Patent Issued for Dynamic database updates using probabilistic determinations (USPTO 11581073): Optum Services (Ireland) Limited

2023 MAR 03 (NewsRx) -- By a News Reporter-Staff News Editor at Insurance Daily News -- A patent by the inventors MacManus, Lorcan B. (Co Kildare, IE), Neftzger, Amy (Franklin, TN, US), filed on November 8, 2019, was published online on February 14, 2023, according to news reporting originating from Alexandria, Virginia, by NewsRx correspondents.

Patent number 11581073 is assigned to Optum Services (Ireland) Limited (Dublin, Ireland).

The following quote was obtained by the news editors from the background information supplied by the inventors: “Provider classification is an important topic in relationship management for health insurance companies. Providers cover a diverse range of specializations, from inpatient hospitals to primary care physicians. Inaccurate classification can be due to data entry errors, or more likely, owing to a change in the organizational structure of the provider’s business (such as a merger or acquisition of another practice). Since provider taxonomy is not a data field required for payment of claims, very few providers update this information in corresponding systems. As a result, this data field may be unpopulated or incorrect in most systems, and current operational processes do not rely on the information provided, but instead perform manual searches into each individual provider’s billing history in order to make a taxonomy-based classification. Thus, the time required for this step may range anywhere from a few hours to several days, depending upon the systems being queried and the number of claims.

“Through ingenuity and innovation, various embodiments of the present invention make substantial improvements to the above challenges.”

In addition to the background information obtained for this patent, NewsRx journalists also obtained the inventors’ summary information for this patent: “In general, embodiments of the present invention provide methods, apparatus, systems, computing devices, computing entities, and/or the like.

“In accordance with one aspect, a method is provided. In one embodiment, the method comprises storing, by one or more processors, (a) a first record for a first provider in a datastore, wherein the first record comprises a data field with a first assigned taxonomy-based classification for the first provider from a taxonomy, (b) a second record for a first provider in the datastore, wherein the second record comprises a data field with a second assigned taxonomy-based classification for the second provider from the taxonomy, and © a third record for a third provider in the datastore, wherein the third record comprises a data field with a third assigned taxonomy-based classification for the third provider from the taxonomy; generating, by the one or more processors and one or more machine learning models, (a) for a first claim for the first provider and based at least in part on first claim data, a first plurality of predicted taxonomy-based classification scores for each classification in the taxonomy, (b) for a second claim for the second provider and based at least in part on second claim data, a second plurality of predicted taxonomy-based classification scores for each classification in the taxonomy, and © for a third claim for the third provider and based at least in part on third claim data, a third plurality of predicted taxonomy-based classification scores for each classification in the taxonomy; programmatically identifying, by the one or more processors, (a) a first predicted taxonomy-based classification for the first claim from the first plurality of predicted taxonomy-based classification scores, (b) a second predicted taxonomy-based classification for the second claim from the second plurality of predicted taxonomy-based classification scores, and © a third predicted taxonomy-based classification for the third claim from the third plurality of predicted taxonomy-based classification scores; programmatically comparing, by the one or more processors, (a) the first predicted taxonomy-based classification for the first provider with the first assigned taxonomy-based classification for the first provider, (b) the second predicted taxonomy-based classification for the second provider with the second assigned taxonomy-based classification for the second provider, © the third predicted taxonomy-based classification for the third provider with the third assigned taxonomy-based classification for the third provider; responsive to the respective comparisons, programmatically assigning, by the one or more processors, (a) an unknown condition to the first claim, (b) a match condition to the second claim, and © a not matched condition to the third claim; and responsive to assigning the unknown condition to the first claim, programmatically updating the data field of the first record with the first assigned taxonomy-based classification to the first predicted taxonomy-based classification.

