Timing of Tracheostomy for Prolonged Respiratory Wean in Critically Ill Coronavirus Disease 2019 Patients: A Machine Learning Approach

Abstract

Objectives: To propose the optimal timing to consider tracheostomy insertion for weaning of mechanically ventilated patients recovering from coronavirus disease 2019 pneumonia. We investigated the relationship between duration of mechanical ventilation prior to tracheostomy insertion and in-hospital mortality. In addition, we present a machine learning approach to facilitate decision-making. Design: Prospective cohort study. Setting: Guy’s & St Thomas’ Hospital, London, United Kingdom. Patients: Consecutive patients admitted with acute respiratory failure secondary to coronavirus disease 2019 requiring mechanical ventilation between March 3, 2020, and May 5, 2020. Interventions: Baseline characteristics and temporal trends in markers of disease severity were prospectively recorded. Tracheostomy was performed for anticipated prolonged ventilatory wean when levels of respiratory support were favorable. Decision tree was constructed using C4.5 algorithm, and its classification performance has been evaluated by a leave-one-out cross-validation technique. Measurements and Main Results: One-hundred seventy-six patients required mechanical ventilation for acute respiratory failure, of which 87 patients (49.4%) underwent tracheostomy. We identified that optimal timing for tracheostomy insertion is between day 13 and day 17. Presence of fibrosis on CT scan (odds ratio, 13.26; 95% CI [3.61–48.91]; p ≤ 0.0001) and Pao 2:Fio 2 ratio (odds ratio, 0.98; 95% CI [0.95–0.99]; p = 0.008) were independently associated with tracheostomy insertion. Cox multiple regression analysis showed that chronic obstructive pulmonary disease (hazard ratio, 6.56; 95% CI [1.04–41.59]; p = 0.046), ischemic heart disease (hazard ratio, 4.62; 95% CI [1.19–17.87]; p = 0.027), positive end-expiratory pressure (hazard ratio, 1.26; 95% CI [1.02–1.57]; p = 0.034), Pao 2:Fio 2 ratio (hazard ratio, 0.98; 95% CI [0.97–0.99]; p = 0.003), and C-reactive protein (hazard ratio, 1.01; 95% CI [1–1.01]; p = 0.005) were independent late predictors of in-hospital mortality. Conclusions: We propose that the optimal window for consideration of tracheostomy for ventilatory weaning is between day 13 and 17. Late predictors of mortality may serve as adverse factors when considering tracheostomy, and our decision tree provides a degree of decision support for clinicians.

Systematic review and meta-analysis of tracheostomy outcomes in COVID-19 patients

“…Of these, 46 studies met inclusion criteria. 7 further studies were removed with shared data, leaving 39 studies for meta-analysis 16 , 17 , 18 , 19 , 20 , 21 , 22 .

Fig.

…”

Outcomes of tracheostomy in COVID-19 patients in National Guard Health Affairs, Riyadh, Saudi Arabia

“…8 A study of 87 tracheostomized patients did find that only 7 died after receiving a tracheostomy. 11 However, the present study had a higher rate of mortality as 25 patients died after receiving a tracheostomy; COVID-19 related issues caused the majority of the cases. Moreover, the present study showed that an uptrending CRP level was the only factor significantly associated with mortality.…”

“…This finding was in agreement with another study that concluded that both CRP and PEEP levels were independently associated with mortality in tracheostomized patients. 11 Study limitations. The study population comprised patients from a single hospital in Riyadh, Saudi Arabia.…”

Do Mechanically Ventilated COVID-19 Patients Present a Higher Case-Fatality Rate Compared With Other Infectious Respiratory Pandemics? A Systematic Review and Meta-Analysis

“…Finally, a total of 61 peer-reviewed studies were included in the final analysis (Fig. 1A) 10,12,13,21–78 . Of these final 61 studies, 11 studies were conducted in China, 3 were conducted in America (2 studies from South America and 1 study from Central America), 17 involved centers in the United States, 16 involved centers in Europe, 3 involved centers in Canada, 9 involved centers in Asia, and 2 were based on multinational collaborations (one was between the United Kingdom and Ireland, and the second was between the United States, Europe, Canada, and Japan).…”