Predicting scheduled hospital attendance with artificial intelligence (12 April 2019)

Summary

Failure to attend scheduled hospital appointments disrupts clinical management and consumes resource estimated at £1 billion annually in the UK NHS alone. Accurate stratification of absence risk can maximise the yield of preventative interventions. The wide multiplicity of potential causes, and the poor performance of systems based on simple, linear, low-dimensional models, suggests complex predictive models of attendance are needed. In this paper, Nelson et al. quantify the effect of using complex, non-linear, high-dimensional models enabled by machine learning.