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

Arunjit Takhar; Pavol Surda; Imran Ahmad; Nikul Amin; Asit Arora; Luigi Camporota; Poppy Denniston; Kariem El-Boghdadly; Miroslav Kvassay; Denisa Macekova; Michal Munk; David Ranford; Jan Rabcan; Chysostomos Tornari; Duncan Wyncoll; Elena Zaitseva; Nicholas Hart; Stephen Tricklebank

doi:10.1097/CCE.0000000000000279

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

Arunjit Takhar, Pavol Surda, Imran Ahmad, Nikul Amin, Asit Arora, Luigi Camporota, Poppy Denniston, Kariem El-Boghdadly, Miroslav Kvassay, Denisa Macekova, Michal Munk, David Ranford, Jan Rabcan, Chysostomos Tornari, Duncan Wyncoll, Elena Zaitseva, Nicholas Hart, Stephen Tricklebank

Centre for Human & Applied Physiological Sciences

Research output: Contribution to journal › Article › peer-review

13 Citations (Scopus)

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 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.

Original language	English
Pages (from-to)	e0279
Journal	Critical Care Explorations
Volume	2
Issue number	11
DOIs	https://doi.org/10.1097/CCE.0000000000000279
Publication status	Published - Nov 2020

Access to Document

10.1097/CCE.0000000000000279

Cite this

Takhar, A., Surda, P., Ahmad, I., Amin, N., Arora, A., Camporota, L., Denniston, P., El-Boghdadly, K., Kvassay, M., Macekova, D., Munk, M., Ranford, D., Rabcan, J., Tornari, C., Wyncoll, D., Zaitseva, E., Hart, N., & Tricklebank, S. (2020). Timing of Tracheostomy for Prolonged Respiratory Wean in Critically Ill Coronavirus Disease 2019 Patients: A Machine Learning Approach. Critical Care Explorations, 2(11), e0279. https://doi.org/10.1097/CCE.0000000000000279

@article{bedf8a1ff0db4068895513d6480386a8,

title = "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 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.",

author = "Arunjit Takhar and Pavol Surda and Imran Ahmad and Nikul Amin and Asit Arora and Luigi Camporota and Poppy Denniston and Kariem El-Boghdadly and Miroslav Kvassay and Denisa Macekova and Michal Munk and David Ranford and Jan Rabcan and Chysostomos Tornari and Duncan Wyncoll and Elena Zaitseva and Nicholas Hart and Stephen Tricklebank",

note = "Copyright {\textcopyright} 2020 The Authors. Published by Wolters Kluwer Health, Inc. on behalf of the Society of Critical Care Medicine.",

year = "2020",

month = nov,

doi = "10.1097/CCE.0000000000000279",

language = "English",

volume = "2",

pages = "e0279",

journal = "Critical Care Explorations",

issn = "2639-8028",

publisher = "Wolters Kluwer",

number = "11",

}

Takhar, A, Surda, P, Ahmad, I, Amin, N, Arora, A, Camporota, L, Denniston, P, El-Boghdadly, K, Kvassay, M, Macekova, D, Munk, M, Ranford, D, Rabcan, J, Tornari, C, Wyncoll, D, Zaitseva, E, Hart, N & Tricklebank, S 2020, 'Timing of Tracheostomy for Prolonged Respiratory Wean in Critically Ill Coronavirus Disease 2019 Patients: A Machine Learning Approach', Critical Care Explorations, vol. 2, no. 11, pp. e0279. https://doi.org/10.1097/CCE.0000000000000279

TY - JOUR

T1 - Timing of Tracheostomy for Prolonged Respiratory Wean in Critically Ill Coronavirus Disease 2019 Patients

T2 - A Machine Learning Approach

AU - Takhar, Arunjit

AU - Surda, Pavol

AU - Ahmad, Imran

AU - Amin, Nikul

AU - Arora, Asit

AU - Camporota, Luigi

AU - Denniston, Poppy

AU - El-Boghdadly, Kariem

AU - Kvassay, Miroslav

AU - Macekova, Denisa

AU - Munk, Michal

AU - Ranford, David

AU - Rabcan, Jan

AU - Tornari, Chysostomos

AU - Wyncoll, Duncan

AU - Zaitseva, Elena

AU - Hart, Nicholas

AU - Tricklebank, Stephen

PY - 2020/11

Y1 - 2020/11

N2 - 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.

AB - 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.

U2 - 10.1097/CCE.0000000000000279

DO - 10.1097/CCE.0000000000000279

M3 - Article

C2 - 33225305

SN - 2639-8028

VL - 2

SP - e0279

JO - Critical Care Explorations

JF - Critical Care Explorations

IS - 11

ER -

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

Abstract

Access to Document

Fingerprint

Cite this