Abstract: A patient record matching system can calculate commonality measurements for first names in patient records, and dependent on the measurements, and require different amounts of additional information in the records to match before identifying the records as matching to the same person. Optionally, the system can examine differences in birth dates between the records. The differences can be categorized based on the type of differences and then used to determine what types of other matching information must be in the records before the records are identified as matching to the same person. Optionally, the first names in the records can be identified, and additional characters may be examined to determine whether these additional characters match or are different to determine whether the records match to the same person. Optionally, linkages between wholly different names may be identified and used for later record matching.

Abstract: An AI record matching system may obtain patient records having different first names, compare demographic information in the records, determine whether the demographic information is linked with a common household, and identify nicknames by comparing the patient records using a first model. The first model may include mathematical relationships that represent different relationships among a first number of instances where the patient records have the first names that do not match, a second number of instances where the patient records having the first names that do not match but share a demographic marker, a threshold proportion of households for determining that the first names are the nicknames of each other, and a required volume of the households.

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.

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.

Abstract: Methods for determining whether different first names are nicknames of each other and are to be used for matching different patient records with the same person are provided. At least one method includes obtaining the different first names and demographic information associated with each of the different first names, determining whether at least a threshold number of instances of the patient records include pairs of the different first names each associated with a household, measuring a likelihood of affinity between the different first names in each of the pairs based on the demographic information associated with each of the different first names, comparing the likelihood of affinity with an affinity threshold, identifying the different first names in at least one of the pairs as the nicknames of each other responsive to the likelihood of affinity exceeding the affinity threshold, and updating or creating a database storing associations between the nicknames.

Abstract: A method for matching patient records with persons is provided. The method includes obtaining the patient records and determining whether various patient attributes exclusively include a single value of patient identifiers while other patient attributes do not include the same value, determining whether several patient attributes in the different patient records include a common value, determining whether name segments in the records match, determining whether a difference between last names in the records have a designated affinity, determining how common a patient name is in a population, and/or determining whether dwelling units of addresses in the records match.

Abstract: A system and method for identifying patient records within a pharmacy benefit plan that are candidates for correction are provided. The system and method identify candidate patient records that satisfy undermatch criteria. Last change dates are determined for the candidate records that satisfy the undermatch criteria. The last change dates indicate when demographic information within the candidate records last changed. Last usage dates are determined for a lesser-utilized subset of the patient identifiers in the set. A correction subset of the candidate records is prioritized for correction. The candidate records are prioritized for correction being the candidate records that satisfy the undermatch criteria, that were not corrected since the last change date, and that have the patient identifiers within the lesser-utilized subset. A portion of the correction subset is supplied to a correction engine based on prioritization of the correction subset and a capacity constraint of the correction engine.

Abstract: A method for associating patient records with one or more persons is provided. The method involves obtaining different patient records each having demographic information at a healthcare management system, determining that the demographic information in the different records do not match, and determining whether the demographic information in the different records are linked with a common household using matching rules. The method also includes determining whether the demographic information in the records includes exclusionary intra-family overmatching data. The overmatching data represent names of different persons that match each other according to the matching rules. The method also includes determining whether the different records are associated with different persons or the same person based on the common household and the overmatching data.