scholarly journals Deep learning to predict long-term mortality in patients requiring 7 days of mechanical ventilation

PLoS ONE ◽  
2021 ◽  
Vol 16 (6) ◽  
pp. e0253443
Author(s):  
Naomi George ◽  
Edward Moseley ◽  
Rene Eber ◽  
Jennifer Siu ◽  
Mathew Samuel ◽  
...  
Keyword(s):  
Neural Network ◽  
Intensive Care Unit ◽  
Mechanical Ventilation ◽  
Intensive Care ◽  
Deep Learning ◽  
Medical Information ◽  
Prediction Models ◽  
Prolonged Mechanical Ventilation ◽  
External Validation ◽  
Saps Ii Score

Background Among patients with acute respiratory failure requiring prolonged mechanical ventilation, tracheostomies are typically placed after approximately 7 to 10 days. Yet half of patients admitted to the intensive care unit receiving tracheostomy will die within a year, often within three months. Existing mortality prediction models for prolonged mechanical ventilation, such as the ProVent Score, have poor sensitivity and are not applied until after 14 days of mechanical ventilation. We developed a model to predict 3-month mortality in patients requiring more than 7 days of mechanical ventilation using deep learning techniques and compared this to existing mortality models. Methods Retrospective cohort study. Setting: The Medical Information Mart for Intensive Care III Database. Patients: All adults requiring ≥ 7 days of mechanical ventilation. Measurements: A neural network model for 3-month mortality was created using process-of-care variables, including demographic, physiologic and clinical data. The area under the receiver operator curve (AUROC) was compared to the ProVent model at predicting 3 and 12-month mortality. Shapley values were used to identify the variables with the greatest contributions to the model. Results There were 4,334 encounters divided into a development cohort (n = 3467) and a testing cohort (n = 867). The final deep learning model included 250 variables and had an AUROC of 0.74 for predicting 3-month mortality at day 7 of mechanical ventilation versus 0.59 for the ProVent model. Older age and elevated Simplified Acute Physiology Score II (SAPS II) Score on intensive care unit admission had the largest contribution to predicting mortality. Discussion We developed a deep learning prediction model for 3-month mortality among patients requiring ≥ 7 days of mechanical ventilation using a neural network approach utilizing readily available clinical variables. The model outperforms the ProVent model for predicting mortality among patients requiring ≥ 7 days of mechanical ventilation. This model requires external validation.

scholarly journals Prediction of prolonged mechanical ventilation for intensive care unit patients: A cohort study

2013 ◽  
pp. 184-188 ◽  
Author(s):  
Alvaro Sanabria ◽  
Ximena Gomez ◽  
Valentin Vega ◽  
Luis Carlos Dominguez ◽  
Camilo Osorio
Keyword(s):  
Intensive Care Unit ◽  
Mechanical Ventilation ◽  
Cohort Study ◽  
Intensive Care ◽  
Critically Ill ◽  
Medical Condition ◽  
Prolonged Mechanical Ventilation ◽  
Invasive Mechanical Ventilation ◽  
Adult Patients ◽  
Saps Ii Score

Introduction: There are no established guidelines for selecting patients for early tracheostomy. The aim was to determine the factors that could predict the possibility of intubation longer than 7 days in critically ill adult patients. Methods: This is cohort study made at a general intensive care unit. Patients who required at least 48 hours of mechanical ventilation were included. Data on the clinical and physiologic features were collected for every intubated patient on the third day. Uni- and multivariate statistical analyses were conducted to determine the variables associated with extubation. Results: 163 (62%) were male, and the median age was 59±17 years. Almost one-third (36%) of patients required mechanical ventilation longer than 7 days. The variables strongly associated with prolonged mechanical ventilation were: age (HR 0.97 (95% CI 0.96-0.99); diagnosis of surgical emergency in a patient with a medical condition (HR 3.68 (95% CI 1.62-8.35), diagnosis of surgical condition-non emergency (HR 8.17 (95% CI 2.12-31.3); diagnosis of non-surgical-medical condition (HR 5.26 (95% CI 1.85-14.9); APACHE II (HR 0.91 (95% CI 0.85-0.97) and SAPS II score (HR 1.04 (95% CI 1.00-1.09) The area under ROC curve used for prediction was 0.52. 16% of patients were extubated after day 8 of intubation. Conclusions: It was not possible to predict early extubation in critically ill adult patients with invasive mechanical ventilation with common clinical scales used at the ICU. However, the probability of successfully weaning patients from mechanical ventilation without a tracheostomy is low after the eighth day of intubation.

