Vision

Access to clinical datasets is usually restricted by data owners. This results in lengthy legal/ethical approvals and additional data processing efforts. AETIONOMY proposed a way out of this dilemma by the generation of free, virtual patient cohorts.

Our rationale is as follows: Ultimately, all clinical studies are just data. For many of the variables measured in studies like ADNI and PPMI we actually know the distribution of values; for other variables we may quantify our a priori knowledge and assume a distribution around its known mean. The data will be introduced into forward modeling approaches (integrative cause-and-effect modeling informed by biology) and linked to generative brain network models (The Virtual Brain) to create individual Virtual Patient brain models, which produce the entire range of human brain imaging data using Monte Carlo simulations (or related methods). The virtual cohort can by challenged by real-world data any time; it can be “optimised” to fit observational data or distributions observed in ADNI or PPMI or any other cohort better, if desired. Randomizer functions, however, can be used to generate diversity in variables wherever we believe that this should be helpful and lead to better representation of what we know about real patients.