LO
DeploymentCognitive automation2024-06-30
Cwm Taf Morgannwg health board in Wales reports using an AI autocoder for referral, waiting-list and emergency department activity, with 20.7% more episodes coded and all its coders retained
Medical coderoccupation page →
Event date / reported
2024-06-30 · reported 2024-09-24
Evidence stage
DeploymentAn employer has put it into production. Can move the baseline — weighted by scale and how similar the setting is.
Tasks this bears on
Coding short, routine charts
High-volume encounters with short, standard documents — imaging reports, lab orders, simple outpatient visits.
Automating✓ Evidence-backed
Where this applies
One Welsh health board describing its own coding programme in an entry for the NHS Wales Awards, published by NHS Wales. The programme combined recruitment, professional development, standards and technology, including 'AI-driven autocoding' with major updates to the autocoder quarterly; the board supported autocoder use for referral, waiting-list and Emergency Department activities — high-volume, short records — and expanded coding to most outpatient procedures. It reports a 20.7% rise in finished consultant episodes coded, no change in accuracy and completeness, and full retention of qualified and trainee coders over twelve months. It is an award submission written by the board itself, and the gains come from the whole programme, so they cannot be credited to the autocoder alone.
What this means
In one Welsh health board, the short, high-volume records — referrals, waiting lists, emergency visits — are now coded with an AI autocoder, and the board says output rose without losing accuracy or coders. The routine end of the job is being handed to the machine; the people stayed.
What it does not yet show
It is one board's award entry, and the increase comes from a programme that also recruited and trained staff; it does not show what share of records the autocoder handles alone or how it is checked.
What you can check
Open the NHS Wales Awards 2024 entry for Cwm Taf Morgannwg University Health Board, Clinical Coding, and find "supported autocoder use for referral, waiting list, and Emergency Department activities".
Does it change the assessment?
No. The impact index is never moved by a single event. What this record did: the 1 linked task judgement above now rest on evidence instead of inference.
Source
NHS Wales Performance and Improvement — NHS Wales Awards 2024 entry, Cwm Taf Morgannwg University Health Board, Clinical Coding (published 24 September 2024) · verified 2026-09-27 · Claude (VOLO agent) · interpreted 2026-09-27 · Claude (VOLO agent)
Primary source — published by the party that did this, or the authority of record. No co-signature needed.