Systems and methods for patient record matching

Patent metadata

Field	Value
Publication number	US-11515018-B2
Application number	US-202217682352-A
Country	US
Kind code	B2
Filing date	Feb 28, 2022
Priority date	Nov 8, 2018
Publication date	Nov 29, 2022
Grant date	Nov 29, 2022

Abstract

An AI record matching system includes processors that may compare patient records using one or more rules, criteria, or parameters and determine whether any of the patient records include different demographic information but include same medical information for a same person based on comparing the patient records using the one or more rules, criteria, or parameters. The processors may receive feedback data indicating an overmatching of the patient records to the same person or an undermatching of the patient records to the same person. The processors may be trained by modifying the one or more rules, criteria, or parameters based on the feedback data. The processors may iteratively repeat one or more of examining the patient records, determining whether any of the patient records include the different demographic information but the same medical information for the same person, receiving the feedback data, and training the one or more processors.

First claim

What is claimed is:

1. An artificial intelligence (AI) record matching system comprising:
one or more processors at a healthcare management system that are configured to obtain patient records having demographic information, the one or more processors configured to compare the demographic information in the patient records and determine that the demographic information in the patient records does not match,
responsive to determining that the demographic information in the patient records does not match, the one or more processors are configured to:
determine whether the demographic information in the patient records that do not match are linked with a common household by comparing the patient records using artificial neurons connected with each other in different layers,
compare a first model containing a first set of one or more rules, criteria, or parameters that include mathematical relationships between (a) the patient records that are input to the artificial neurons and (b) outputs from the artificial neurons that indicate whether the patient records match or do not match each other, the mathematical relationships including one or more of a limit on an edit distance on differences between the demographic information in the patient records, a value for a likelihood of affinity measurement between the demographic information in the patient records, or a threshold number or threshold percentage of times that the demographic information in the patient records match,
compare the records using the first set of the one or more rules, criteria, or parameters to determine:
(c) whether the demographic information in the patient records that do not match include a common first name and a same date of birth and whether the patient records indicate membership in a common health benefit plan,
(d) whether the demographic information in the patient records that do not match include personal identifiers that share at least a designated length of a character string,
(e) whether the demographic information in the patient records that do not match include a common street address name, a common postal code, and the common first name and include a combination of a street address number and the common street address name is used by no more than a designated number of people, or
(f) whether the demographic information in the patient records that do not match include the common street address name, the street address number, and the common postal code, and the combination of the street address number and the common street address name is used by no more than the designated number of people,

determine whether the demographic information in the patient records that do not match includes exclusionary intra-family overmatching data according to the first set of one or more rules, criteria, or parameters and using the artificial neurons responsive to determining that the demographic information in the patient records that do not match are linked to with the common household,
determine whether the demographic information includes the exclusionary intra-family overmatching data by using the artificial neurons to determine:
(g) whether the demographic information in the patient records that do not match include the common first name but different dates of birth that are within a designated time period of each other,
(h) whether the demographic information in the patient records that do not match includes the same date of birth but different first names that include a designated nickname, a truncated variation of the first names, or initials of the first names,
(i) whether the demographic information in the patient records that do not match include different character strings that have at least a designated length of identical characters, or
(j) whether the demographic information in the patient records that do not match includes the different first names that differ by no more than a designated edit distance,

determine that the patient records include medical information of a same person using the artificial neurons and responsive to:
determining that the demographic information in the patient records that do not match are linked with the common household but do not include the exclusionary intra-family overmatching data or
determining that the patient records do not all include the medical information of the same person responsive to determining that the demographic information in the patient records are not linked with the common household or include the exclusionary intra-family overmatching data,

repeatedly receive feedback data indicative of one or more of overmatching or undermatching the patient records to each other using the first set of one or more rules, criteria, or parameters, and
repeatedly train the artificial neurons based on the feedback data by repeatedly modifying the one or more rules, criteria, or parameters of the first set to change connections between the artificial neurons in the different layers into a modified second set of the one or more rules, criteria, or parameters that differs from the first set, the one or more processors configured to use the one or more rules, criteria, or parameters that are modified in the second set during repeated training of the connections between the artificial neurons to reduce the one or more of overmatching or undermatching of the patient records during successive iterations of the one or more processors examining the patient records.

2. The AI record matching system of claim 1 , wherein the one or more processors are configured to use the modified set of the one or more rules, criteria, or parameters as the first set of the one or more rules, criteria, or parameters during at least one of the successive iterations of the one or more processors examining the patient records, the one or more processors configured to be repeated re-trained by using the feedback data obtained following using the modified set of the one or more rules, criteria, or parameters as the first set of the one or more rules, criteria, or parameters and modifying the first set of the one or more rules, criteria, or parameters into another iteration of the modified set of the one or more rules, criteria, or parameters.

3. The AI record matching system of claim 1 , wherein the one or more processors are configured to create a database that organizes different portions of the demographic information of at least one of the records in the database, the database created by the one or more processors to include connecting data elements that each include a name and a value that indicate the patient records that match the same person, the database created by the one or more processors to indicate that the patient records that match include medical data of the same person without changing the demographic information in the patient records, the one or more processors configured to use the database that is created and the modified set of the one or more rules, criteria, or parameters during the successive iterations of examination of the patient records to determine that the patient records match the same person without repeating determining whether the demographic information in the patient records are linked with the common household and without repeating determining whether the demographic information in the patient records include the exclusionary intra-family overmatching data.

4. The AI record matching system of claim 1 , wherein the one or more processors are configured to determine whether the patient records are linked with the common household includes by identifying a first combination of the first name and the date of birth in the patient records, identifying a second combination of the first name and the date of birth in the patient records, determining whether the first combination is associated with a first address in th

Assignees

• Express Scripts Strategic Dev Inc

Inventors

• Sragow Howard M
• Kreitzman Elisa D
• Russo Steven V
• Ahmad Mateen

Classifications

• G16H10/60 Primary

  for patient-specific data, e.g. for electronic patient records · CPC title

• G06F16/355 Primary

  Creation or modification of classes or clusters · CPC title

• G06N3/08

  Learning methods · CPC title

• G06N3/04

  Architecture, e.g. interconnection topology · CPC title

• G16H40/67

  for remote operation · CPC title