OneAdvanced launches the UK’s first private sovereign healthcare LLM trained on NHS Primary Care data with NVIDIA

Birmingham, UK – 9 June 2026 – OneAdvanced, one of the UK’s largest providers of sector-focused SaaS software, today announced the successful completion of a a pilot programme with NVIDIA, to develop and validate a contextual sovereign-AI model for NHS Care Navigation trained on pseudonymised real-world NHS patient online consultation requests.

The pilot demonstrates that the OneAdvanced ‘Care Navigator LLM’ can materially improve triage accuracy, support faster access to appropriate care and reduce NHS resource wastage.

The results demonstrate that sovereign AI models trained on UK healthcare data can deliver world-class performance while meeting the governance, privacy and clinical standards required by the NHS and expected by UK citizens.

The pilot outcome brings together a unique combination of OneAdvanced’s UK sovereign healthcare data, more than 35-years of NHS workflow expertise, and partnership with NVIDIA AI infrastructure.

Built using the NVIDIA Nemotron open models and NeMo libraries, and trained on a stratified, balanced set of pseudonymised NHS patient triage requests submitted through OneAdvanced’s triage and online consultation platform (Patchs) in use across 500,000 monthly UK patient interactions. The pilot used a systematic evaluation process to compare the accuracy to a wide range of external LLMs, including leading frontier models such as Claude Sonnet and Claude Opus.

Unlike public LLMs, OneAdvanced’s ‘Care Navigator LLM’ learns directly from clinicians over time – corrections made by GPs using the system form the basis of continuous training data for the LLM.

The OneAdvanced NVIDIA Nemotron-Nano-9B Care Navigation pilot realised key benefits, demonstrating that the NHS can procure the right AI solutions in the flow of work for clinicians, increasing patient experience and decreasing NHS wastage, leading to increased patient capacity:

• Up to 150x lower inference costs than leading frontier models
• Outperformed leading frontier AI models including Claude Sonnet and Haiku variants
• Achieved significantly higher accuracy than a GP control group in benchmark categorisation tasks.

Combined, these results demonstrate the potential to improve triage accuracy at national scale while reducing NHS waste, increasing clinical capacity and improving patient experience.

The NHS transformation as outlined in the NHS 10 Year Health Plan requires a multitude of changes;

1. operational ways of working, with shared workflows across disparate departments;
2. freeing up of clinicians’ time from administration to patient engagements;
3. an understanding that sticking ‘digital’ across the front door does not solve patient engagement, humans do; and
4. leverage of incumbent providers to co-create the technological solutions of the future, in accordance with working practices, operations, governance and safety.

Importantly, all patient data processed through the OneAdvanced ‘Care Navigator LLM’ is stored, hosted and governed under UK Law, supporting NHS requirements around data residency, resilience and regulatory compliance. The model weights, fine-tuning, hosting and inference all sit within the UK perimeter, keeping the capability under UK hosting and governance.

Dr Ben Brown, GP Partner at, Langworthy Medical Practice, and Medical Director at OneAdvanced, added:

"Detecting clinical topics in patient requests is key to enable the ‘AI Care Navigator’ within the Triage and Online Consultation platform to ask the right follow up questions and provide the right response to patients. This allows me as a busy GP to understand the patients’ needs quicker and deal with their request more effectively. Increasing the accuracy of clinical topic detection through AI Care Navigator makes this process even better, reducing workload for me and my staff, and ensuring patients get the most appropriate care they need quicker.”

Simon Walsh, Chief Executive Officer at OneAdvanced, said:

“We’re delighted to have invested in this technological advancement, delivering improved care navigation accuracy for patients and waste avoidance for the NHS. We are focused on delivering structural advantages to the UK NHS, along with compliance to medical device and UK sovereign AI model standards, utilising decades of experience and deep integrations with the NHS, which are an absolute necessity for real-world impact to be realised.  The future of AI in healthcare will not be built on generic models. In healthcare, accuracy, governance and context matter more than anything.”

By developing a sovereign model specifically for AI-assisted care navigation and triage, powered by NVIDIA technology, we are demonstrating how organisations creating the greatest impact will be those combining advanced AI capability with deep operational expertise, trusted domain knowledge and governed data embedded directly into the flow of work.

“With decades of experience supporting the NHS and one of the UK’s largest healthcare workflow datasets, OneAdvanced is helping to transform how primary and community care best serve patients for the years ahead.”

Anthony Hills, Director UK & Ireland at NVIDIA, said:

“The UK has a significant opportunity to lead in the development of sovereign AI for highly regulated and mission-critical sectors such as healthcare.

“OneAdvanced’s work demonstrates how NVIDIA technology can be applied to create practical AI systems that support clinicians, improve patient experience and operate safely at scale.  This pilot highlights the difference organisations with deep NHS expertise and context can make in accelerating digital transformation across healthcare.”

OneAdvanced is one of the UK’s largest healthcare software providers, with more than 35 years’ experience supporting primary, secondary, urgent, private and social care settings. Its software supports more than 40 million NHS patients annually, including 85% of NHS 111 services, more than 4,000 GP practices and over 160 NHS trusts.