Machine learning to predict late respiratory support in preterm infants: a retrospective cohort study.

Bronchopulmonary dysplasia (BPD) has been a critical morbidity in preterm infants. To improve our definition and prediction of BPD is challenging yet indispensable. We aimed to apply machine learning (ML) to investigate effective models by using the recently-proposed and data-driven definition to predict late respiratory support modalities at 36 weeks' post menstrual age (PMA). We collected data on very-low-birth-weight infants born between 2016 and 2019 from the Taiwan Neonatal Network database. Twenty-four attributes associated with their early life and seven ML algorithms were used in our analysis. The target outcomes were overall mortality, death before 36 weeks' PMA, and severity of BPD under the new definition, which served as a proxy for respiratory support modalities. Of the 4103 infants initially considered, 3200 were deemed eligible. The logistic regression algorithm yielded the highest area under the receiver operating characteristic curve (AUROC). After attribute selection, the AUROC of the simplified models remain favorable (e.g., 0.801 when predicting no BPD, 0.850 when predicting grade 3 BPD or death before 36 weeks' PMA, and 0.881 when predicting overall mortality). By using ML, we developed models to predict late respiratory support. Estimators were developed for clinical application after being simplified through attribute selection.

Crystalline growth of rubrene film enhanced by vertical ordering in cadmium arachidate multilayer substrate.

The growth of highly crystalline rubrene thin films for organic field effect transistor (OFET) application remains a challenge. Here, we report on the vapor-deposited growth of rubrene films on the substrates made of cadmium arachidate (CdA) multilayers deposited onto SiO2/Si(100) via the Langmuir-Blodgett technique. The CdA films, containing 2n+1 layers, with integer n ranging from 0 to 4, are surface-terminated identically by the methyl group but exhibit the thickness-dependent morphology. The morphology and structure of both CdA and rubrene films are characterized by X-ray reflectivity (XRR), X-ray diffraction (XRD), near-edge X-ray absorption fine structure (NEXAFS) spectroscopy, and atomic force microscopy (AFM). Crystalline rubrene films, evidenced by XRD and marked by platelet features in AFM images, become observable when grown onto the CdA layer thicker than 5L. XRD data show that vertical ordering, that is, ordering along surface normal, of CdA multilayer substrates exerts a strong influence in promoting the crystalline growth of rubrene films. This promoted growth is not due to the surface energy of CdA layer but derived from the additional interaction localized between rubrene and CdA island sidewall and presumably strengthened by a close dimensional match between the a-axis of rubrene lattice and the layer spacing of CdA multilayer. The best OFET mobility is recorded for 9L CdA substrate and reaches 6.7 × 10(-2) cm(2) V(-1) s(-1), presumably limited by the roughness of the interface between CdA and rubrene films.