Automated Assessment System with Cross Reality for Neonatal Endotracheal Intubation Training

Neonatal endotracheal intubation (ETI) is a resuscitation skill and therefore, requires an effective training regimen with acceptable success rates. However, current training regimen faces some challenges, such as the lack of visualization inside the manikin and quantification of performance, resulting in inaccurate guidance and highly variable manual assessment. We present a Cross Reality (XR) ETI simulation system which registers ETI training tools to their virtual counterparts. Thus, our system can capture all aspects of motions and visualize the entire procedure, offering instructors with sufficient information for assessment. A machine learning approach was developed to automatically evaluate the ETI performance for standardizing assessment protocols by using the performance parameters extracted from the motions and the scores from an expert rater. The classification accuracy of the machine learning algorithm is 83.5%.