Extubation Readiness Research Articles

Inverse reinforcement learning for intelligent mechanical ventilation and sedative dosing in intensive care units

BackgroundReinforcement learning (RL) provides a promising technique to solve complex sequential decision making problems in health care domains. To ensure such applications, an explicit reward function encoding domain knowledge should be specified beforehand to indicate the goal of tasks. However, there is usually no explicit information regarding the reward function in medical records. It is then necessary to consider an approach whereby the reward function can be learned from a set of presumably optimal treatment trajectories using retrospective real medical data. This paper applies inverse RL in inferring the reward functions that clinicians have in mind during their decisions on weaning of mechanical ventilation and sedative dosing in Intensive Care Units (ICUs).MethodsWe model the decision making problem as a Markov Decision Process, and use a batch RL method, Fitted Q Iterations with Gradient Boosting Decision Tree, to learn a suitable ventilator weaning policy from real trajectories in retrospective ICU data. A Bayesian inverse RL method is then applied to infer the latent reward functions in terms of weights in trading off various aspects of evaluation criterion. We then evaluate how the policy learned using the Bayesian inverse RL method matches the policy given by clinicians, as compared to other policies learned with fixed reward functions.ResultsResults show that the inverse RL method is capable of extracting meaningful indicators for recommending extubation readiness and sedative dosage, indicating that clinicians pay more attention to patients’ physiological stability (e.g., heart rate and respiration rate), rather than oxygenation criteria (FiO2, PEEP and SpO2) which is supported by previous RL methods. Moreover, by discovering the optimal weights, new effective treatment protocols can be suggested.ConclusionsInverse RL is an effective approach to discovering clinicians’ underlying reward functions for designing better treatment protocols in the ventilation weaning and sedative dosing in future ICUs.

The association of early postoperative desaturation in the operating theatre with hospital discharge to a skilled nursing or long-term care facility.

It is unclear which criteria should be used to define readiness for tracheal extubation in the operating theatre. We studied the effects of desaturation in the operating theatre immediately after tracheal extubation on long-term outcomes. Performing a pre-specified, retrospective analysis of 71,025 cases involving previously independent adults undergoing non-cardiac surgery, we evaluated the association between desaturation events (oxygen saturation <90%) within 10min of tracheal extubation and adverse discharge (to a skilled nursing facility or long-term care facility). A total of 404 (12.3%) cases with, and 5035 (7.4%) cases without, early postoperative desaturation had an adverse discharge. Early postoperative desaturation was associated with higher odds of being discharged to a nursing facility (adjusted odds ratio 1.36 (95%CI 1.20-1.54); p<0.001). Increased duration of desaturation augmented the effect (p for trend <0.001). Desaturation was associated with a higher risk of respiratory, renal and cardiovascular complications as well as increased duration of hospital stay, postoperative intensive care unit admission frequency and cost. Several modifiable factors were associated with desaturation including: high intra-operative long-acting opioid administration; high neostigmine dose; high intra-operative inspired oxygen concentration; and low oxygen delivery immediately before tracheal extubation. There was substantial provider variability between anaesthetists in the incidence of postoperative desaturation unexplained by patient- and procedure-related factors. Early postoperative desaturation is a potentially preventable complication associated with a higher risk of adverse discharge disposition. Anaesthetists may consider developing guidelines to define tracheal extubation readiness that contain postoperative desaturation as an adverse outcome after tracheal extubation.

Muscle strength and endurance to predict successful extubation in mechanically ventilated patients: A pilot study evaluating the utility of upper-limb muscle strength and ergometry