scholarly journals Prone Position after Liberation from Prolonged Mechanical Ventilation in COVID-19 Respiratory Failure

2020 ◽  
Vol 2020 ◽  
pp. 1-7
Author(s):  
Andrei Karpov ◽  
Anish R. Mitra ◽  
Sarah Crowe ◽  
Gregory Haljan
Keyword(s):  
Intensive Care Unit ◽  
Mechanical Ventilation ◽  
Intensive Care ◽  
Respiratory Failure ◽  
Respiratory Rate ◽  
Prolonged Mechanical Ventilation ◽  
Case Series ◽  
Prone Positioning ◽  
Retrospective Case ◽  
Number Of Patients

Objective and Rationale. Prone positioning of nonintubated patients has prevented intubation and mechanical ventilation in patients with respiratory failure from coronavirus disease 2019 (COVID-19). A number of patients in a recently published cohort have undergone postextubation prone positioning (PEPP) following liberation from prolonged mechanical ventilation in attempt to prevent reintubation. The objective of this study is to systematically search the literature for reports of PEPP as well as describe the feasibility and outcomes of PEPP in patients with COVID-19 respiratory failure. Design. This is a retrospective case series describing the feasibility and tolerability of postextubation prone positioning (PEPP) and its impact on physiologic parameters in a tertiary intensive care unit during the COVID-19 pandemic. Setting and Patients. This study was conducted on patients with COVID-19 respiratory failure hospitalized in a tertiary Intensive Care Unit at Surrey Memorial Hospital during the COVID-19 pandemic. Measurements and Results. We did not find prior reports of PEPP following prolonged intubation in the literature. Four patients underwent a total of 13 PEPP sessions following liberation from prolonged mechanical ventilation. Each patient underwent a median of 3 prone sessions (IQR: 2, 4.25) lasting a median of 1.5 hours (IQR: 1.2, 2.1). PEPP sessions were associated with a reduction in median oxygen requirements, patient respiratory rate, and reintubation rate. The sessions were well tolerated by patients, nursing, and the allied health team. Conclusions. The novel practice of PEPP after liberation from prolonged mechanical ventilation in patients with COVID-19 respiratory failure is feasible and well tolerated, and may be associated with favourable clinical outcomes including improvement in oxygenation and respiratory rate and a low rate of reintubation. Larger prospective studies of PEPP are warranted.

scholarly journals The percutaneous dilatational tracheostomy in the intensive care unit - our experience

2018 ◽  
Vol 71 (suppl. 1) ◽  
pp. 77-82
Author(s):  
Vladimir Dolinaj ◽  
Sanja Milosev ◽  
Gordana Jovanovic ◽  
Ana Andrijevic ◽  
Nensi Lalic ◽  
...  
Keyword(s):  
Intensive Care Unit ◽  
Mechanical Ventilation ◽  
Intensive Care ◽  
Prothrombin Time ◽  
Prolonged Mechanical Ventilation ◽  
Percutaneous Tracheostomy ◽  
Percutaneous Dilatational Tracheostomy ◽  
Seldinger Technique ◽  
Dilatational Tracheostomy ◽  
Tracheal Cannula

