Focus on ventilation and airway management in the ICU

Jong, Audrey De; Citerio, Giuseppe; Jaber, Samir

doi:10.1007/s00134-017-4982-y

Cited by 4 publications

(1 citation statement)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One one hand, higher costs occur if unnecessary ventilation is still taking effect, while premature extubation can give rise to increased risk of morbidity and mortality. Optimal decision making regarding when to wean patients off of a ventilator thus becomes nontrivial since there is currently no consistent clinical opinion on the best protocol for weaning of ventilation [238]. Prasad et al [220] applied off-policy RL algorithms, FQI-ERT and with feed forward neural networks, to determine the best weaning time of invasive mechanical ventilation, and the associated personalized sedation dosage.…”

Section: B Critical Carementioning

confidence: 99%

Reinforcement Learning in Healthcare: A Survey

Yu¹,

Liu²,

Nemati³

2019

Preprint

View full text Add to dashboard Cite

As a subfield of machine learning, reinforcement learning (RL) aims at empowering one's capabilities in behavioural decision making by using interaction experience with the world and an evaluative feedback. Unlike traditional supervised learning methods that usually rely on one-shot, exhaustive and supervised reward signals, RL tackles with sequential decision making problems with sampled, evaluative and delayed feedback simultaneously. Such distinctive features make RL technique a suitable candidate for developing powerful solutions in a variety of healthcare domains, where diagnosing decisions or treatment regimes are usually characterized by a prolonged and sequential procedure. This survey will discuss the broad applications of RL techniques in healthcare domains, in order to provide the research community with systematic understanding of theoretical foundations, enabling methods and techniques, existing challenges, and new insights of this emerging paradigm. By first briefly examining theoretical foundations and key techniques in RL research from efficient and representational directions, we then provide an overview of RL applications in a variety of healthcare domains, ranging from dynamic treatment regimes in chronic diseases and critical care, automated medical diagnosis from both unstructured and structured clinical data, as well as many other control or scheduling domains that have infiltrated many aspects of a healthcare system. Finally, we summarize the challenges and open issues in current research, and point out some potential solutions and directions for future research.

show abstract

Section: B Critical Carementioning

confidence: 99%

Reinforcement Learning in Healthcare: A Survey

Yu¹,

Liu²,

Nemati³

2019

Preprint

View full text Add to dashboard Cite

show abstract

The challenge of avoiding intubation in immunocompromised patients with acute respiratory failure

Jong

Calvet

Lemiale

et al. 2018

Expert Review of Respiratory Medicine

View full text Add to dashboard Cite

A growing number of immunocompromised (IC) patients with acute hypoxemic respiratory failure (ARF) is admitted to the intensive care unit (ICU) worldwide. Areas covered: This review provides an overview of the current knowledge of the ways to prevent intubation in IC patients with ARF. Expert commentary: Striking differences oppose ARF incidence, characteristics, etiologies and management between IC and non-IC patients. Survival benefits have been reported with early admission to ICU in IC patients. Then, while managing hypoxemia and associated organ dysfunction, the identification of the cause of ARF will be guided by a rigorous clinical assessment at the bedside, further assisted by an invasive or noninvasive diagnostic strategy based on clinical probability for each etiology. Finally, the initial respiratory support aims to avoid mechanical ventilation for the many yet recognizing those patients for whom delaying intubation expose them to suboptimal management. We advocate for not using noninvasive ventilation (NIV) in this setting. A proper evaluation of High-flow nasal cannula oxygen (HFNC) is required in IC patients as to demonstrate its superiority compared to standard oxygen therapy. Day-to-day decisions must strive to avoid delayed intubation, and make every effort to identify ARF etiology.

show abstract

Effect of endotracheal tube plus stylet versus endotracheal tube alone on successful first-attempt tracheal intubation among critically ill patients: the multicentre randomised STYLETO study protocol

et al. 2020

View full text Add to dashboard Cite

IntroductionTracheal intubation is one of the most daily practiced procedures performed in intensive care unit (ICU). It is associated with severe life-threatening complications, which can lead to intubation-related cardiac arrest. Using a preshaped endotracheal tube plus stylet may have potential advantages over endotracheal tube without stylet. The stylet is a rigid but malleable introducer which fits inside the endotracheal tube and allows for manipulation of the tube shape; to facilitate passage of the tube through the laryngeal inlet. However, some complications from stylets have been reported including mucosal bleeding, perforation of the trachea or oesophagus and sore throat. The use of a stylet for first-attempt intubation has never been assessed in ICU and benefit remains to be established.Methods and analysisThe endotracheal tube plus stylet to increase first-attempt success during orotracheal intubation compared with endotracheal tube alone in ICU patients (STYLETO) trial is an investigator-initiated, multicentre, stratified, parallel-group unblinded trial with an electronic system-based randomisation. Patients will be randomly assigned to undergo the initial intubation attempt with endotracheal tube alone (ie,without stylet, control group) or endotracheal tube + stylet (experimental group). The primary outcome is the proportion of patients with successful first-attempt orotracheal intubation. The single, prespecified, secondary outcome is the incidence of complications related to intubation, in the hour following intubation. Other outcomes analysed will include safety, exploratory procedural and clinical outcomes.Ethics and disseminationThe study project has been approved by the appropriate ethics committee ‘Comité-de-Protection-des-Personnes Nord-Ouest3-19.04.26.65808 Cat2 RECHMPL19_0216/STYLETO2019-A01180-57’”. Informed consent is required. The results will be submitted for publication in a peer-reviewed journal and presented at one or more scientific conferences. If combined use of endotracheal tube plus stylet facilitates tracheal intubation of ICU patients compared with endotracheal tube alone, its use will become standard practice, thereby decreasing first-attempt intubation failure rates and, potentially, the frequency of intubation-related complications.Trial registration detailsClinicalTrials.gov Identifier:NCT04079387.

show abstract

Focus on ventilation and airway management in the ICU

Cited by 4 publications

References 15 publications

Reinforcement Learning in Healthcare: A Survey

Reinforcement Learning in Healthcare: A Survey

The challenge of avoiding intubation in immunocompromised patients with acute respiratory failure

Effect of endotracheal tube plus stylet versus endotracheal tube alone on successful first-attempt tracheal intubation among critically ill patients: the multicentre randomised STYLETO study protocol

Contact Info

Product

Resources

About