Discovery platform

A system for evaluating a treatment with respect to progression of a disease of interest, comprising:

• one or more processors;
• a memory;
• and
• one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including instructions for:
• obtaining a plurality of baseline placebo medical images of a placebo group of subjects captured before a placebo is administered to the placebo group of subjects and a plurality of follow-up placebo medical images of the placebo group of subjects captured after the placebo is administered to the placebo group of subjects;
• generating a plurality of baseline placebo embeddings in a latent space based on the plurality of baseline placebo medical images;
• generating a plurality of follow-up placebo embeddings in the latent space based on the plurality of follow-up placebo medical images;
• inputting the plurality of baseline placebo embeddings into one or more machine learning models to obtain a plurality of predicted follow-up placebo embeddings in the latent space;
• obtaining a plurality of placebo progression embeddings based on the plurality of follow-up placebo embeddings and the plurality of predicted follow-up placebo embeddings;
• obtaining a plurality of baseline treatment medical images of a treatment group of subjects captured before the treatment is administered to the treatment group of subjects and a plurality of follow-up treatment medical images of the treatment group of subjects captured after the treatment is administered to the treatment group of subjects;
• generating a plurality of treatment placebo embeddings in the latent space based on the plurality of baseline treatment medical images;
• generating a plurality of follow-up treatment embeddings in the latent space based on the plurality of follow-up treatment medical images;
• inputting the plurality of baseline treatment embeddings into the one or more machine learning models to obtain a plurality of predicted follow-up treatment embeddings in the latent space;
• obtaining a plurality of treatment progression embeddings based on the plurality of follow-up treatment embeddings and the plurality of predicted follow-up treatment embeddings;
• and
• generating a classification model for determining whether a patient has received the placebo or the treatment based on the plurality of treatment progression embeddings and the plurality of placebo progression embeddings.