Background. Successful extubation of mechanically ventilated patients is essential for the physiotherapist to succeed in respiratory rehabilitation of the patient. Delay in the weaning process increases the complication rate of mechanical ventilation. A variety of parameters are used as predictors of extubation readiness, but the association between muscle strength (deltoid, neck flexor muscle group and trapezius), endurance and extubation readiness has not been determined. Objectives. The aim of the study was to determine if muscle strength and endurance can be used as possible predictors of successful extubation in mechanically ventilated patients. The objectives were to determine if muscle strength measured with the Oxford grading scale can be used as a possible predictor, and if muscle endurance measured with the MOTOmed letto2 cycle ergometer can be used as a possible predictor. Methods. During the pilot study, 37 subjects were recruited. Deltoid, neck flexors and trapezius muscle strength was tested using the Oxford grading scale and respiratory muscle strength using maximum inspiratory and expiratory pressures. Endurance was determined by riding the MOTOmed letto2 cycle ergometer for 5 minutes with the upper limbs. Results. Muscle strength of the deltoid and the neck flexor muscle group tested with the Oxford grading scale was associated with successful extubation respectively, ( p =0.022; p =0.019). Muscle endurance tested with the MOTOmed letto2 cycle ergometer also demonstrated an association with successful extubation ( p =0.014). Conclusion. Future studies with larger sample sizes are recommended. Keywords. Mechanical ventilation, intensive care unit, extubation failure, respiratory muscle strength, peripheral muscle strength, muscle endurance

Predicting extubation readiness by monitoring the electrical activity of the diaphragm after prolonged mechanical ventilation: a pediatric case report

BackgroundThe intensity of the electrical activity of the diaphragm (Edi) correlates with inspiratory effort. The ratio of tidal volume to the Edi is known as neuroventilatory efficiency (NVE) and is used as an index for ventilation efficiency. Here, we present a case showing that Edi and NVE may be effective parameters to predict successful extubation.Case presentationA 6-month-old female infant required prolonged mechanical ventilation after cardiac surgery. Fifty-two days after surgery, her trachea was extubated but required reintubation. Edi monitoring was initiated to assess diaphragm function. The Edi was > 70 mcV just after the reintubation, and her NVE was 1.0 mL/mcV, but gradually decreased. On day 59, her Edi values during the spontaneous breathing trials were 13 mcV with the improvement of NVE (2.5 mL/mcV) and her trachea was extubated without complications.ConclusionsThe Edi and NVE were valuable for deciding the extubation readiness in a long-term mechanically ventilated patient.

Undersampling and Bagging of Decision Trees in the Analysis of Cardiorespiratory Behavior for the Prediction of Extubation Readiness in Extremely Preterm Infants.

Extremely preterm infants often require endotracheal intubation and mechanical ventilation during the first days of life. Due to the detrimental effects of prolonged invasive mechanical ventilation (IMV), clinicians aim to extubate infants as soon as they deem them ready.Unfortunately, existing strategies for prediction of extubation readiness vary across clinicians and institutions, and lead to high reintubation rates. We present an approach using Random Forest classifiers for the analysis of cardiorespiratory variability to predict extubation readiness. We address the issue of data imbalance by employing random undersampling of examples from the majority class before training each Decision Tree in a bag. By incorporating clinical domain knowledge, we further demonstrate that our classifier could have identified 71% of infants who failed extubation, while maintaining a success detection rate of 78%.

Abstract P-501: A REMIFENTANYL BASED PROTOCOL FOR WEANING NEONATES AND CHILDREN &lt; 3 MONTH FROM PROLONGED, INVASIVE, MECHANICAL VENTILATION (IMV).

Aims & Objectives: Remifentanil is a synthetic opioid with an ultrashort action. We describe a remifentanyl based weaning protocol designed to facilitate extubation after prolonged IMV Methods Patients on IMV > 7 days aged < 3 month were included. Continuous morphine infusion was switched to remifentanyl, while iv. benzodiazepines were gradually changed to oral diazepam. Dosage of remifentanyl was titrated to achieve patient comfort (SBS and WAT1 scoring) maintaining spontaneous breathing effort. For extubation readiness testing and extubation continuous remifentanyl was reduced to an individualized minimal dose Results 8 patients median age 9 days (7- 90), 3,5kg (1,9- 8) after 10,6 (7- 19) IMV days were included. Median daily doses for fentanyl and midazolam at protocol entry were 0,068µg/kg/minute and 0,6mg/kg/h respectively. Remifentanyl was startet at 0,3 µg/kg/minute. Maximum remifentanyl dosage was 0,6 µg/kg/minute (0,33- 0,9). Extubation remifentanyl dose was 0,07µg/kg/min. (0,05- 0,11) and was highest in patients > 14 days of IMV. Mean duration of continuous remifentanyl until extubation was 40 hours (20- 77). Time from reduction of remifentanyl to extubation dose to extubation was 123 minutes (15- 360). 4 Patients received additional Dexmedetomidine. Patients needed bolus sedation with oral diazepam and chloralhydrat median 6,2 (2- 12) and 0,8 (0- 2) times respectively. No patient was reintubated Conclusions Remifentanyl based weaning from IMV provides both patient and provider comfort in avoiding prolonged pre-extubation aggitation and extubation can be well timed. There is potential to reduce duration of weaning process and intubation. It´s a usefull alternative to conventional protocols and merits lager scale evaluation

