GOSH-led trial of AI-scribe technology shows ‘transformative’ benefits for patients and clinicians across London

AI technology tested across nine NHS sites has been proven to free up clinicians to spend nearly a quarter more time with patients.

A major NHS England sponsored study has found that AI-scribing technology can significantly reduce clinician workload while improving patient care, with potential to unlock millions of pounds worth of activity if rolled out nationally.

The study, led by GOSH's Innovation Unit, GOSH DRIVE, was conducted across nine NHS sites in London to assess the impact of an AI-scribing tool, TORTUS, which automatically transcribes consultations and drafts summarised clinical notes for clinicians to review. Over 17,000 patient encounters were evaluated across a diverse range of sites including hospitals, GP practices, mental health services and ambulance teams.

The London-wide study followed on from early success of a trial of the technology in outpatient settings at GOSH.

Results showed a 23.5% increase in direct patient interaction time during appointments, alongside an 8.2% reduction in overall appointment length when AI-scribes were used. A&E saw particularly strong results, with a 13.4% increase in patients seen per shift.

Clinicians described the AI-scribing tool as “transformative” with particular benefits for neurodivergent staff and those working in high-pressure environments. There was a 35% reduction in clinicians feeling overwhelmed by notetaking and qualitative feedback focused on improved satisfaction with time, attention, and documentation accuracy. The technology was widely viewed as enabling better patient care.

Patients and carers also reported improved interactions and greater satisfaction, with Net Promoter Scores1 indicating strong support for AI-scribe-enabled consultations. Patients and families also responded positively, with 92% consenting to AI-scribes use and many noting better engagement during consultations.

Dr Shankar Sridharan, Chief Clinical Information Officer at GOSH said: “This trial is significant as it shows the NHS can lead the way in safely adopting AI. Innovation can’t happen in isolation and by working collaboratively to test this technology across London - from hospitals to ambulances - we’ve proven it can work at scale and make a real difference for both patients and clinicians.”

During consultations with patients, clinicians will typically dictate or manually type notes into a computer and compose letters during and after the consultation.

AI-scribes automate this process, using ambient voice technology (AVT) with generative AI to listen to the consultation and draft a clinic note and letter using templates which can be personalised to each clinician’s style and preferences. Importantly, the AI does not do any clinical decision making and all notes and letters are checked and edited by the clinician before being saved to a patient’s record.

The AI-scribe for this study was provided by a technology partner, TORTUS, a UK based AI start-up. TORTUS is fully compliant with UK GDPR and no patient data are held by the organisation or used to train the AI.

The results from A&E, tested at St George’s University Hospital, were particularly impressive and showed a significant increase in emergency care productivity. When using the AI-scribe, time taken to complete the initial patient note halved, with clinicians reporting greater efficiency and reduced cognitive load.

As part of the study, economic modelling was undertaken by York Health Economics Consortium to show the financial impacts that could be seen across the system if the technology was scaled. This found that if one additional patient was seen per shift per clinician, this equates to £270.93 added capacity per day. Scaling nationally (11,055 A&E clinicians in England), AI-scribe use could yield 9,259 extra A&E consultations each day, saving £176 million in documentation time and unlocking an additional £658 million in capacity annually.

Dr Ahmed Mahdi, Consultant in Emergency Medicine for St George's University Hospital, said: "In such a fast-paced, high-pressured environment, every second counts - and this technology allows us to be more efficient, cut down on admin, and ultimately focus on patient care. Better use of technology is central to the future of the NHS, and it's exciting to be at the forefront of an innovative pilot that’s truly reshaping how we deliver care."

Following the success of the trial, a rollout of AI-scribe technology across outpatient settings at GOSH is planned to begin this autumn. The findings have already informed NHS England’s national guidance on AI-enabled scribing and contributed to the Government’s 10-year Health Plan for health innovation and productivity. This research has already informed the creation of the NHS T.E.S.T. Framework, a national model for evaluating AI technologies in healthcare, and supports NHS England’s guidance on AI-scribing tools.

Health Minister, Stephen Kinnock, said: “This is exactly the kind of innovation we need as we work to build an NHS fit for the future and end hospital backlogs.

“By freeing up clinicians from administrative burden to spend more time with patients, we're not just improving efficiency – we're enhancing the human connection that sits at the heart of great healthcare.

“As part of our 10 Year Health Plan, technologies like AI scribes are crucial in our shift from analogue to digital healthcare. By harnessing the power of technology safely and responsibly, we can deliver better outcomes for patients and better value for taxpayers, whilst ensuring our NHS supports our brilliant staff.”

Dr Vin Diwakar, Clinical Transformation Director at NHS England, said: “Allowing clinicians to spend nearly 25% more of their time interacting with patients and less time typing into a computer improves patient care and reduces the burden of administrative tasks.

“We’re striving to bring the benefits of innovations like this to the frontline so we can transform healthcare for patients as part of the 10 Year Health Plan.”