Percutaneous tracheostomy is a commonly carried out procedure in patients in the Intensive Care Unit. Percutaneous dilatational tracheostomy consists of the introduction of a tracheal cannula from the front of the neck, through blunt dissection of the pretracheal tissues, using a guide by Seldinger technique. When percutaneous dilatational tracheostomy procedure was introduced in routine clinical practice in the Clinical Center of Vojvodina, procedural protocol was established. This Protocol includes: 1. indications, contraindications and timing for percutaneous dilatational tracheostomy, 2. assessment of the patient, 3. preparation of the patient and equipment, 4. procedure description, 5. potential complications and complication management. At our institution percutaneous dilatational tracheostomy is performed on an individual patient basis assessment within 5-7 days following translaryngeal intubation. Routinely the platelet count, activated prothrombin time and prothrombin time are checked. The patient?s neck is assessed clinicaly and by the use of fiberoptic bronchoscope and ultrasound. At our institution we use the modified Ciaglia technique of the percutaneous dilatational tracheostomy-Ciaglia Single Dilatator method with the TRACOE? experc Set vario which includes spiral rein?forced tracheal cannula. At the end of procedure fiberoptic evaluation of the tracheobroinchial tree is made and chest X-ray is done. Percutaneous dilatational tracheostomy is a simple, safe, and effective procedure performed in the Intensive Care Unit. It is the preferred technique of airway management in the Intensive Care Units in the patients requiring prolonged mechanical ventilation, tracheobronchial hygiene and weaning from mechanical ventilation.

Patients’ recollections of stressful experiences while receiving prolonged mechanical ventilation in an intensive care unit*

2002 ◽  
Vol 30 (4) ◽  
pp. 746-752 ◽  
Author(s):  
Armando J. Rotondi ◽  
Lakshmipathi Chelluri ◽  
Carl Sirio ◽  
Aaron Mendelsohn ◽  
Richard Schulz ◽  
...  
Keyword(s):  
Intensive Care Unit ◽  
Mechanical Ventilation ◽  
Intensive Care ◽  
Prolonged Mechanical Ventilation ◽  
Stressful Experiences

Decannulation and Survival following Tracheostomy in an Intensive Care Unit

2003 ◽  
Vol 112 (10) ◽  
pp. 853-858 ◽  
Author(s):  
Randal Leung ◽  
Donald Campbell ◽  
Lachlan MacGregor ◽  
Robert G. Berkowitz
Keyword(s):  
Intensive Care Unit ◽  
Mechanical Ventilation ◽  
Intensive Care ◽  
Prolonged Mechanical Ventilation ◽  
Rank Test ◽  
Consecutive Series ◽  
Term Outcome ◽  
Royal Melbourne Hospital ◽  
Long Term Outcome ◽  
Risk Of Aspiration

We investigated the long-term outcome of patients requiring tracheostomy in an intensive care unit (ICU) in an attempt to identify risk factors that would indicate a low probability of early decannulation. A retrospective study was conducted of a consecutive series of 106 patients who underwent tracheostomy in the period between January 1, 2001, and December 31, 2001, during their admission to the ICU at the Royal Melbourne Hospital, Melbourne, Australia. There were 61 male and 39 female patients with a median age of 65 years. The indications for tracheostomy were prolonged mechanical ventilation (47), tracheobronchial toilet or risk of aspiration (45), and an unstable or obstructed airway (8). Thirty-seven patients died during the study period. All surviving patients were successfully decannulated (median cannulation time, 25 days). Patients with tracheostomies inserted for an unstable or obstructed airway had a significantly shorter cannulation time (median time of 13 days) as compared to the other two indications (mechanical ventilation, 25 days; risk of aspiration, 33 days; log-rank test, χ2(2) = 14.62 and p = .0007). Multivariate analysis showed that the effect of an unstable or obstructed airway was independent of the remaining group variables. We conclude that ICU patients who need a tracheostomy have a high mortality rate. Only the indication for tracheostomy insertion predicts early decannulation, and other patient variables are not significant predictors.

Sign in / Sign up

Export Citation Format

Share Document