The measurement layer for healthcare.

TimeTrace Labs builds the measurement infrastructure for healthcare: a maths-first layer for physiological signal extraction, paired with a frontier-scale world model trained on time-series.

We are a team of physicists, mathematicians, quantitative researchers, ML engineers, and neuroscientists from Oxford research roots, building calm, interpretable systems that track physiological drift across time and modalities.

Two layers, one platform for physiology.

TimeTrace Labs combines a maths-first measurement layer built for noisy, irregular biological signals with a world-model layer trained on physiological time-series.

The measurement layer provides interpretable, audit-grade descriptors at the individual level. The world model extends those descriptors into richer representations where the data supports it.

Together, they form a calm, dependable measurement infrastructure for healthcare that can track drift across diseases, modalities, and timescales.

“Particle physics extracts rare events from billions of collisions. We bring the same discipline to physiology — under the conditions that define healthcare data.”

Measurement × world model.

Both layers operate on the same physiological substrate. The measurement layer constrains; the world model amplifies. Outputs are fused — interpretable descriptors paired with learned representations, calibrated together.

Layer 01 · Measurement

A Maths-first Measurement Layer.

Built for noise, irregular sampling, and individual-level inference at low N. Every output is a calibrated descriptor — full provenance, audit-grade, interpretable by construction.

  • noise suppression · drift-aware
  • N=1 inference · low-data regime
  • full interpretability · audit trail
Layer 02 · World Model

A Frontier-scale World Model.

Representation learning trained on physiological time-series at scale — across modalities, populations, and timeframes. Amplifies signal where the data supports it; defers to measurement where it doesn't.

  • multimodal representation
  • cross-cohort transfer · self-supervised
  • signal amplification · uncertainty-aware
Combined output

Interpretable descriptors paired with learned representations, calibrated together.

7M+
Individuals
32
Different Conditions

From drift to descriptor.

Raw multimodal time-series enter on the left. The measurement layer constrains noise; the world model lifts representation. Calibrated descriptors leave on the right — each one traceable to its origin.

One measurement layer.
Every cohort, every continent.

Trials, studies, consumer devices and health systems — past or present, single or multimodal, disease-agnostic. The platform travels with the data.

12
Active cohorts
31
Countries · contributing data
8
Modality classes
live · 31 nodes

Built for the conditions that define healthcare data.

nine primitives
across both layers
/ 01

Noise suppression

Adaptive filters that respect physiological priors and survive irregular sampling.

/ 02

N=1 inference

Individual-level estimates at low data, calibrated to each subject's own baseline.

/ 03

Drift detection

Slow change in physiology, surfaced before it becomes a clinical event.

/ 04

Multimodal fusion

EEG, ECG, actigraphy, glucose, voice — combined under a single representation.

/ 05

Latent traversal

World-model latents you can probe along clinically meaningful axes.

/ 06

Calibrated uncertainty

Every descriptor carries a confidence interval the world model can't override.

/ 07

Interpretability

Every output traces to a primitive. No black boxes between physiology and decision.

/ 08

Cross-cohort transfer

Representations trained on one population that hold up on another, with proof.

/ 09

Audit-grade APIs

Every call returns a versioned, signed record — built for clinical and regulatory review.

The approach generalises across diseases, data types, and scales.

/ 01
Earlier detection of disease.
Drift in physiology becomes detectable months before it crosses thresholds current instruments can resolve.
neuro · cardio
/ 02
Sharper patient stratification.
Trial enrichment by physiological phenotype, not just biomarker — shrinking variance and N.
clinical trials
/ 03
More reliable endpoints.
Continuous, calibrated, individual-level outcome measures that survive regulatory scrutiny.
regulatory · digital endpoints
/ 04
Finer measurement of drug effects.
Pharmacodynamic timescales current instruments can't resolve — visible across modalities at once.
pharmacology
/ 05
Population-scale monitoring.
Audit-grade descriptors at the cohort level for public health and health system signal.
public health

A team of physicists, mathematicians, quantitative researchers, ML engineers, and neuroscientists.

Spun out of a decade of research at the University of Oxford. We bring the discipline of fields that have learned to measure under exactly these conditions — particle physics, quantitative finance — and apply it to the conditions of biology.

Physicists & Mathematicians
06
Measurement layer · noise theory · inference at low N.
ML Engineers
07
Frontier-scale representation learning on physiological time-series.
Quant Researchers
04
Signal extraction in noise-dominated regimes — markets, then physiology.
Neuroscientists & Clinicians
05
Translation, validation, and clinical-grade endpoint design.

Bring the measurement layer to your data.

Trials, studies, consumer devices, health systems — past or present, single or multimodal, disease-agnostic. We start from what you already generate.