A system for prediction of clinical trial participation. The system includes: a processor of a participation probability node; a memory on which are stored machine-readable instructions that when executed by the processor, cause the processor to: receive a clinical trial (CT) request from a user device, parse the CT request to derive at least one CT parameter, query a patients' database based on the at least one CT parameter to store a set of potential CT participants, collect social media activity-related data for each of the potential CT participants from the set, generate a plurality of feature vectors based on the social media activity-related data of the potential CT participants, and provide the feature vectors to the machine learning module for generating a predictive model indicating a participation probability index for each of the potential CT participants.