Translational research thread
Phenotype fingerprinting
Using clinical sequence models to identify rare, under-recognised, or hard-to-characterise disease patterns.
Clinical AI · EHR representation · research software
Chris Sainsbury
Clinician-researcher working on clinical foundation models, EHR representation learning, translational AI, and research software.
I work across medicine, machine learning, and research infrastructure. This site is a public front page for the main things I am working on: active projects, recent outputs, papers, software, and current directions.
GitHub profile shorthand: data analysis in diabetes · machine learning · sailing.
Research programme
ORCA
Treating electronic health records as a language, with implications for representation, translation, and generation.
Scientific-discovery system
NEXUS
Predicting cross-domain method transfer by learning from historical discoveries and validated transfers.
Programme-level research thread
ASCEND research arc
A linked sequence of work spanning ASCENDgpt, FlatASCEND, and ORCA.
Public-facing project
glucose.ai
A literature intelligence and discovery surface for diabetes and AI/ML work.
Research infrastructure
pi / cog workflows
Tools and workflows for keeping projects, sources, tasks, and synthesis organised in a usable working system.
recent outputs
Papers and scholarly outputs
Sparse Autoencoder Decomposition of Clinical Sequence Model Representations: Feature Complexity, Task Specialisation, and Mortality Prediction
C Sainsbury, F Dong, A Karwath
arXiv preprint arXiv:2605.04072
FlatASCEND: Autoregressive Clinical Sequence Generation with Continuous Time Prediction and Association-Based Pharmacological Testing
C Sainsbury, F Dong, K Andreas
arXiv
Implementation of a diabetes electronic health record with clinical decision support in primary care: A mixed methods study
J Dickson, S Cunningham, C Sainsbury, M Rutter, N Kanumilli, E Pearson, ...
Diabetic Medicine 43, 111-112
DIABETES2VEC: Learning routine care trajectories to identify incident diabetes risk
C Sainsbury, G Jones, A Karwath
Diabetes Technology & Therapeutics 28, 140S-141S
Causal and Active Learning-Based Counterfactual Chest X-ray Generation for Supporting Clinical Decision-Making in Lung Disease
Y Zhu, G Mohr, L Zhang, C Sainsbury, F Dong, JD Maclay, DJ Lowe, ...
Fifth Conference on Causal Learning and Reasoning
areas of work
What connects the portfolio
The portfolio spans academic papers, translational grants, scientific-discovery systems, and software for organising research. The aim is not just to build models, but to make them clinically meaningful and operationally usable.