“In accordance with another aspect, a computer program product is provided. The computer program product may comprise at least one computer-readable storage medium having computer-readable program code portions stored therein, the computer-readable program code portions comprising executable portions configured to store (a) a first record for a first provider in a datastore, wherein the first record comprises a data field with a first assigned taxonomy-based classification for the first provider from a taxonomy, (b) a second record for a first provider in the datastore, wherein the second record comprises a data field with a second assigned taxonomy-based classification for the second provider from the taxonomy, and © a third record for a third provider in the datastore, wherein the third record comprises a data field with a third assigned taxonomy-based classification for the third provider from the taxonomy; generate, by one or more machine learning models, (a) for a first claim for the first provider and based at least in part on first claim data, a first plurality of predicted taxonomy-based classification scores for each classification in the taxonomy, (b) for a second claim for the second provider and based at least in part on second claim data, a second plurality of predicted taxonomy-based classification scores for each classification in the taxonomy, and © for a third claim for the third provider and based at least in part on third claim data, a third plurality of predicted taxonomy-based classification scores for each classification in the taxonomy; programmatically identify (a) a first predicted taxonomy-based classification for the first claim from the first plurality of predicted taxonomy-based classification scores, (b) a second predicted taxonomy-based classification for the second claim from the second plurality of predicted taxonomy-based classification scores, and © a third predicted taxonomy-based classification for the third claim from the third plurality of predicted taxonomy-based classification scores; programmatically compare (a) the first predicted taxonomy-based classification for the first provider with the first assigned taxonomy-based classification for the first provider, (b) the second predicted taxonomy-based classification for the second provider with the second assigned taxonomy-based classification for the second provider, © the third predicted taxonomy-based classification for the third provider with the third assigned taxonomy-based classification for the third provider; responsive to the respective comparisons, programmatically assign (a) an unknown condition to the first claim, (b) a match condition to the second claim, and © a not matched condition to the third claim; and responsive to assigning the unknown condition to the first claim, programmatically update the data field of the first record with the first assigned taxonomy-based classification to the first predicted taxonomy-based classification.

“In accordance with yet another aspect, a computing system comprising at least one processor and at least one memory including computer program code is provided. In one embodiment, the at least one memory and the computer program code may be configured to, with the processor, cause the apparatus to store (a) a first record for a first provider in a datastore, wherein the first record comprises a data field with a first assigned taxonomy-based classification for the first provider from a taxonomy, (b) a second record for a first provider in the datastore, wherein the second record comprises a data field with a second assigned taxonomy-based classification for the second provider from the taxonomy, and © a third record for a third provider in the datastore, wherein the third record comprises a data field with a third assigned taxonomy-based classification for the third provider from the taxonomy; generate, by one or more machine learning models, (a) for a first claim for the first provider and based at least in part on first claim data, a first plurality of predicted taxonomy-based classification scores for each classification in the taxonomy, (b) for a second claim for the second provider and based at least in part on second claim data, a second plurality of predicted taxonomy-based classification scores for each classification in the taxonomy, and © for a third claim for the third provider and based at least in part on third claim data, a third plurality of predicted taxonomy-based classification scores for each classification in the taxonomy; programmatically identify (a) a first predicted taxonomy-based classification for the first claim from the first plurality of predicted taxonomy-based classification scores, (b) a second predicted taxonomy-based classification for the second claim from the second plurality of predicted taxonomy-based classification scores, and © a third predicted taxonomy-based classification for the third claim from the third plurality of predicted taxonomy-based classification scores; programmatically compare (a) the first predicted taxonomy-based classification for the first provider with the first assigned taxonomy-based classification for the first provider, (b) the second predicted taxonomy-based classification for the second provider with the second assigned taxonomy-based classification for the second provider, © the third predicted taxonomy-based classification for the third provider with the third assigned taxonomy-based classification for the third provider; responsive to the respective comparisons, programmatically assign (a) an unknown condition to the first claim, (b) a match condition to the second claim, and © a not matched condition to the third claim; and responsive to assigning the unknown condition to the first claim, programmatically update the data field of the first record with the first assigned taxonomy-based classification to the first predicted taxonomy-based classification.”

