Mathematics & statistics
Measure error, then investigate it.
MSE = Σ(ŷᵢ − yᵢ)² / n
Compare estimates with held-out observations. Report error by person, time horizon and setting; an average can conceal an important failure.
Our research
Research for a better diabetes future.
Investigating better management, earlier recognition and the biological barriers to durable treatments and potential cures.
Four foundations. One standard of rigor.
Every biomedical capability needs more than a plausible story. These foundations guide the questions we ask and the evidence we seek.
M
Mathematics & statistics
Define what is being estimated, which assumptions matter and how uncertainty will be measured.
B
Biomedicine & physiology
Connect the question to the right population, measurement and biological process.
C
Chemistry & molecular biology
Preserve the identity of compounds, assays, genetic variants and the context in which they are studied.
E
Empirical validation
Test against strong baselines, independent data and the needs of people who will use the result.
The science behind a useful answer.
We want to understand what a model can tell us, how uncertain that answer is, and whether it remains useful beyond the data it learned from.
Reading a model estimate
Concept illustration only. Points represent observations; the dashed line represents an estimate. The shaded region illustrates uncertainty, without a fitted model or numerical confidence level.
Biology gives the question context.
Which population, tissue, measurement or stage of life does this question concern? Evidence should retain that context.
Mathematics makes uncertainty explicit.
We plan to compare transparent baselines, quantify error and check how estimates behave across people and settings.
Chemistry preserves what was measured.
An ingredient, compound, genetic variant and laboratory assay are distinct pieces of evidence. Their identity and conditions matter.
Evaluation asks whether it helps.
Our standard is independent testing and a defined human use, with limitations and useful negative results reported alongside findings.
These are our research principles. This illustration does not demonstrate forecasting accuracy, clinical effectiveness or an available medical product.
Computational science
Biology asks the question. Mathematics makes it testable.
Our model research brings physiology, chemistry and statistical learning together. A useful computation must preserve what a measurement means and reveal where an explanation could be wrong.
Inside one neural unit
A small calculation. A visible result.
A neural network combines weighted inputs and nonlinear transformations. Change these dimensionless example values to see a single ReLU unit respond.
a = max(0, w · x + b)
Activation a
max(0, 1.2 × 0.8 − 0.2)
Educational arithmetic. Not a trained model or a health prediction. Bias b is fixed at −0.2; no data leaves this page.
Biomedicine & physiology
Connect patterns with mechanisms.
dQ/dt = Rᵢₙ − Rₒᵤₜ
This general conservation relationship illustrates compartment-model thinking. A physiological model also needs defined quantities, consistent units, measured parameters and experimental validation.
Chemistry & molecular biology
Keep the biological setting attached.
Compound identity, concentration, tissue, assay and exposure belong beside a finding. A cell-level observation is a starting point for investigation, not evidence of a treatment effect in people.
Empirical validation & engineering
Test the science and the system.
Independent cohorts, reproducible experiments, calibrated uncertainty and reviewer feedback guide progress. A larger neural network must earn its place against a simpler method.
How we will check a research result.
Our publication agenda spans qualified datasets, reproducible benchmarks, methods and, when appropriate, prospective clinical studies.
Reproducibility first
Traceable sources, realistic evaluation splits and clear analysis protocols make findings easier to inspect and challenge.
Useful negative results
When a complex model fails to outperform a simple one, that finding belongs in the record too.
Our research programs are proposed or in development. We do not yet have published Diabeteris clinical results.
Questions become studies.
Studies need many disciplines.
Our ambition includes collaboration with scientists, universities, clinicians and public-health researchers, with clear protocols and reproducible analysis.
Learning across disciplines
Bringing academic expertise and engineering together around a research question.
Understanding populations
Studying population patterns starts with understanding the source, context and limits of the data.
The foundation behind the work
Data. Models. Scientific understanding.
We are building a shared diabetes evidence library, the Metra model research program and Foundry’s controlled data workflows to support our research and future applications.
Research partnerships
Help build better
diabetes research.
Discuss a study, a data source or a practical need with us.
Contact us