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

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 Pao2:Fio2 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), Pao2:Fio2 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.

Tracheostomy, ventilatory wean, and decannulation in COVID-19 patients.

PURPOSE: COVID-19 patients requiring mechanical ventilation can overwhelm existing bed capacity. We aimed to better understand the factors that influence the trajectory of tracheostomy care in this population to facilitate capacity planning and improve outcomes. METHODS: We conducted an observational cohort study of patients in a high-volume centre in the worst-affected region of the UK including all patients that underwent tracheostomy for COVID-19 pneumonitis ventilatory wean from 1st March 2020 to 10th May 2020. The primary outcome was time from insertion to decannulation. The analysis utilised Cox regression to account for patients that are still progressing through their tracheostomy pathway. RESULTS: At the point of analysis, a median 21 days (IQR 15-28) post-tracheostomy and 39 days (IQR 32-45) post-intubation, 35/69 (57.4%) patients had been decannulated a median of 17 days (IQR 12-20.5) post-insertion. The overall median age was 55 (IQR 48-61) with a male-to-female ratio of 2:1. In Cox regression analysis, FiO2 at tracheostomy ≥ 0.4 (HR 1.80; 95% CI 0.89-3.60; p = 0.048) and last pre-tracheostomy peak cough flow (HR 2.27; 95% CI 1.78-4.45; p = 0.001) were independent variables associated with prolonged time to decannulation. CONCLUSION: Higher FiO2 at tracheostomy and higher pre-tracheostomy peak cough flow are associated with increased delay in COVID-19 tracheostomy patient decannulation. These finding comprise the most comprehensive report of COVID-19 tracheostomy decannulation to date and will assist service planning for future peaks of this pandemic.

Recommendation of a practical guideline for safe tracheostomy during the COVID-19 pandemic.

PURPOSE: The COVID-19 pandemic is placing unprecedented demand upon critical care services for invasive mechanical ventilation. There is current uncertainty regarding the role of tracheostomy for weaning ventilated patients with COVID-19 pneumonia. This is due to a number of factors including prognosis, optimal healthcare resource utilisation, and safety of healthcare workers when performing such a high-risk aerosol-generating procedure. METHODS: Literature review and proposed practical guideline based on the experience of a tertiary healthcare institution with 195 critical care admissions for COVID-19 up until 4th April 2020. RESULTS: A synthesis of the current international literature and reported experience is presented with respect to prognosis, viral load and staff safety, thus leading to a pragmatic recommendation that tracheostomy is not performed until at least 14 days after endotracheal intubation in COVID-19 patients. Practical steps to minimise aerosol generation in percutaneous tracheostomy are outlined and we describe the process and framework for setting up a dedicated tracheostomy team. CONCLUSION: In selected COVID-19 patients, there is a role for tracheostomy to aid in weaning and optimise healthcare resource utilisation. Both percutaneous and open techniques can be performed safely with careful modifications to technique and appropriate enhanced personal protective equipment. ORL-HNS surgeons can play a valuable role in forming tracheostomy teams to support critical care teams during this global pandemic.