To identify relevant action items (that may ultimately be reflected as claims data) for closing an identified gap in care reflected by combinations of disparate claims data records within a claims data store, a task-based interventional system executes rule-based models to determine action items eligible for closing a particular gap in care identified based on criteria associated with one or more programs. The task-based interventional system executes one or more machine-learning models to generate care scores associated with relevant entities associated with the identified gaps in care and generates a task data object comprising data indicative of an action item to close the gap in care together with executable jobs for initiating computer-based workflows to provide data indicative of the gap in care to relevant entities.