(12) Establishing a Ventilator Weaning and Extubation Readiness Protocol in the Pediatric Intensive Care Unit Utilizing Pressure Regulated Volume Control and Volume Support: A Quality Improvement Initiative

Specific Aim: To establish and implement a respiratory therapist (RT) ventilator weaning and extubation readiness protocol utilizing pressure regulated volume control (PRVC) and volume support (VS) to reduce length of mechanical ventilation (MV). Background: Many patients admitted to the PICU require MV as part of management of their critical illness. Pediatric patients who require MV are at increased risk for infection, lung injury, delirium, and habituation to sedation. This Ventilator Weaning and Extubation Readiness (VEER)Protocol was designed to reduce the number of days a patient remained on the ventilator, averaged per one hundred patient days, …

(30) Duration of intubation, timing of extubations, and barriers to performing extubation readiness trials in a pediatric ICU: preliminary data from a prospective unit-based study

(30) Duration of intubation, timing of extubations, and barriers to performing extubation readiness trials in a pediatric ICU: preliminary data from a prospective unit-based study

(12) Establishing a Ventilator Weaning and Extubation Readiness Protocol in the Pediatric Intensive Care Unit Utilizing Pressure Regulated Volume Control and Volume Support: A Quality Improvement Initiative

(12) Establishing a Ventilator Weaning and Extubation Readiness Protocol in the Pediatric Intensive Care Unit Utilizing Pressure Regulated Volume Control and Volume Support: A Quality Improvement Initiative

Predictors of extubation readiness in preterm infants: a systematic review and meta-analysis

ContextA variety of extubation readiness tests have already been incorporated into clinical practice in preterm infants.ObjectiveTo identify predictor tests of successful extubation and determine their accuracy compared with clinical judgement...

De-escalation of Care Through Pediatric Intensive Care Unit Liberation Rounds and a Daily Checklist

Introduction:Pediatric intensive care unit (PICU) Liberation Bundle1 was implemented to standardize weaning of ICU support after clinical stabilization and to prevent iatrogenicity by timely assessment of pain, extubation readiness, sedation, delirium, withdrawal, early mobilization, and family engagement. By implementing a PICU Liberation bedside rounding process and a de-escalation daily rounding checklist, we hypothesized that the PICU Liberation Bundle compliance will improve and the risk for iatrogenic conditions can be minimized.Methods:The “old” rounding process used a nursing script organized by organ systems while the “new” process (Fig. 1) focused on PICU Liberation Bundle elements and the addition of a physician-completed checklist (Fig. 2). Independent observers collected data during rounds. All checklists completed over the first 50 days after deployment were analyzed.Results:There was an increase in frequency of PICU Liberation Bundle elements discussed during the “new” process with similar rounding time compared with the “old” process (Table 1). The overall compliance with the checklist was 90.4% (322 of 356 total patient-days). The medical plan was modified 62 times in 14.0% (45 of 322) of the checklists completed. The 5 most frequently modified tasks were converting intravenous to per os meds (13), initiating bowel regimen (11), initiating GI prophylaxis (9), consulting physical therapy/occupational therapy/physical medicine and rehabilitation services (9), and initiating sleep enhancement protocol (6) accounting for 77.4% (48/62) of all amendments made.Conclusions:PICU Liberation rounding process improved adherence with the PICU Liberation Bundle elements, and the checklist caught numerous missed opportunities, thereby increasing the frequency of timely de-escalation of care and minimizing the risk of iatrogenic conditions without lengthening rounding time.

