Maintenance Notice

Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Wednesday, July 01, 2020 at 8:00 PM to 10:00 PM EST. We apologize in advance for any inconvenience this may cause you.

Who will be affected?

Accepted for/Published in: JMIR Research Protocols

Date Submitted: Jun 23, 2026
Date Accepted: Jul 22, 2026

The final, peer-reviewed published version of this preprint can be found here:

Evaluation of Ambient Voice Technology in the National Health Service in England: Protocol for a Phase 2 Study

Morris S, Shand J, Georghiou T, Herbert K, Lawrence R, Mehta R, Ng PL, Rolewicz L, Elphinstone H, Walton H

Evaluation of Ambient Voice Technology in the National Health Service in England: Protocol for a Phase 2 Study

JMIR Res Protoc 2026;15:e105261

DOI: 10.2196/105261

PMID: 42832701

Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.

Evaluation of Ambient Voice Technology in the NHS In England: Phase 2 Study Protocol

  • Stephen Morris; 
  • Jenny Shand; 
  • Theo Georghiou; 
  • Kevin Herbert; 
  • Rachel Lawrence; 
  • Raj Mehta; 
  • Pei Li Ng; 
  • Lucina Rolewicz; 
  • Holly Elphinstone; 
  • Holly Walton

ABSTRACT

Background:

Ambient Voice Technology (AVT) uses conversational artificial intelligence to record and organise clinical consultations in real time. It is being adopted quickly across the NHS. However, evidence about its effects on productivity, costs, or staff experience across different healthcare settings is limited. Phase 1 of this research programme developed a taxonomy, logic model, and outcome framework for evaluating AVT. Phase 2 will carry out a multi-site, mixed-methods evaluation of AVT in four NHS trusts. These include mental health outpatient services, acute hospital outpatient clinics, and accident and emergency departments.

Objective:

This study aims to explore the real-world impact of AVT on productivity, costs, and staff experience across NHS adult services.

Methods:

The study includes three parts. (i) A quantitative quasi-experimental analysis of routine NHS data to estimate the impact of AVT on documentation time, clinician activity, and service outcomes. (ii) A comprehensive health economic evaluation comprising cost-consequence analysis, cost-benefit analysis, and budget impact modelling. (iii) Interviews with up to 36 staff from three services (mental health outpatient, acute hospital outpatient, and accident and emergency) to explore their experience of using AVT, their views on its impact, and what helps and gets in the way of its use. Sites will be chosen to include different care settings, organisational environments, and AVT products. Quantitative and economic analyses will use NHS electronic health records and national datasets to understand changes over time and measure the impact of AVT. Interview data will be analysed using thematic analysis and rapid assessment procedures to identify key themes. All study findings will be combined to give a clear view of AVT and its impact.

Results:

Data collection is expected to begin in August 2026 and conclude by January 2027. Publication of results is anticipated in February 2027.

Conclusions:

This evaluation will provide real-world evidence on the productivity, economic, and experiential impacts of AVT in the NHS. Outputs will include peer-reviewed papers, a slide-deck summary for the funder, and a publicly available health economic decision-support tool to help NHS organisations decide if they should adopt AVT.


 Citation

Please cite as:

Morris S, Shand J, Georghiou T, Herbert K, Lawrence R, Mehta R, Ng PL, Rolewicz L, Elphinstone H, Walton H

Evaluation of Ambient Voice Technology in the National Health Service in England: Protocol for a Phase 2 Study

JMIR Res Protoc 2026;15:e105261

DOI: 10.2196/105261

PMID: 42832701

Download PDF


Request queued. Please wait while the file is being generated. It may take some time.

© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.