Predicting Length of Stay in Intensive Care

Pie & AI: Belgrade

Talk
Deep Learning Approaches to Electronic Health Records
by Emma Rocheteau, Cambridge University

Abstract
Over the past decade, a digital revolution in healthcare recording and monitoring has enabled an explosion of AI research in the clinical domain. In this talk, Emma will give a broad overview of the field
including its opportunities and challenges, before describing her own
research. In collaboration with Microsoft Research, they have developed a new deep learning model based on the combination of temporal convolution and pointwise (1x1) convolution, to solve the problem of the length of stay prediction in the intensive care unit.

Follow us