Dexamethasone effect on heart rate variability in preterm infants on mechanical ventilation.

Dexamethasone is administered to some preterm infants with chronic lung disease to facilitate weaning from mechanical ventilation. Heart rate characteristics (HRC), including heart rate variability (HRV), may be impacted by glucocorticoids and may predict extubation readiness. A commercially available monitor developed for sepsis detection continuously calculates HRV and an HRC index, which are inversely related. Determine the impact of dexamethasone on HRV and the HRC index, in relation to extubation success. We identified 109 preterm infants who received dexamethasone while on mechanical ventilation and had HRC index monitoring data available. Average hourly HRV and HRC index were compared the day before and the day after initiation of dexamethasone in three groups: infants who remained on mechanical ventilation, those who were successfully extubated, and those who were extubated and required reintubation in < 3 days. There was a significant increase in HRV and decrease in the HRC index the day after dexamethasone was started (HRV 16.2±0.5 vs 27.6±1.1 ms; HRC index 1.51±0.11 vs. 0.79±0.06 mean SE, p < 0.001). The 63 infants who were extubated within a day of starting dexamethasone had significantly higher HRV compared to those who remained on mechanical ventilation. There was no difference in HRV or its change with dexamethasone in the 45 infants who remained successfully extubated compared to the 18 infants who required reintubation within 3 days. Dexamethasone improves HRV and lowers the HRC index in preterm infants with chronic lung disease on mechanical ventilation.

An Interprofessional Quality Improvement Initiative to Standardize Pediatric Extubation Readiness Assessment.

Establishing protocols to wean mechanical ventilation and assess readiness for extubation, with the goal of minimizing morbidity associated with extubation failure and prolonged mechanical ventilation, have become increasingly important in contemporary PICUs. The aim of this quality improvement initiative is to establish a respiratory therapist-led daily spontaneous breathing trial protocol to standardize extubation readiness assessment and documentation in our PICU. A quality improvement project. Single center, tertiary care Children's Hospital PICU. All intubated patients admitted to PICU requiring conventional mechanical ventilation between February 2013 and January 2016. A working group of pediatric intensivists, respiratory therapists, nurses, and information technology specialists established the protocol, standardized documentation via the electronic medical record, and planned education. Daily spontaneous breathing trial protocol implementation began in February 2015. All patients on mechanical ventilation were screened daily at approximately 4 AM by a respiratory therapist to determine daily spontaneous breathing trial eligibility. If all screening criteria were met, patients were placed on continuous positive airway pressure of 5 cm H2O with pressure support of 8 cm H2O for up to 2 hours. If tolerated, patients would be extubated to supplemental oxygen delivered via nasal cannula in the morning, after intensivist approval. Daily audits were done to assess screening compliance and accuracy of documentation. We analyzed data from 398 mechanically ventilated patients during daily spontaneous breathing trial period (February 2015-January 2016), compared with 833 patients from the pre-daily spontaneous breathing trial period (February 2013-January 2015). During the daily spontaneous breathing trial period, daily screening occurred in 92% of patients. Extubation failure decreased from 7.8% in the pre-daily spontaneous breathing trial period to 4.5% in daily spontaneous breathing trial period. The use of high-flow nasal cannula slightly increased during the project, while there was no change in duration of mechanical ventilation or the use of noninvasive ventilation. An interprofessionally developed respiratory therapist-led extubation readiness protocol can be successfully implemented in a busy tertiary care PICU without adverse events.

Protocol-Directed Sedation Versus Non-Protocol-Directed Sedation to Reduce the Duration of Mechanical Ventilation in Intensive Care Patients.

Protocol-Directed Sedation Versus Non-Protocol-Directed Sedation to Reduce the Duration of Mechanical Ventilation in Intensive Care Patients.

