OpSense Healthcare

Clinical AI trained on thousands of real consultations, not online scrapings.

Meet Julian — the world's first clinical decision-support AI trained on tens of thousands of real urology cases, curated by a practising NHS consultant surgeon.

INPUT — CONSULTATION AUDIOOUTPUT — STRUCTURED CLINICAL DATA
Why now

Most clinical AI has never heard a surgeon's consultation.

General-purpose models are trained on old textbooks, out-of-date guidelines, and scraped internet text. They've rarely seen the pauses, the follow-up questions, the hedged uncertainty of an actual clinic room — the texture that separates a safe tool from a plausible-sounding one.

Data gap

No surgical-grade training data

Most frontier models are trained on poor quality data. Julian has been trained on thousands of real consultations by a practising surgeon.

Trust gap

Clinicians don't trust generic tools

Tools built without clinical authorship rarely reflect how experienced consultants actually reason and communicate.

Deployment gap

Regulatory pathways are treated as an afterthought

Most health-AI products bolt on compliance late. We're building the regulatory pathway in from day one.

The product

Meet Julian.

Julian started life as a virtual patient, trained on tens of thousands of real urology cases. An experienced clinician (attending) has since consulted with Julian thousands of times — and every one of those transcripts and audio recordings feeds back in, training Julian into the decision-support AI now live in clinic.

10,000+
Real urology cases underpinning the model
1,000+
Consultations recorded and structured for training
1: Julian
The first clinical persona, live
PATIENT
It's mostly at night — I'm up three, four times.
Julian
I'm sorry to hear that. What about during the day — any frequency, urgency or incontinence?
How it works

A data flywheel, not a one-off model.

Every consultation — real or simulated — feeds the next version of the model. The pipeline is the product.

01

Voice consultation

Real and simulated consultations, recorded with consent.

02

Transcription

Speech-to-text tuned for clinical dialogue and terminology.

03

Structured data

Transcripts cleaned, labelled, and prepared for training.

04

Fine-tuned model

A domain model refined on this data, not generic web text.

05

Back to the clinic

Deployed as training tools that generate the next round of data.

Built by clinicians
Dr Conor Mösli Lynch

Dr Conor Mösli Lynch

Fellow of The Royal College of Surgeons
Founder, OpSense · Consultant Urological Surgeon

Julian is built from inside the clinic, not around it. Dr Conor is a practising Consultant Urological Surgeon in the UK, across state and private practice, and co-author of a major textbook in urological surgery.

FRCS Urol
Consultant Urological Surgeon
Textbook Co-Author
Practising Clinician
Presented at
American Urological Association
The British Association of Urological Surgeons
European Association of Urology
Training access

For NHS clinicians

If you hold an NHS email address, you can request access to a training build of Julian for simulation and CPD use — separate from the clinical decision-support product.

Access is restricted to verified nhs.net / nhs.uk email addresses.
  • 1Enter your NHS email address — we check it's a recognised NHS domain.
  • 2We email you a verification link to confirm it's really you.
  • 3Follow the link to set a password and start your first training session with Julian.
Built for the real bar

Regulatory rigor from day one.

Health-AI credibility is won or lost on compliance. We're mapping our pathway early, not retrofitting it after launch.

MHRA / SaMD

Assessing classification under the UK Software as a Medical Device framework as patient-facing features are developed.

UKCA marking

Building toward UKCA conformity for any component that meets the medical device threshold.

UK GDPR & DPIA

Data protection impact assessment and UK GDPR compliance built into the pipeline design, not added later.

Clinical governance

Early engagement with medical defence organisations ahead of any patient-facing deployment.

Get in touch

Building the clinical data layer for the next generation of care.

We're raising to expand the transcript pipeline and bring the first fine-tuned model to clinic.

hello@opsense.health