Ventilator flow data predict bronchopulmonary dysplasia in extremely premature neonates

Abstract

Early prediction of bronchopulmonary dysplasia (BPD) may facilitate tailored management for neonates at risk. We investigated whether easily accessible flow data from a mechanical ventilator can predict BPD in neonates born extremely premature (EP).In a prospective population-based study of EP-born neonates, flow data were obtained from the ventilator during the first 48 h of life. Data were logged for >10 min and then converted to flow–volume loops using custom-made software. Tidal breathing parameters were calculated and averaged from ≥200 breath cycles, and data were compared between those who later developed moderate/severe and no/mild BPD.Of 33 neonates, 18 developed moderate/severe and 15 no/mild BPD. The groups did not differ in gestational age, surfactant treatment or ventilator settings. The infants who developed moderate/severe BPD had evidence of less airflow obstruction, significantly so for tidal expiratory flow at 50% of tidal expiratory volume (TEF50) expressed as a ratio of peak tidal expiratory flow (PTEF) (p=0.007). A compound model estimated by multiple logistic regression incorporating TEF50/PTEF, birthweight z-score and sex predicted moderate/severe BPD with good accuracy (area under the curve 0.893, 95% CI 0.735–0.973).This study suggests that flow data obtained from ventilators during the first hours of life may predict later BPD in premature neonates. Future and larger studies are needed to validate these findings and to determine their clinical usefulness.

Prediction Models for Bronchopulmonary Dysplasia in Preterm Infants: A Systematic Review

“…Subsequently, 88 articles were excluded, among which 11 articles used the composite outcome “BPD or death.” In total, 18 studies ( 14 – 31 ) were included in this systematic review ( Figure 1 ). Eight studies ( 14 , 16 , 19 , 21 , 22 , 25 – 27 ) described model development without external validation, five studies ( 15 , 17 , 24 , 29 , 30 ) described model development with external validation in independent data, and five studies ( 18 , 20 , 23 , 28 , 31 ) described external validation with or without model updating.…”

Bronchopulmonary Dysplasia Predicted by Developing a Machine Learning Model of Genetic and Clinical Information

“…According to the previously reported clinical prediction models of BPD, the AUROC is about 0.8 (Onland et al, 2013;Bentsen et al, 2018;Hunt et al, 2018). We hypothesized that adding the genetic information into the prediction model of BPD can improve the AUROC value by 0.1.…”

“…(AUROC) ranged from 0.50 to 0.76 for BPD in an external validation study of a systematic review (Onland et al, 2013). Additionally, the ratio of tidal expiratory flow at 50% of expired volume to peak tidal expiratory flow (as one of the mechanical ventilation parameters) gave an AUROC for the development of moderate/severe BPD (sBPD) of 0.774 (Bentsen et al, 2018); mechanical ventilation at 1 week provided an AUROC for the development of BPD and sBPD of 0.77 and 0.83 (Hunt et al, 2018), respectively; and a multifactorial model that included BW, GA, sex, presence of a hemodynamically significant patent ductus arteriosus (as diagnosed by an echocardiogram), respiratory distress syndrome, hypotension within the first 72 h of life, and intraventricular hemorrhage (IVH) delivered an AUROC for the development of BPD of 0.930-which showed a noticeably improved discriminatory performance, but without favorable clinical maneuverability (Gursoy et al, 2015).…”

Corticosteroid response predicts bronchopulmonary dysplasia status at 36 weeks in preterm infants treated with dexamethasone: A pilot study

“…Similarly, models based on ventilator flow loops 31 or oxygen desaturations 32 require custom software. Scores that incorporate readily available clinical data, such as N-terminal-prohormone B-type natriuretic peptide levels 33 and Score for Neonatal Acute Physiology scores 34 are attractive, but do not include drug response.…”