Methods for electronically processing insurance claims and devices thereof
AssigneeMitchell International, Inc.
InventorsMichele Hibbert-Iacobacci, Valerie Lindgren, Vicki Dunbar, Susan Englehart
Life of this patent
Estimating the term…
Abstract
A method and computing apparatus for automatically identifying whether or not one or more identified injuries are related to the insurance claim which has been submitted is described. The method and computing apparatus identify injury data in an electronic medical claim data associated with a claimant based diagnosis code data, uses a classifier to determine an association between the identified injury data represented by the diagnosis code data and the initial injury data represented by the initial diagnosis code data is identified when historical claim data is determined to be present for the claimant.
Claims18
A method for determining a correlation between initial diagnosis injury and received claim injury, the method comprising:
- creating a database comprising correlations by industry experts for at least one diagnosis code in a plurality of training diagnosis codes for initial diagnosis injury and received claim injury, the correlation indicating whether the initial diagnosis injury in a historical medical claim is not caused by, caused by, or associated with the traumatic incident of a received medical claim;
- inputting the database into a plurality of classifiers, each of the plurality of classifiers specific to determining the correlations;
- for each of the plurality of classifiers, training by the data processor each of the plurality of classifiers to correlate the initial diagnosis injury and the received claim injury;
- and
- analyzing a request to process an electronic claim in the data processor and the trained plurality of classifiers to output a correlation between an injury in the received electronic medical claim and an injury present in a historical medical claim.
A computing apparatus for an association between an injury and a claim, comprising:
- a processor;
- a memory coupled to the processor;
- wherein the processor is configured to:
- create a database comprising correlations by industry experts for at least one diagnosis code in a plurality of training diagnosis codes for initial diagnosis injury and received claim injury, the correlation indicating whether the initial diagnosis injury in a historical medical claim is not caused by, caused by, or associated with the traumatic incident of a received medical claim;
- input the database into a plurality of classifiers, each of the plurality of classifiers specific to determining the correlations;
- for each of the plurality of classifiers, train by the data processor each of the plurality of classifiers to correlate the initial diagnosis injury and the received claim injury;
- and
- analyze a request to process an electronic claim in the data processor and the trained plurality of classifiers to output a correlation between an injury in the received electronic medical claim and the injury present in the historical medical claim.
A non-transitory computer-readable storage medium storing a plurality of instructions executable by one or more processors, the plurality of instructions when executed by the one or more processors cause the one or more processors to:
- create a database comprising correlations by industry experts for at least one diagnosis code in a plurality of training diagnosis codes for initial diagnosis injury and received claim injury, the correlation indicating whether the initial diagnosis injury in a historical medical claim is not caused by, caused by, or associated with the traumatic incident of a received medical claim;
- input the database into a plurality of classifiers, each of the plurality of classifiers specific to determining the correlations;
- for each of the plurality of classifiers, train by the data processor each of the plurality of classifiers to correlate the initial diagnosis injury and the received claim injury;
- and
- analyze a request to process an electronic claim in the data processor and the trained plurality of classifiers to output a correlation between an injury in the received electronic medical claim and the injury present in the historical medical claim.
Dependencies are inferred from the claim text.