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.