Systems and methods for processing insurance claims using agentic artificial intelligence (ai) models

A computer implemented system for processing insurance claims using agentic Artificial Intelligence (AI) models, wherein the computer implemented system comprises:

• a processor;
• and
• a memory communicably coupled to the processor, wherein the memory comprises processor-executable instructions which, when executed by the processor, cause the processor to:
• receive input data corresponding to an insurance from at least one user, wherein the input data comprises an insurance claim, a claimant history data, and a plurality of insurance policy documents;
• extract a plurality of decision rules corresponding to the received input data by processing the plurality of insurance policy documents within the received input data using a first Generative Artificial Intelligence (Gen AI) model, wherein the plurality of decision rules corresponds to a natural language data format;
• transform the extracted plurality of decision rules into a graph-based decision structure, wherein the graph-based decision structure comprises a decision tree with a plurality of nodes and a plurality of edges, and wherein each node represents a respective coverage condition obtained from the plurality of insurance policy documents;
• generate an initial result for the insurance claim by evaluating the decision tree using a second Gen AI model;
• generate a stepwise reasoning path corresponding to a traversal of the decision tree using a third Gen AI model based on the generated initial result, wherein the third Gen AI model corresponds to a chain-of-thought reasoning model;
• validate at least one of diagnosis codes, procedure codes, claimant attributes, and coverage conditions corresponding to the plurality of nodes of the decision tree by querying a pre-determined domain-specific knowledge graph, wherein the pre-determined domain-specific knowledge graph comprises relationships among the plurality of decision rules;
• detect at least one of an inconsistency in the coverage conditions and missing supporting claim data based on the generated stepwise reasoning path, results of validation and the pre-determined domain-specific knowledge graph;
• and
• generate a structured feedback for the insurance claim using the third Gen AI model, wherein the structured feedback indicates a subset of nodes requiring re-evaluation and subsequent relevant claim data to be retrieved;
• generate a final adjudication result by fine-tuning the traversal of the decision tree and updating the initial result using the second Gen AI model based on the structured feedback;
• and
• output the final result and an explanation data for the final result on a user interface of a user device.