receiving, by one or more processors, user data from a plurality of pharmacy data systems, wherein the user data comprises prescription information for a patient and a prescription of the patient;

receiving, by the one or more processors, medication supply data for a medication in the prescription of the patient;

transmitting, by the one or more processors and to a computing device of the patient, one or more questions;

receiving, by the one or more processors, one or more responses from the patient to the one or more questions;

generating, by the one or more processors, a processed response based on processing the one or more responses;

determining, by the one or more processors applying a machine learning model to the user data, the medication supply data, and the processed response, a first pre-intervention adherence score for the patient and the medication at a first time in a messaging campaign;

determining, by the one or more processors and responsive to the first pre-intervention adherence score, a first intervention action;

transmitting, by the one or more processors and responsive to the first intervention action, a first intervention message to the computing device of the patient;

determining, by the one or more processors applying the machine learning model and responsive to the first intervention action, a second adherence score at a second time in the messaging campaign;

determining, by the one or more processors and responsive to the second adherence score, a change in adherence score between the first pre-intervention adherence score and the second adherence score; and

modifying, by the one or more processors and based on the change in adherence score, the machine learning model used to determine adherence scores and cadence of the messaging campaign.