Prediction of Extubation readiness in extremely preterm infants by the automated analysis of cardiorespiratory behavior: study protocol

BackgroundExtremely preterm infants (≤ 28 weeks gestation) commonly require endotracheal intubation and mechanical ventilation (MV) to maintain adequate oxygenation and gas exchange. Given that MV is independently associated with important adverse outcomes, efforts should be made to limit its duration. However, current methods for determining extubation readiness are inaccurate and a significant number of infants fail extubation and require reintubation, an intervention that may be associated with increased morbidities. A variety of objective measures have been proposed to better define the optimal time for extubation, but none have proven clinically useful. In a pilot study, investigators from this group have shown promising results from sophisticated, automated analyses of cardiorespiratory signals as a predictor of extubation readiness. The aim of this study is to develop an automated predictor of extubation readiness using a combination of clinical tools along with novel and automated measures of cardiorespiratory behavior, to assist clinicians in determining when extremely preterm infants are ready for extubation.MethodsIn this prospective, multicenter observational study, cardiorespiratory signals will be recorded from 250 eligible extremely preterm infants with birth weights ≤1250 g immediately prior to their first planned extubation. Automated signal analysis algorithms will compute a variety of metrics for each infant, and machine learning methods will then be used to find the optimal combination of these metrics together with clinical variables that provide the best overall prediction of extubation readiness. Using these results, investigators will develop an Automated system for Prediction of EXtubation (APEX) readiness that will integrate the software for data acquisition, signal analysis, and outcome prediction into a single application suitable for use by medical personnel in the neonatal intensive care unit. The performance of APEX will later be prospectively validated in 50 additional infants.DiscussionThe results of this research will provide the quantitative evidence needed to assist clinicians in determining when to extubate a preterm infant with the highest probability of success, and could produce significant improvements in extubation outcomes in this population.Trial registrationClinicaltrials.gov identifier: NCT01909947. Registered on July 17 2013.Trial sponsor: Canadian Institutes of Health Research (CIHR).

APEX_SCOPE: A graphical user interface for visualization of multi-modal data in inter-disciplinary studies.

In multi-disciplinary studies, different forms of data are often collected for analysis. For example, APEX, a study on the automated prediction of extubation readiness in extremely preterm infants, collects clinical parameters and cardiorespiratory signals. A variety of cardiorespiratory metrics are computed from these signals and used to assign a cardiorespiratory pattern at each time. In such a situation, exploratory analysis requires a visualization tool capable of displaying these different types of acquired and computed signals in an integrated environment. Thus, we developed APEX_SCOPE, a graphical tool for the visualization of multi-modal data comprising cardiorespiratory signals, automated cardiorespiratory metrics, automated respiratory patterns, manually classified respiratory patterns, and manual annotations by clinicians during data acquisition. This MATLAB-based application provides a means for collaborators to view combinations of signals to promote discussion, generate hypotheses and develop features.

Respiratory severity score and extubation readiness in very low birth weight infants

The respiratory severity score (RSS) is a byproduct of mean airway pressure (MAP) and fraction of inspired oxygen (FiO2). We sought to determine whether RSS could be used as a screening tool to predict extubation readiness in very low birth weight (VLBW) infants. In a retrospective cohort study, medical records of all VLBW infants admitted to our unit (6/1/09-2/28/12) were reviewed for infants' demographics, prenatal characteristics, and medication use. Also, records were reviewed for unplanned vs. planned extubation, blood gas, ventilator parameters and signs of severe respiratory failure [RF, defined as partial pressure of carbon dioxide (pCO2)>65, pH<7.20, FiO2>50%, and MAP>10cm] on the day of extubation. During the study period 31% (45/147) failed extubation. Overall, infants who failed extubation had a lower birth weight (BW) and gestational age (GA), and on the day of extubation had a higher RSS and percentage of having one or more signs of severe RF. In a logistic regression model, adjusting for BW, GA, RSS and RF, RSS remained the only risk factor associated with extubation failure [adjusted OR 1.63 (95% CI: 1.10-2.40); p=0.01]. RSS had a sensitivity of 0.86 (95% CI: 0.72-0.94) at a cutoff of 1.26 and a specificity of 0.88 (95% CI: 0.80-0.94) at a cutoff of 2.5. There was no difference in extubation failure between unplanned vs. planned extubation [41% (9/22) vs. 29% (36/125); p=0.25]. An elevated RSS is associated with extubation failure. Successful unplanned extubation is common in VLBW infants.

