When research is done in clinical trials, a drug being studied might perform better if tested on a very specific and relevant set of people with the condition. A hallmark of precision medicine in general is that not all patients respond well to the drug that works best on average. The challenge is to identify this population ahead of conducting a clinical trial.

Multi-Layer Analysis enables the researcher to address the interdependencies at the level of study design. The software is easy to use.

For the user, it is a new way of thinking about the data, so we are designing the software to actually guide the researcher suggesting next layer’s content to draw from and techniques to perform on that level of the data to help identify this unique population to study. This populating is not limited to people, but can provide novel populations for many types of prospective research.

Generating a Transient Structure to Evaluate While Using Layers of Unstructured Data

On unstructured data MLA is able to automate variable formation. It can bring new contents into a unique, temporary variable that can be evaluated across layers. The identifying and auto-populating a variable can happen after transforming previous content through the addition of other data sets, parameters, variables to evaluate under; forming an unstudied data set (unstudied because it was generated through the techniques in the previous layers like those listed above).