NCT01909947

Prediction of Extubation Readiness in Extreme Preterm Infants by the Automated Analysis of CardioRespiratory Behavior

Prediction of Extubation Readiness in Extreme Preterm Infants by the Automated Analysis of CardioRespiratory Behavior: the APEX Study

• Status: Completed
• Phase: —
• Study type: Observational
• Enrollment: 266 (actual)
• Sponsor: McGill University Health Centre/Research Institute of the McGill University Health Centre · Academic / Other
• Sex: All
• Age: —
• Healthy volunteers: Not accepted

Summary

The investigators hypothesize that machine learning methods using a combination of novel, quantitative measures of cardio-respiratory variability can accurately predict the optimal time to extubate extreme preterm infants. In this multicenter prospective study, cardiorespiratory signals will be recorded from 250 extreme preterm infants who are eligible for extubation. Automated signal analysis algorithms will compute a variety of metrics for each infant describing the cardiorespiratory state. Machine learning methods will then be used to find the optimal combination of these statistical measures and clinical features that provide the best overall predictor of extubation readiness. Finally, investigators will develop an Automated system for Prediction of EXtubation (APEX) 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 (NICU). The performance of APEX will later be clinically validated in 50 additional infants prospectively.

Detailed description

At birth, extreme preterm infants (≤28 weeks) have inconsistent respiratory drive, airway instability, surfactant deficiency and immature lungs that frequently result in respiratory failure. Management of these infants is difficult and most will require endotracheal intubation and mechanical ventilation (ETT-MV) within the first days of life to survive. ETT-MV is an invasive therapy that is associated with adverse clinical outcomes including ventilator-associated pneumonia, impaired neurodevelopment, and increased mortality. Consequently, clinicians try to remove ETT-MV as quickly as possible. However, 25 to 35% of these extubation attempts will fail and infants will require reintubation, an intervention that is also associated with increased morbidity and mortality. Therefore physicians must determine the optimal time for extubation which minimizes the duration of ETT-MV and maximizes the chances of success. A variety of objective measures have been proposed to assist with this decision but none has proven to be useful clinically. Investigators from this group have recently explored the predictive power of indices of autonomic nervous system function based on measurements of heart rate (HRV) and respiratory variability (RV). The use of sophisticated, automated algorithms to analyze those cardiorespiratory signals have shown some promising preliminary results in predicting which infants can be extubated successfully.

Conditions

• Prediction of Extubation Readiness

Interventions

Type	Name	Description
OTHER	Cardiorespiratory signal acquisition	Cardiorespiratory signals will measure heart rate (using electrocardiography), chest and abdominal movements (using respiratory inductance plethysmography) and oxygen saturation (using pulse oximetry). Data will be acquired during 2 recording periods: 1. A 60-minute period while the infant receives any mode of conventional mechanical ventilation 2. A 5-minute period prior to extubation while the mode of ventilation is switched to endotracheal tube CPAP (Continuous Positive Airway Pressure), so that the respiratory pattern will be controlled by the infant

Timeline

• Start date: 2013-09-01
• Primary completion: 2018-10-01
• Completion: 2018-12-01
• First posted: 2013-07-29
• Last updated: 2019-04-01

Locations

5 sites across 2 countries: United States, Canada