Privacy-preserving machine learning
Developing AI that learns from clinical data without that data ever being exposed or leaving its source.
Trenthos Research · Australia
Research that keeps health data where it belongs.
Trenthos Research builds privacy-preserving technology to improve how healthcare is delivered in Australia - with patient consent at the centre, and data that never leaves the country.
Hosting
Australia only
Use of data
Patient-consented
By default
De-identified
Stage
Early, pre-launch
The data shaping healthcare wasn't built here.
Much of the data and AI shaping healthcare today was built on overseas populations, in systems that move patient information far from the people it came from. Australian healthcare deserves better - locally relevant tools, developed responsibly, on infrastructure that stays on-shore.
Trenthos Research is our early-stage effort to close that gap. We are building the methods and infrastructure to advance healthcare AI without compromising the privacy of a single patient.
Areas of focus, not finished work.
These are the directions we are building toward. We describe them honestly as research themes - areas we are actively working in, not capabilities we have already delivered.
Synthetic data for medical AI
Creating realistic, fully synthetic clinical data that can support research and software testing without using real patient records.
Federated learning
Building methods to train shared models across multiple sites so everyone benefits from better tools while each site's data stays on its own premises.
Real-world evidence
Turning routine, consented, de-identified clinical information into insight that can improve care and inform practice.
Clinical decision support
Exploring tools that help clinicians make faster, better-informed decisions at the point of care.
Ophthalmic imaging analysis
Researching how imaging - OCT, fundus photography and visual fields - might be analysed to surface useful signal for clinicians, always supporting rather than replacing their judgement.
Principles before products.
These commitments come first, and everything we build is shaped by them. They are written to match the consent and privacy documents that govern how data is actually handled.
- Data stays in Australia All Trenthos infrastructure is hosted in Australian regions. Patient data does not leave the country.
- Nothing without consent Patients decide whether their de-identified information is ever used for research, and can change their mind at any time.
- De-identified by default We design our research around de-identified data and apply strong privacy protections.
- Clinics are partners, not sources Clinics and services that take part share in the outcomes - better tools, and co-authorship on research they help make possible.
- Transparency We explain what we do in plain language, and publish our methods openly where we can.
What we're learning as we build.
We write about the technical and regulatory realities of building healthcare technology in Australia - what works, what is harder than it looks, and what we are learning as we go.
-
14 Jun 2026
For clinicians
Where the clinic day goes, and the workflow that gives it back
Two hours of EHR for every hour with patients, 4,000 clicks a shift, an inbox that never empties. The evidence on documentation burden, and the workflow that answers it.
-
8 Jun 2026
For practices
Before you launch clinical AI in Australia, work out if it is a medical device
An AI scribe that only transcribes is not a medical device; one that diagnoses is. The TGA test that decides whether yours is regulated before launch.
-
1 Jun 2026
For practices
What building compliant healthcare software in Australia actually takes
The engineering underneath the word "compliant" - data residency, tenant isolation, audit, retention - and the Australian rules that decide the architecture.
A small team, building carefully.
Trenthos Research is founder-led and clinically informed. It is led by Dr Chun-Huei Liu, a clinically trained doctor building Trenthos and its first product, Lumen, with a focus on responsible health technology in Australia.
We are a small, growing team. We would rather say less and mean it than overstate where we are. As the work develops, this page will grow with it.
Working with us.
We are in the early stages, and actively interested in speaking with clinicians, researchers, and health services who share our view that better care and strong privacy are not in conflict. If that is you, we would like to hear from you.