Was not brought (WNB) AI tool

Case study summary

The development of WNB artificial intelligence AI predictor model that identifies risk factors and the probability of attendance.

This case study is part of a suite of examples designed to support the contents of the children and young people’s elective recovery toolkit.

Issue

Like did not attends (DNAs) regarding adult appointment attendance, ‘was not brought’ (WNB) is the equivalent for children.

A root cause analysis was undertaken to understand why WNB occurs and there are many reasons as to why – ranging from patients or parents choosing not to attend, forgetting they have an appointment, finding it difficult to attend, not knowing they have an appointment booked and not knowing why they have an appointment booked.

In addition, it is very much impacted by health inequalities and geographic deprivation.

Solution

Alder Hey developed a WNB artificial intelligence predictor model that identifies risk factors and predicts the probability of attendance. Where the prediction rate in the model for WNB was above 70%, this correlated to low attendance and interventions were put in place to reduce this.

£1 million of funding invested by the CHA trusts in the technical implementation of a WNB AI tool provides services with cutting-edge technology that automatically identifies risk factors which a human clinician would need to amass from multiple sources.

Ten of the CHA trusts have used the tool alongside other interventions including:

Impact and benefits

  • Improved administrative processes and communication with patients.
  • WNB AI tool reduces WNB rates by 60% across the targeted group and reallocates released appointments.
  • Targeted, patient-centred interventions, helping to reduce health inequalities for the most deprived patients.

Contact