Artificial-intelligence-based prescription prior authorization validation

A computerized system for analyzing prior authorization documentation comprising:

• memory hardware configured to store instructions;
• and
• processor hardware configured to execute the instructions stored by the memory hardware, wherein the instructions include:
• receiving a first set of information including a set of pages;
• determining a set of relevant pages from among the set of pages;
• determining a set of document types associated with the set of relevant pages;
• orchestrating a first optical character recognition (OCR) process on the set of relevant pages to produce a first set of digitized pages;
• orchestrating, based on the first set of digitized pages, a second OCR process on the set of relevant pages to produce a second set of digitized pages;
• based on the set of document types, selecting a set of prompts;
• prompting a machine learning model with the set of prompts to extract a set of request data from the second set of digitized pages;
• based on the set of request data, determining a set of authorization criteria;
• prompting the machine learning model with a second set of prompts associated with the set of authorization criteria to determine a set of authorization data from the second set of digitized pages;
• determining, via the machine learning model, whether the set of authorization data meets the set of authorization criteria;
• in response to a determination that the set of authorization data meets the set of authorization criteria, approving an authorization request;
• and
• in response to a determination that the set of authorization data does not meet the set of authorization criteria, rejecting the authorization request.

A non-transitory computer-readable medium comprising processor-executable instructions including:

• receiving a first set of information including a set of pages;
• determining a set of relevant pages from among the set of pages;
• determining a set of document types associated with the set of relevant pages;
• orchestrating a first optical character recognition (OCR) process on the set of relevant pages to produce a first set of digitized pages;
• orchestrating, based on the first set of digitized pages, a second OCR process on the set of relevant pages to produce a second set of digitized pages;
• based on the set of document types, selecting a set of prompts;
• prompting a machine learning model with the set of prompts to extract a set of request data from the second set of digitized pages;
• based on the set of request data, determining a set of authorization criteria;
• prompting the machine learning model with a second set of prompts associated with the set of authorization criteria to determine a set of authorization data from the second set of digitized pages;
• determining, via the machine learning model, whether the set of authorization data meets the set of authorization criteria;
• in response to a determination that the set of authorization data meets the set of authorization criteria, approving an authorization request;
• and
• in response to a determination that the set of authorization data does not meet the set of authorization criteria, rejecting the authorization request.