top of page

Models to Enable Clinical Decision-Making

Our Model Types

Joint Outcome-Biomarker Models

Generable Website Design2.png

Linking the model for the hazard with submodels for individual biomarkers. Joint models for comorbidities.

In Phase II and Phase III these models inform the risk of an event by incorporating individual patients’ biomarker evolution, which may be governed by a complex non-linear process. During biomarker selection, these models help quantify biomarkers' impact on clinical endpoints. 

Main Challenge

Nonlinear process dynamics, predicting for the study arm, individual patients, and biomarker 

Our Unique Solution

Non-parametric and semi-mechanistic biomarker models, hierarchical models with external controls, causal estimands, and post-stratification to adjust for the differences between the sample and the population

Complex PK/PD Models

Generable Website Design.png

Using Ordinary Differential Equation (ODE) solvers we encode how the drug diffuses through different parts of the body.

These models are often used in preclinical and Phase I trials in order to establish safe dosing regimens. While safety is the main concern, we strive to detect signs of early efficacy.

Main Challenge

Small data and non-linear system dynamics

Our Unique Solution

We are able to infer both the population and individual level parameters and present it to non-specialists in an easily interpretable form.

Biomarker Screening Models


Using modern non-parametric Bayesian methods like lgpr and BART, allowes us to flexibly model the data-generating process.

This is the wide data of the big data spectrum. Traditional machine learning approaches including clustering and dimensionality reduction are unlikely to uncover meaningful clinical relationships.

Main Challenge

Too many possible combinations frequently guide the researchers to confuse signal with noise.

Our Unique Solution

Using better priors and Bayesian non-parametrics increases our chances of finding the best biomarker candidates while retaining inferential uncertainty, and guarding against over-confidence

bottom of page