Using Machine Learning and Explainable AI to predict and understand mental health appointment DNAs to reduce inequalities


30 Second Summary

This project uses machine learning to explore correlations whether there is a correlation between missed mental health appointments and factors like deprivation, age, ethnicity, and travel distance. Reducing non-attendance can significantly impact waiting lists.

Machine Learning
Geographic Modelling
Travel Times
Explainable AI
Author
Affiliation

Heath McDonald

Lancashire and South Cumbria NHS Foundation Trust

As a provider of Mental Health Services for SMI, Lancashire & South Cumbria NHS Foundation Trust is committed to helping to deliver the aims of Core20Plus5. Core20PLUS5 is a national NHS England approach to inform action to reduce healthcare inequalities at both national and system level.

The aim of this HSMA project is to use machine learning to help understand whether there is a correlation between failed attendance of mental health outpatient appointments and deprivation, or whether this could be being influenced by other factors (features) such as age, ethnicity, the distance travelled to get to those appointments etc.

With constantly growing waiting lists. anything we can do to reduce non-attendance can have a significant impact on these.

The project idea is to develop a Machine learning model to investigate whether there is a relationship between travel distance and method and appointment attendance. The project will also use explainable AI to help users understand what the results mean.