Impact of Low-Dose Ketamine on the Usage of Continuous Opioid Infusion for the Treatment of Pain in Adult Mechanically Ventilated Patients in Surgical Intensive Care Units.

Ketamine at subanesthetic doses has been shown to provide analgesic effects without causing respiratory depression and may be a viable option in mechanically ventilated patients to assist with extubation. The aim of this study was to evaluate the effects of low-dose ketamine on opioid consumption in mechanically ventilated adult surgical intensive care unit (ICU) patients. A retrospective review of mechanically ventilated adult patients receiving low-dose ketamine continuous infusion (1-5 µcg/kg/min) for adjunctive pain control admitted to surgical ICUs was conducted. Patients were included if they met an ICU safety screen for a spontaneous breathing trial (SBT) implying extubation readiness pending SBT results. The primary end point was the slope of change in morphine equivalents (MEs) 12 hours pre- and postketamine infusion. We hypothesized that low-dose ketamine would increase the slope of opioid dose reduction. Forty patients were analyzed. The median dose of ketamine was 5 µg/kg/min (interquartile range [IQR]: 3.5-5) and the treatment duration was 1.89 days (IQR: 0.96-3.06). Prior to ketamine, the majority of patients received volume-controlled or pressure-supported ventilation with a median duration of 2.05 days (IQR: 1.38-3.61). The median time from the initiation of ketamine to extubation was 1.44 days (IQR: 0.58-2.66). For the primary outcome, there was a significant difference in the slope of ME changes from 1 to -0.265 mg/h 12 hours pre- and postketamine initiation (P < .001). For the secondary outcomes, ketamine was associated with a decrease in vasopressor requirements (phenylephrine equivalent 70 vs 40 mg/h; P = .019). Low-dose continuous infusion ketamine in mechanically ventilated adult patients was associated with a significant increase in the rate of opioid dose reduction without adverse effects on hemodynamic stability.

Halogenated volatile anesthetics in the intensive care unit: current knowledge on an upcoming practice.

The aim of this narrative review was to highlight key points of volatile anesthetics administration in the intensive care unit (ICU), including AnaConDa® and Mirus® devices characteristics and the reported findings on clinical outcomes in critically ill patients. Intravenous sedation in the ICU is associated with issues, such as over- and under-sedation. Halogenated compounds, which can be safely administered by inserting a device in any ICU ventilation circuit, have interesting pharmacodynamic and pharmacokinetic profiles for patients with multi-organ failure. Moreover, analysis of the concentration of exhaled volatile compounds could help evaluation of sedation depth. A recent meta-analysis confirmed that rapid washout of the volatile anesthetics improved both extubation readiness and quality of awakening when compared to intravenous sedation. When administered for a long period, volatile anesthetics improved sedation stability with fewer dose adjustments. Pre- and post-conditioning properties of halogenated compounds are interesting and long-term exposition to this compound is investigated for a potential impact on mortality rate and ICU/hospital length of stay. For now, psychomotor side effects have been reported, mostly in infants, but there were no hepatic or renal injuries. Findings regarding hemodynamic stability are conflicting. Apart from sedation, volatile anesthetics were therapeutic in case reports of status asthmaticus and epilepticus and data are cumulating for benefits in cases of acute respiratory distress syndrome. According to current literature, they should be withheld in cerebral injury. To summarize, the use of volatile anesthetics for sedation is yet only approved by German guidelines, but could spread due to its potential benefits.

Abnormal Breathing Patterns Predict Extubation Failure in Neurocritically Ill Patients

In neurologically injured patients, predictors for extubation success are not well defined. Abnormal breathing patterns may result from the underlying neurological injury. We present three patients with abnormal breathing patterns highlighting failure of successful extubation as a result of these neurologically driven breathing patterns. Recognizing abnormal breathing patterns may be predictive of extubation failure and thus need to be considered as part of extubation readiness.