Objective of the work is the development of prognostic machine learning models that predict qualitative and quantitative measures of postnatal growth in very low birth weight preterm infants. Observational retrospective data about 964 infants at risk are retrieved from “Fondazione Monza e Brianza per il bambino e la mamma“’s electronic medical record. Both prenatal (gestational, socioeconomic, etc.) and perinatal (nutritional, respiratory assistance, drug prescription and daily growth) data up to a week after birth are the features included. Model’s performances are compared to previous literature and human performance, showing a substantial improvement (in e.g., best regression MAE=0.49, best classification AUC=0.94).
Description Logics (DL) have been traditionally proposed for modeling and reasoning about domain specific knowledge with ontologies. In recent years several types of new unstructured content emerged, especially due to rapid and constantly increasing development of the Web: such content types provide potentially useful information that can be formally represented with DL languages and stored into knowledge bases (KB). A characterizing aspect of ontologies is their ability to support Question Answering (QA) applications over a KB, where a DL specification represents the foundation for reasoning services and inference of knowledge. A relatively well explored use case is QA with flexible query specification, traditionally formalized within fuzzy set theory in relational data-bases. This talk will explain the basic concepts of DL ontologies and QA applications, and how to think about them in presence of flexible queries.