The claims supplied by the inventors are:

“1. A computer-implemented method comprising: identifying, by one or more processors, a taxonomy comprising a plurality of classifications; storing, by the one or more processors, (a) a first record for a first provider in a datastore, wherein the first record comprises a data field with a first assigned taxonomy-based classification for the first provider from the plurality of classifications in the taxonomy, (b) a second record for a second provider in the datastore, wherein the second record comprises a data field with a second assigned taxonomy-based classification for the second provider from the plurality of classifications in the taxonomy, and © a third record for a third provider in the datastore, wherein the third record comprises a data field with a third assigned taxonomy-based classification for the third provider from the plurality of classifications in the taxonomy, wherein the first assigned taxonomy-based classification for the first provider is selected from a group consisting of null, empty, unknown, and not populated; generating, by the one or more processors and one or more machine learning models, (a) for a first claim for the first provider and based at least in part on first claim data, a first plurality of predicted taxonomy-based classification scores, wherein the first plurality of predicted taxonomy-based classification scores comprises a predicted taxonomy-based classification score for each classification in the taxonomy, (b) for a second claim for the second provider and based at least in part on second claim data, a second plurality of predicted taxonomy-based classification scores, wherein the second plurality of predicted taxonomy-based classification scores comprises a predicted taxonomy-based classification score for each classification in the taxonomy, and © for a third claim for the third provider and based at least in part on third claim data, a third plurality of predicted taxonomy-based classification scores, wherein the third plurality of predicted taxonomy-based classification scores comprises a predicted taxonomy-based classification score for each classification in the taxonomy; programmatically identifying, by the one or more processors, (a) a first predicted taxonomy-based classification for the first claim from the first plurality of predicted taxonomy-based classification scores, (b) a second predicted taxonomy-based classification for the second claim from the second plurality of predicted taxonomy-based classification scores, and © a third predicted taxonomy-based classification for the third claim from the third plurality of predicted taxonomy-based classification scores, wherein (i) the second predicted taxonomy-based classification for the second claim is equivalent to the second assigned taxonomy-based classification for the second provider, and (ii) the third predicted taxonomy-based classification for the third claim is not equivalent to the third assigned taxonomy-based classification for the third provider; programmatically comparing, by the one or more processors, (a) the first predicted taxonomy-based classification for the first provider with the first assigned taxonomy-based classification for the first provider, (b) the second predicted taxonomy-based classification for the second provider with the second assigned taxonomy-based classification for the second provider, and © the third predicted taxonomy-based classification for the third provider with the third assigned taxonomy-based classification for the third provider; responsive to the respective comparisons, programmatically assigning, by the one or more processors, (a) an unknown condition to the first claim, (b) a match condition to the second claim, and © a not matched condition to the third claim, wherein (i) the unknown condition is assigned to any claim whose corresponding assigned taxonomy-based classification is selected from the group consisting of null, empty, unknown, and not populated, (ii) the match condition is assigned to any claim whose corresponding assigned taxonomy-based classification and respected predicted taxonomy-based classification are equivalent, and (iii) the not matched condition is assigned to any claim whose corresponding assigned taxonomy-based classification and respective predicted taxonomy-based classification are not equivalent; and responsive to assigning the unknown condition to the first claim, programmatically updating the data field of the first record with the first assigned taxonomy-based classification to the first predicted taxonomy-based classification.

“2. The computer-implemented method of claim 1 further comprising, responsive to assigning the match condition to the second claim, programmatically assigning the second claim to an electronic bypass queue.

“3. The computer-implemented method of claim 2 further comprising updating a user interface to indicate assignment of the second claim to the electronic bypass queue.

“4. The computer-implemented method of claim 1 further comprising, responsive to assigning the not matched condition to the third claim, programmatically assigning the third claim to an electronic review queue.

“5. The computer-implemented method of claim 4 further comprising updating a user interface to indicate assignment of the third claim to the electronic review queue, wherein updating the user interface comprises generating a notification.

“6. The computer-implemented method of claim 1 further comprising automatically reassigning a fourth claim assigned to an electronic review queue to a standard queue.”

There are additional claims. Please visit full patent to read further.

URL and more information on this patent, see: MacManus, Lorcan B. Dynamic database updates using probabilistic determinations. U.S. Patent Number 11581073, filed November 8, 2019, and published online on February 14, 2023. Patent URL (for desktop use only): https://ppubs.uspto.gov/pubwebapp/external.html?q=(11581073)&db=USPAT&type=ids

(Our reports deliver fact-based news of research and discoveries from around the world.)