UK hospital uses AI to predict which patients are most likely to miss appointmentsBMJ 2019; 365 doi: https://doi.org/10.1136/bmj.l1792 (Published 15 April 2019) Cite this as: BMJ 2019;365:l1792
- Gareth Iacobucci
- The BMJ
An algorithm that can predict which patients are most likely to miss appointments could save the NHS millions of pounds, say the UK clinicians who developed the tool.
A team from University College London Hospital created a mathematical modelling tool using records from 22 000 appointments for MRI scans across two NHS hospitals. Findings published in the journal Digital Medicine showed that using the artificial intelligence tool enabled correct identification of 90% of patients who would not attend.1
The tool was not wholly precise, incorrectly identifying around half of patients who attended appointments as being at risk of not attending. But the targeted approach enabled the hospital to …