Speed and scale
For complex diseases, existing tools like Genome Wide Association Studies (GWAS) and Machine Learning (ML) do a poor job of finding clinically relevant signal. A common response is to assemble larger and larger populations to help identify ultra-rare variants. However, this approach is slow and expensive, often only marginally effective, and can be counterproductive from a clinical relevance perspective.
By contrast, our AI and combinatorial analytics generate much deeper disease insights much faster from much smaller datasets.
We routinely work with just several hundred patient cases compared against controls, or amongst themselves, to explain a quantitative trait, for example, different levels of drug response in a clinical trial.