Towards an educational tool for supporting neonatologists in the delivery room
This work addresses the need for better training tools for neonatologists in delivery rooms, though it appears incremental as it builds on existing risk factor analysis without introducing a fundamentally new paradigm.
The paper tackled the problem of predicting high-risk situations requiring neonatal resuscitation by developing a machine learning approach to identify risk factors from real data, with the goal of creating a mobile application to improve recognition rates and intervention planning.
Nowadays, there is evidence that several factors may increase the risk, for an infant, to require stabilisation or resuscitation manoeuvres at birth. However, this risk factors are not completely known, and a universally applicable model for predicting high-risk situations is not available yet. Considering both these limitations and the fact that the need for resuscitation at birth is a rare event, periodic training of the healthcare personnel responsible for newborn caring in the delivery room is mandatory. In this paper, we propose a machine learning approach for identifying risk factors and their impact on the birth event from real data, which can be used by personnel to progressively increase and update their knowledge. Our final goal will be the one of designing a user-friendly mobile application, able to improve the recognition rate and the planning of the appropriate interventions on high-risk patients.