Predicting Extubation Readiness in Preterm Infants Utilizing Machine Learning: A Diagnostic Utility Study.

Abstract

The objective of this study was to predict extubation readiness in preterm infants using machine learning analysis of bedside pulse oximeter and ventilator data. This is an observational study with prospective recordings of oxygen saturation (SpO₂) and ventilator data from infants <30 weeks of gestation age. Research pulse oximeters collected SpO₂ (1 Hz sampling rate) to quantify intermittent hypoxemia (IH). Continuous ventilator metrics were collected (4-5-minute sampling) from bedside ventilators. Data modeling was completed using unbiased machine learning algorithms. Three model sets were created using the following data source combinations: (1) IH and ventilator (IH + SIMV), (2) IH, and (3) ventilator (SIMV). Infants were also analyzed separated by postnatal age (infants <2 or ≥2 weeks of age). Models were compared by area under the receiver operating characteristic curve (AUC). A total of 110 extubation events from 110 preterm infants were analyzed. Infants had a median gestation age and birth weight of 26 weeks and 825 g, respectively. Of the 3 models presented, the IH + SIMV model achieved the highest AUC of 0.77 for all infants. Separating infants by postnatal age increased accuracy further achieving AUC of 0.94 for <2 weeks of age group and AUC of 0.83 for ≥2 weeks group. Machine learning analysis has the potential to enhance prediction accuracy of extubation readiness in preterm infants while utilizing readily available data streams from bedside pulse oximeters and ventilators.