Abstract: Techniques for identifying data for use in a healthcare application are described. In an example, a server can receive, via a graphical user interface (GUI), first instructions defining rule(s) associated with an outcome that is relevant to a healthcare application and second instructions defining a schema for translating the rule(s) into logical expression(s). The server can access a plurality of data entries and can apply the logical expression(s) to the plurality of data entries to identify a first data entry that satisfies the rule(s). At a substantially same time, the server can apply a model to the plurality of data entries to identify a second data entry that is predicted to be associated with the outcome. The server can generate an output identifying the first data entry and the second data entry and can utilize the output for the healthcare application.