health effects [25,26]. Moreover, Glasgow coma scale, responsible for evaluating the degree of consciousness and brain damage in patients with COVID-19 infection, is considered to be a predictor for intubation [27]. A deviation in the Glasgow coma scale score in patients with COVID-19 infection was significantly correlated to death [28].…”

Effect of high-flow oxygen versus T-piece ventilation strategies during spontaneous breathing trials on weaning failure among patients receiving mechanical ventilation: a randomized controlled trial

“…FiO 2 was set as 0.4, and flow was set at 60 L/min to gain the maximum benefit from high-flow oxygen device [15,19]. To minimize the effects of oxygenation on the weaning failure, FiO 2 level was set at 0.4 in both groups [1,17,20]. In both groups, SBT was performed for 30-60 min (or less in case of clinical intolerance).…”

Inspiratory and peripheral muscle strength as predictors for extubation failure in COVID-19 patients

“…With great interest, I read the article by Fleuren et al on determining the predictors for extubation failure in COVID-19 patients [ 1 ]. The authors have methodically utilised the machine learning models to identify the potential parameters that would predict the extubation failure in critically ill COVID-19 patients.…”