Bit vector record linkage
AssigneeCerner Innovation, Inc.
InventorDouglas S. McNair
Life of this patent
Estimating the term…
Abstract
Methods, systems, and computer-readable media are provided for facilitating record matching and entity resolution and for enabling improvements in record linkage. A power-spectrum-based temporal pattern-specific weight may be incorporated into record linkage methods to enhance the record linkage accuracy and statistical performance. For example, in embodiments, a value-specific weight may be calculated from a population-based frequency of field-specific values or dichotomized values of selected phenotypic variables, and provides an opportunity to capture and measure the relative importance of specific values found in a field. A phenotypic bit-vector “fingerprint” pattern-specific weight or Bayesian power spectrum weight may be determined and incorporated into record linkage methods.
Claims20
A computer-implemented method of determining related records, the method comprising:
- retrieving a plurality of candidate health records, each candidate health record having one or more encounters, each of the one or more encounters associated with a date-time coordinate;
- for each candidate health record, sorting the one or more encounters in chronological order based on the date-time coordinates;
- determining a time difference between each serial encounter of the sorted one or more encounters, and assembling the time difference between each serial encounter as a time series;
- ranking the plurality of candidate health records;
- determining a candidate match for a first candidate health record and a second candidate health record of the plurality of candidate health records based on a threshold value applied to the ranked plurality of candidate health records;
- and merging a first candidate health record and a second candidate health record based on the candidate match.
One or more computer storage media having computer-executable instructions embodied thereon that, when executed by one or more processors, cause the one or more processors to perform a method for determining related records, the method comprising:
- retrieving a plurality of candidate health records, each candidate health record having one or more encounters, each of the one or more encounters associated with a date-time coordinate;
- for each candidate health record, sorting the one or more encounters in chronological order based on the date-time coordinates;
- determining a time difference between each serial encounter of the sorted one or more encounters, and assembling the time difference between each serial encounter as a time series;
- ranking the plurality of candidate health records;
- determining a candidate match for a first candidate health record and a second candidate health record of the plurality of candidate health records based on a threshold value applied to the ranked plurality of candidate health records;
- and merging a first candidate health record and a second candidate health record based on the candidate match.
A search system for determining related records, the system comprising:
- one or more processors;
- and one or more computer storage media storing computer-useable instructions that, when used by the one or more processors, cause the one or more processors to:
- retrieve a plurality of candidate health records, each candidate health record having one or more encounters, each of the one or more encounters associated with a date-time coordinate;
- for each candidate health record, sort the one or more encounters in chronological order based on the date-time coordinates;
- determine a time difference between each serial encounter of the sorted one or more encounters, and assembling the time difference between each serial encounter as a time series;
- rank the plurality of candidate health records;
- determine a candidate match for a first candidate health record and a second candidate health record of the plurality of candidate health records based on a threshold value applied to the ranked plurality of candidate health records;
- and merge a first candidate health record and a second candidate health record based on the candidate match.
Dependencies are inferred from the claim text.