Methods

Many of the common issues in healthcare data are addressed by Rejuve's AI platform, including how to deal with partially overlapping, sparse, and multi-modal observational data. For example, confounders in observational data, which frequently obscure causal connections, pose a challenge for scientific health studies. A confounder in statistics is a variable that influences both the dependent and independent variables, resulting in a spurious association. Confounding is a causal concept that cannot be described using correlations or associations. But Rejuve's AI is designed to make sense of this ambiguity, attempting to reconstruct the whole from observed individual causal relations proved in randomized controlled trials. Rejuve's approach to addressing this and other common issues revolves around three key concepts: Synergistic Data and Model Integration, Causation, and Decentralization.