Medicine should not be one-size-fits-all
We use the latest advances in Bayesian computing, Probabilistic Programming, and Decision Theory to bridge the gap between data, models, and decision makers. Our models make predictions and support decisions for individuals, subgroups, trials, and disease populations.
Why Us?
Usability
Our platform makes models usable by non-statisticians -- models become useful when they are used by people who have to make decisions.
Algorithms
Recent advances in computational statistics allow us to tackle models previously thought too difficult due to non-linearities and the number of unknowns.
Predictive Accuracy
In-sample predictions are easy. Our models make well calibrated predictions out of sample: for a new patient, a new study arm, and even a new trial.
Interpretability
Our models are generative, transparent, explainable, and testable. In contrast to black box methods, we know what these models are doing.
Small Data
Our models work well in the small data regime, such as in platform trials in Oncology and Rare Diseases, where we need to take advantage of information external to the clinical trial.
Model Types
Pharmacometric Models
Using Ordinary Differential Equation (ODE) solvers we encode how the drug diffuses through different parts of the body.
Learn More
Joint Survival Models
Linking the model for the hazard with submodels for individual biomarkers. Joint models for comorbidities.
Learn More
Genomic Models
Retain proper uncertainties and produce more accurate predictions than popular tools like Lasso and PCA.
Learn More
Personalized Brain Network Models
Used in modeling the brain dynamics of epileptic seizures with stochastic differential equations.
Learn More
