RESUMO
OBJECTIVE: We aim to create a predictive model capable of giving a noninvasive, immediate and reliable estimate of the arterial partial pressure of carbon dioxide (PaCO2) in mechanically ventilated children with a better reliability than its estimation from end-tidal CO2 (PetCO2) and minute ventilation volume (Vmin) evolution. METHODS: We collected data from the Intensive Care Unit (ICU) database of Sainte-Justine University Hospital (Montreal, Canada) and used the multilayer perceptron (MLP) to estimate the PaCO2. Input data were (1) Arterial blood gas (ABG) at a previous time to calibrate the model, (2) mechanical ventilator parameters and (3) pulse oximetry. The data were divided into four groups depending on the time gap between previous ABG and its prediction: [0 h, 2 h], [2 h, 6 h], [6 h, 12 h] and [12 h, 24 h]. RESULTS: We included 17,329 ABGs collected from 527 patients between May 2015 and October 2018. Median age was 6.7 months (interquartile range 1-60) and female proportion was 45%. Patients had a median of 13 ABGs per patient (IQR 5-34). The accuracy of the models in the four groups was 18%, 18%, 19% and 25% higher than the minute volume models and the PetCO2 models (4% to 11%, respectively). CONCLUSION: Our model based on noninvasive parameters was able to better estimate the PaCO2 in mechanically ventilated children when compared to the traditional techniques. SIGNIFICANCE: ABG analysis is very important in ICU; it is the gold standard in respiratory and acid-base evaluation. ABG is invasive, painful and risky. Our approach, noninvasive and reliable, is an alternative for optimizing mechanical ventilator settings, thus providing better care for patients.