Machine learning systems for predictive modeling and related methods

A method for training a data model to predict data states performed by a first prescription processing system of a machine learning system, the first prescription processing system in communication with a data warehouse system, the data warehouse system including a plurality of historical orders and a plurality of payer responses, wherein each of the plurality of historical orders is associated with one of the plurality of payer responses, the prescription processing system comprising a processor and a memory, the method comprising:

• receiving a first portion of the plurality of historical orders and a first portion of the plurality of payer responses;
• applying at least one data balancing operation to the first portion of the plurality of historical orders and the first portion of the payer responses;
• generating a data model of the first portion of the plurality of historical orders and the first portion of the payer responses, wherein the data model is represented by a tree-structure including a plurality of leaves, nodes, and edges;
• generating a predictive machine learning model;
• applying the predictive machine learning model to the data model to generate a trained predictor of whether a medical order requires prior authorization (“PA”), associated with order data;
• receiving a plurality of production orders;
• applying the trained predictor to the plurality of production orders to determine whether the medical order requires PA for each of the plurality of production orders;
• and
• processing the plurality of production orders with each associated PA requirement determination.

A prescription processing system in communication with a first data warehouse system, the prescription processing system comprising a first processor and a first memory, the first data warehouse system comprising a second processor and a second memory, the first data warehouse system further including a plurality of historical orders and a plurality of payer responses, wherein each of the plurality of historical orders is associated with one of the plurality of payer responses, wherein the prescription processing system is configured to:

• receive a first portion of the plurality of historical orders and a first portion of the plurality of payer responses;
• apply at least one data balancing operation to the first portion of the plurality of historical orders and the first portion of the payer responses;
• generate a data model of the first portion of the plurality of historical orders and the first portion of the payer responses, wherein the data model is represented by a tree-structure including a plurality of leaves, nodes, and edges;
• generate a predictive machine learning model;
• apply the predictive machine learning model to the data model to generate a trained predictor of whether a medical order requires prior authorization (“PA”), associated with order data;
• receive a plurality of production orders;
• apply the trained predictor to the plurality of production orders to determine whether the medical order requires PA for each of the plurality of production orders;
• and
• process the plurality of production orders with each associated PA requirement determination.