AI used to spot missing appointments
An artificial intelligence tool trained to read clinical letters has prevented a number of patients from missing out on key appointments.
A team at St Bartholomew’s Hospital used machine learning to analyse thousands of outpatient letters within the congenital heart disease service and to understand if the correct action had been taken by either the patient or the clinical team.
This could range from booking a follow-up appointment, a referral to another specialist or a request for a scan.
The machine was taught to identify key phrases within patient letters and check them against electronic health records.
Over six months the system read 1,500 letters and identified 16 so-called ‘high risk’ cases where action was needed to prevent delays in care or even serious harm.
The technology was also deployed within uro-oncology.
It is the first time AI has been used in this way at Barts Health.
Shane Cashin, the information business partner at St Bartholomew’s, came up with the idea and worked alongside representatives from our clinical services, Queen Mary University of London and Andrew Houston from the Barts Life Sciences programme.
He said: "If used correctly, AI has the potential to ease workloads for our admin teams, reduce waits for patients and improve safety."
Over one million appointments take place at Barts Health every year. In March alone there were 135,000 new and follow-up consultations.
Shane said: "Whilst only a small sample, early analysis also suggests some ethnic groups are disproportionally affected by missed follow up appointments, which could indicate a language or some other barrier when it comes to the contents of their letters."
The team have applied to Barts Charity for additional funding to refine and expand their pilot, and to explore other AI opportunities.
The project has been shortlisted for a HSJ Digital Award in the driving change through AI and automation award category.
Also shortlisted at the event, which takes place on 6 June in Manchester, is our deteriorating patient app initiative, which is up for the digital literacy, education and upskilling award, and a project to improve population health through digital reporting which is a finalist in the generating impact in population health through digital category.
Read more