Search

Background: To embrace the need for freely accessible training data sets originating from the real world, in the ELISE project, we integrate source data from a pediatric intensive care unit and provide it to researchers. Objective: We present our vision, initial results and steps on a trail towards an evolutionary open pediatric intensive care data set. Methods: Our evolution plan for the data set comprises three steps. The final data set will include raw clinical data and labels on critical outcomes such as organ dysfunction and sepsis, generated automatically by computerized and well-evaluated methods. Results: First step resulted in an initial version data set available in a central repository. Conclusions: Our approach has great potential to provide a comprehensive open intensive care data set labeled for critical pediatric outcomes and, thus, contributing to overcome the current lack of real-world pediatric intensive care data usable for training data-driven algorithms. [ABSTRACT FROM AUTHOR]

Critical care can benefit from analyzing data by machine learning approaches for supporting clinical routine and guiding clinical decision-making. Developing data-driven approaches for an early detection of systemic inflammatory response syndrome (SIRS) in patients of pediatric intensive care and exploring the possibility of an approach using training data sets labeled automatically beforehand by knowledge-based approaches rather than clinical experts. Using naïve Bayes classifier and an artificial neuronal network (ANN), trained with real data labeled by (1) domain experts ad (2) a knowledge-based decision support system (CDSS). Accuracies were evaluated by the data set labeled by domain experts using a 10-fold cross validation. The ANN approach trained with data labeled by domain experts yielded a specificity of 0.9139 and sensitivity of 0.8979, whereas the approach trained with a data set labeled by a knowledge-based CDSS achieves a specificity of 0.9220 and a sensitivity of 0.8887. ANN yielded promising results for data-driven detection of pediatric SIRS with real data. Our comparison shows the feasibility of using training data labeled automatically by knowledge-based approaches rather than manually allocated by experts. [ABSTRACT FROM AUTHOR]