Background The rapid development in big data analytics and the data-rich environment of intensive care units together provide unprecedented opportunities for medical breakthroughs in the field of critical care. We developed and validated a machine learning-based model, the Pediatric Risk of Mortality Prediction Tool (PROMPT), for real-time prediction of all-cause mortality in pediatric intensive care units. Methods Utilizing two separate retrospective observational cohorts, we conducted model development and validation using a machine learning algorithm with a convolutional neural network. The development cohort comprised 1445 pediatric patients with 1977 medical encounters admitted to intensive care units from January 2011 to December 2017 at Severance Hospital (Seoul, Korea). The validation cohort included 278 patients with 364 medical encounters admitted to the pediatric intensive care unit from January 2016 to November 2017 at Samsung Medical Center. Results Using seven vital signs, along with patient age and body weight on intensive care unit admission, PROMPT achieved an area under the receiver operating characteristic curve in the range of 0.89–0.97 for mortality prediction 6 to 60 h prior to death. Our results demonstrated that PROMPT provided high sensitivity with specificity and outperformed the conventional severity scoring system, the Pediatric Index of Mortality, in predictive ability. Model performance was indistinguishable between the development and validation cohorts. Conclusions PROMPT is a deep model-based, data-driven early warning score tool that can predict mortality in critically ill children and may be useful for the timely identification of deteriorating patients. Electronic supplementary material The online version of this article (10.1186/s13054-019-2561-z) contains supplementary material, which is available to authorized users.

Conventional dendritic cells (cDCs) are composed of heterogeneous subsets commonly arising from dendritic cell (DC)-committed progenitors. A population of CD301b-expressing DCs has recently been identified in non-lymphoid barrier tissues such as skin. However, whether CD301b DCs in the skin represent an ontogenetically unique subpopulation of migratory cDCs has not been fully addressed. Here, we demonstrated that CD301b dermal DCs were distinct subpopulation of FMS-like tyrosine kinase 3 ligand (FLT3L)-dependent CD11b cDC2 lineage, which required an additional GM-CSF cue for the adequate development. Although the majority of lymphoid-resident cDC2 lacked CD301b expression, dermal migratory cDC2 contained a substantial fraction of CD301b subset. Similar to CD301b population, CD301b dermal DC development was closely regulated by FLT3 signaling, suggesting their common origin from FLT3L-responsive cDC progenitors. However, FLT3L-driven cDC progenitor culture was not sufficient, but additional GM-CSF treatment was required to produce CD301b cDC2. In vivo development of CD301b cDC2 was significantly augmented by exogenous GM-CSF, while the repopulation of CD301b dermal cDC2 was abrogated by GM-CSF neutralization. Functionally, CD301b cDC2 was capable of producing a high level of IL-23, and the depletion of CD301b cDC2 effectively prevented IL-17-mediated psoriasiform dermatitis. Therefore, our findings highlight the differentiation program of a distinct CD301b dermal cDC2 subset in the skin and its involvement in psoriatic inflammation.

No abstract

No abstract

No abstract