Development of a machine learning algorithm to predict intubation among hospitalized patients with COVID-19

This article by Arvind and others first appeared in the Journal of Critical Care in November 2020.
Purpose:  The purpose of this study is to develop a machine learning algorithm to predict future intubation among patients diagnosed or suspected with COVID-19.
Materials and methods:  This is a retrospective cohort study of patients diagnosed or under investigation for COVID-19. A machine learning algorithm was trained to predict future presence of intubation based on prior vitals, laboratory, and demographic data. Model performance was compared to ROX index, a validated prognostic tool for prediction of mechanical ventilation.
Results: 4087 patients admitted to five hospitals between February 2020 and April 2020 were included. 11.03% of patients were intubated. The machine learning model outperformed the ROX-index, demonstrating an area under the receiver characteristic curve (AUC) of 0.84 and 0.64, and area under the precision-recall curve (AUPRC) of 0.30 and 0.13, respectively. In the Kaplan-Meier analysis, patients alerted by the model were more likely to require intubation during their admission (p < 0.0001).
Conclusion:  In patients diagnosed or under investigation for COVID-19, machine learning can be used to predict future risk of intubation based on clinical data which are routinely collected and available in clinical setting. Such an approach may facilitate identification of high-risk patients to assist in clinical care.
The full text of this article is available to subscribers via this link to the journal’s homepage.  The full text of articles from issues older than sixty days is available via this link to an archive of issues of Journal of Critical Care.  A Rotherham NHS Athens password is required.  Eligible staff can register for an Athens password via this link.  Please speak to the library staff for more details.

Impact of therapeutic hypothermia on bleeding events in adult patients treated with extracorporeal life support peri-cardiac arrest

This article by Mecklenburg and colleagues was first published in Journal of Critical Care during November 2020.
Purpose:  Whether therapeutic hypothermia (TH) adds to the risk of bleeding in patients on extracorporeal life support (ECLS) peri-cardiac arrest remains unknown.
Material and methods:  Single center retrospective study on patients receiving veno-arterial ECLS peri-cardiac arrest ± TH at 32–34 C (January 2009–December 2015). Primary outcome: major bleeding (including intracerebral hemorrhage, ICH) < 72h of cardiac arrest. Logistic regression and marginal structural models were used to analyze associations with major bleeding.
Results:  Of 66 patients receiving ECLS, 36 were treated with TH. Major bleeding occurred in 14 patients (39%) treated with ECLS+TH and in 17 patients (57%) with ECLS alone. ICH was reported in 3 (8%) and one patient (3%), respectively. There was no difference in mortality, but lung injury occurred more often in ECLS+TH. A platelet count <60 × 10⁹/L but not TH was associated with major bleeding (including ICH). The estimated causal risk ratio of TH on the occurrence of major bleeding (including ICH) at 72 h post cardiac arrest was 0.95 (95%CI 0.62–1.45).
Conclusions:  Bleeding complications were common in our study. However, TH (32–34 C) was not associated with an increased risk of major bleeding in patients on ECLS peri-cardiac arrest.
The full text of this article is available to subscribers via this link to the journal’s homepage.  The full text of articles from issues older than sixty days is available via this link to an archive of issues of Journal of Critical Care.  A Rotherham NHS Athens password is required.  Eligible staff can register for an Athens password via this link.  Please speak to the library staff for more details.

Burnout, resilience and work engagement among Dutch intensivists in the aftermath of the COVID-19 crisis: A nationwide survey

This article by Meynaar and others was first published in Journal of Critical Care during November 2020.
Purpose:  The COVID-19 crisis put a strain on intensive care resources everywhere in the world increasing the risk of burnout. Previously, the prevalence of burnout among Dutch intensivists was found to be low. Engagement and resilience among intensivists have not previously been studied quantitatively, however, both are related to burnout and provide a possible way to mitigate burnout. Our objective was to study burnout and its association with work engagement and resilience among Dutch intensivists in the aftermath of the COVID-19 crisis.
Methods:  An online questionnaire was sent to all Dutch intensivists. The questionnaire consisted of questions on personal and work-related characteristics and validated questionnaires: the Maslach Burnout Inventory, the Utrecht Work Engagement Scale, and the Resilience Evaluation Scale.
Results:  The response rate was 27.2% with 162 evaluable responses. Thirteen respondents (8.0%) were classified as having burnout, 63 (38.9%) respondents were reporting high work engagement. Burnout was found to be negatively associated with both work engagement and resilience.
Conclusion:  In the aftermath of the 2020 COVID-19 crisis, we found a raised prevalence of burnout among intensivists, however this is still low in international comparisons. Intensivists with burnout scored low on resilience and low on work engagement.
The full text of this article is available to subscribers via this link to the journal’s homepage.  The full text of articles from issues older than sixty days is available via this link to an archive of issues of Journal of Critical Care.  A Rotherham NHS Athens password is required.  Eligible staff can register for an Athens password via this link.  Please speak to the library staff for more details.

