BACKGROUND: Ventilator management for children with hypoxemic respiratory failure may benefit from ventilator protocols, which rely on blood gases. Accurate noninvasive estimates for pH or P aCO 2 could allow frequent ventilator changes to optimize lung-protective ventilation strategies. If these models are highly accurate, they can facilitate the development of closed-loop ventilator systems. We sought to develop and test algorithms for estimating pH and P aCO 2 from measures of ventilator support, pulse oximetry, and end-tidal carbon dioxide pressure (P ETCO 2 ). We also sought to determine whether surrogates for changes in dead space can improve prediction. METHODS: Algorithms were developed and tested using 2 data sets from previously published investigations. A baseline model estimated pH and P aCO 2 from P ETCO 2 using the previously observed relationship between P ETCO 2 and P aCO 2 or pH (using the Henderson-Hasselbalch equation). We developed a multivariate gaussian process (MGP) model incorporating other available noninvasive measurements. RESULTS: The training data set had 2,386 observations from 274 children, and the testing data set had 658 observations from 83 children. The baseline model predicted P aCO 2 within ؎ 7 mm Hg of the observed P aCO 2 80% of the time. The MGP model improved this to ؎ 6 mm Hg. When the MGP model predicted P aCO 2 between 35 and 60 mm Hg, the 80% prediction interval narrowed to ؎ 5 mm Hg. The baseline model predicted pH within ؎ 0.07 of the observed pH 80% of the time. The MGP model improved this to ؎ 0.05. CONCLUSIONS: We have demonstrated a conceptual first step for predictive models that estimate pH and P aCO 2 to facilitate clinical decision making for children with lung injury. These models may have some applicability when incorporated in ventilator protocols to encourage practitioners to maintain permissive hypercapnia when using high ventilator support. Refinement with additional data may improve model accuracy.

State-of-the-art named entity recognition (NER) systems have been improving continuously using neural architectures over the past several years. However, many tasks including NER require large sets of annotated data to achieve such performance. In particular, we focus on NER from clinical notes, which is one of the most fundamental and critical problems for medical text analysis. Our work centers on effectively adapting these neural architectures towards lowresource settings using parameter transfer methods. We complement a standard hierarchical NER model with a general transfer learning framework consisting of parameter sharing between the source and target tasks, and showcase scores significantly above the baseline architecture. These sharing schemes require an exponential search over tied parameter sets to generate an optimal configuration. To mitigate the problem of exhaustively searching for model optimization, we propose the Dynamic Transfer Networks (DTN), a gated architecture which learns the appropriate parameter sharing scheme between source and target datasets. DTN achieves the improvements of the optimized transfer learning framework with just a single training setting, effectively removing the need for exponential search.

No abstract