Veno-venous extracorporeal membrane oxygenation allocation in the COVID-19 pandemic

This research by Kadhiresan and colleagues was first published in the Journal of Critical Care during November 2020.
Rapid global spread of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) and the resultant clinical illness, coronavirus disease 2019 (COVID-19), drove the World Health Organization to declare COVID-19 a pandemic. Veno-venous Extra-Corporeal Membrane Oxygenation (VV-ECMO) is an established therapy for management of patients demonstrating the most severe forms of hypoxemic respiratory failure from COVID-19. However, features of COVID-19 pathophysiology and necessary length of treatment present distinct challenges for utilization of VV-ECMO within the current healthcare emergency. In addition, growing allocation concerns due to capacity and cost present significant challenges. Ethical and legal aspects pertinent to triage of this resource-intensive, but potentially life-saving, therapy in the setting of the COVID-19 pandemic are reviewed here. Given considerations relevant to VV-ECMO use, additional emphasis has been placed on emerging hospital resource scarcity and disproportionate representation of healthcare workers among the ill. Considerations are also discussed surrounding withdrawal of VV-ECMO and the role for early communication as well as consultation from palliative care teams and local ethics committees. In discussing how to best manage these issues in the COVID-19 pandemic at present, we identify gaps in the literature and policy important to clinicians as this crisis continues.
The full text of this article is available to subscribers via this link to the journal’s homepage.  The full text of articles from issues older than sixty days is available via this link to an archive of issues of Journal of Critical Care.  A Rotherham NHS Athens password is required.  Eligible staff can register for an Athens password via this link.  Please speak to the library staff for more details.

Critical Care Reviews Newsletter 466 15th November 2020

The Critical Care Reviews Newsletter, brings you the best critical care research and open access articles from across the medical literature over the past seven days.
The highlights of this week’s edition are the ARREST randomised controlled trial, investigating ECLS for out-of-hospital cardiac arrest and refractory ventricular fibrillation; systematic reviews and meta analyses on high-flow nasal cannula postoperatively and the cuff leak test in adults in predicting post-extubation airway complications; and observational studies on submissions and downloads of preprints in the first year of medRxiv and symptoms of anxiety, depression, and peritraumatic dissociation in critical care clinicians managing patients with COVID-19.
The full text of the newsletter is available to all via this link.

Critical Care Reviews Newsletter 465 9th November 2020

The Critical Care Reviews Newsletter, which provides the best critical care research and open access articles from across the medical literature during the last week.
This week’s edition includes randomised controlled trials such as “Effects of capillary refill time-vs. lactate-targeted fluid resuscitation on regional, microcirculatory and hypoxia-related perfusion parameters in septic shock: a randomized controlled trial” systematic reviews and meta analyses including Non-catecholamine vasopressors in the treatment of adult patients with septic shock—evidence from meta-analysis and trial sequential analysis of randomized clinical trials. and observational studies for example Rescue therapy with inhaled nitric oxide and almitrine in COVID-19 patients with severe acute respiratory distress syndrome.
The full text of the newsletter is available to all via this link.

Intensive Care Medicine Volume 46 Issue 11 November 2020

To view Intensive Care Medicine’s November issue’s contents page follow this link.
Articles published in this issue include: Efficacy and safety of gastrointestinal bleeding prophylaxis in critically ill patients: an updated systematic review and network meta-analysis of randomized trials and COVID-19 in critical care: epidemiology of the first epidemic wave across England, Wales and Northern Ireland
Articles on COVID 19 these are freely available in full text to everyone.
To read the full text of any of these articles via the journal’s homepage requires a personal subscription to “Intensive Care Medicine” though some are available open access.  Individual articles can be ordered from the Rotherham NHS Foundation Trust Library and Knowledge Service.  Registered members of the library can make article requests online via this link.
The full text of articles from issues older than one year ago is available via this link to an archive of issues of Intensive Care Medicine.  A Rotherham NHS Athens password is required.  Eligible staff can register for an Athens password via this link.  Please speak to the library staff for more details.

Automated weaning from mechanical ventilation: Results of a Bayesian network meta-analysis

This article by Neuschwander and others was published in the Journal of Critical Care in November 2020.
Purpose:  Mechanical ventilation (MV) weaning is a crucial step. Automated weaning modes reduce MV duration but the question of the best automated mode remains unanswered. Our objective was to compare the major automated modes for MV weaning in critically ill and post-operative adult patients.
Material and methods:  We conducted a network Bayesian meta-analysis to compare different automated modes. We searched MEDLINE, EMBASE and Cochrane central registry for randomized control trials comparing automated weaning modes either to another automated mode or to standard-of-care. The primary outcome was the duration of MV weaning extracted from the original trials.
Results:  663 articles were screened and 26 trials (2097patients) were included in the final analysis. All automated modes included in the study (ASV, Intellivent ASV, Smartcare, Automode, PAV and MRV) outperformed standard-of-care but no automated mode reduced the duration of mechanical ventilation weaning as compared to others in the network meta-analysis.
Conclusion:  Compared to standard weaning practice, all automated modes significantly reduced the duration of MV weaning in critically ill and post-operative adult patients. When cross-compared using a network meta-analysis, no specific mode was different in reducing the duration of MV weaning.
The full text of this article is available to subscribers via this link to the journal’s homepage.  The full text of articles from issues older than sixty days is available via this link to an archive of issues of Journal of Critical Care.  A Rotherham NHS Athens password is required.  Eligible staff can register for an Athens password via this link.  Please speak to the library staff for more details.

Critical Care Reviews Newsletter 464 1st November 2020

The Critical Care Reviews Newsletter, which provides the best critical care research and open access articles from across the medical literature during the last week.
This week’s edition includes randomised controlled trials such as “Risk of Overcorrection in Rapid Intermittent Bolus vs Slow Continuous Infusion Therapies of Hypertonic Saline for Patients With Symptomatic Hyponatremia”, systematic reviews and meta analyses including “Targeted Temperature Management in Cardiac Arrest Patients with an Initial Non-Shockable Rhythm: A Systematic Review and Meta-Analysis” and an observational study on “The subcortical basis of outcome and cognitive impairment in TBI.”
The full text of the newsletter is available to all via this link.