Automated assertion reuse for improved record linkage in distributed and autonomous healthcare environments with heterogeneous trust models

Patent metadata

Field	Value
Publication number	US-9892231-B2
Application number	US-200913132949-A
Country	US
Kind code	B2
Filing date	Nov 19, 2009
Priority date	Dec 12, 2008
Publication date	Feb 13, 2018
Grant date	Feb 13, 2018

Abstract

An assertion acceptance value matrix ( 300 ) indicates the reliability of assertions, particularly assertions or decisions whether records match or do not match, made by other medical institutions in a federation of medical institutions with different patient record systems and some common patients. Records from different institutions with a high likelihood of matching or not matching are automatically matched or not matched. Those that are ambiguous are manually reviewed. The assertion acceptance value matrix is used to reduce or expedite the manual review.

First claim

Having thus described the preferred embodiments, the invention is now claimed to be:

1. A method of reusing comparisons, comprising:
at a first medical institution:
(a) receiving a record supplied by an at least one second medical institution with an input;
(b) comparing the received record with a plurality of records currently maintained by a receiving party in order to determine if any two compared records correspond to a same customer with at least one computer processor;
(c) generating a likelihood ratio based on a probability value that the compared records match with the at least one computer processor;
(d) comparing the likelihood ratio to an accept threshold and to a reject threshold, the accept threshold being different from the reject threshold with the at least one computer processor;
(e) assigning a record to an exception list stored in a central database when the record's likelihood ratio is both less than the accept threshold and is also greater than the reject threshold to an exception list with the at least one computer processor;
(f) determining whether the records on the exception list should be accepted as a match or rejected as not matching and recording the determination with the at least one computer processor;
(g) receiving assertions made by the at least one second medical institution indicative of whether records on the exception list were accepted or rejected as matching with the at least one computer processor;
(h) comparing the records on the exception list that were at least one of accepted and rejected by both the first medical institution and each of the at least one second medical institution in order to calculate an assertion acceptance value for each outside party with the at least one computer processor; and

at the central database:
(i) creating a matrix of assertion acceptance values by:
placing the name of at least one party which receives assertions on one axis with the at least one computer processor,.
placing the name of at least one party which issues the assertions on a second axis with the at least one computer processor: and
creating one cell for each intersection between the receiving axis and the issuing axis, wherein each cell contains at least one assertion acceptance value with the at least one computer processor;

(j) recording the assertion acceptance values in the matrix with the at least one computer processor for access by a federation of a plurality of medical institutions, the records being patient records of a federation of medical institutions, the institutions having different medical records systems, some patients having unmatched patient records in the medical systems of a plurality of the medical institutions; and
(k) at at least a third medical institution, retrieving the assertion acceptance value matrix from the database and utilizing the assertion acceptance value matrix to automatically accept or reject records on the exception list.

2. The method of claim 1 , where the probability value is within the in the range from 0 to 1 inclusive, where 0 represents no acceptance and 1 means the received assertion is the ground truth.

3. The method according to claim 1 , wherein each assertion acceptance value is calculated as a weighted ratio of prior common assertions determined by the receiving party and each other party.

4. The method according to claim 1 , wherein each cell in the matrix of assertion acceptance values may contain separate assertion acceptance values for a positive assertion and one for a negative assertion.

5. The method according to claim 1 , wherein the first medical institution, the at least one second medical institution, and the at least one third medical institution are members of a common federation of medical institutions and the records are patient records, the institutions having different medical record systems with different patient identifiers.

6. The method according to claim 5 , wherein the received record and an accepted record of one of the medical institutions in the federation of plurality of medical institutions are assigned a unique, federation wide medical record number.

7. The method according to claim 1 , wherein the acceptance value matrix is at least one of:
used in the likelihood ratio generating step to increase or decrease the probability in accordance with the acceptance values; or
used in the step of determining whether records on the exception list should be accepted or rejected.

8. A non-transitory computer readable medium programmed with software which when implemented by a processor performs the method according to claim 1 .

9. An assertion acceptance value matrix stored on a non-transitory computer readable medium generated by the method according to claim 1 .

10. The method according to claim 1 , further including:
performing (a)-(k) at at least one other medical institution of the federation of a plurality of medical institutions.

11. An apparatus for generating reusable comparisons, comprising:
an input of a first medical institution which receives records supplied by at least one second medical institution, the records being patient records of a federation of medical institutions including the first and the at least one second medical institution, the institutions having different medical records systems, some patients having unmatched patient records in the medical systems of a plurality of the medical institutions;
a database which stores a plurality of records;
at least one computer processor which:
(a) compares the received record with each record retrieved from the database in order to generate a likelihood ratio based on a probability that the compared records match;
(b) compares the likelihood ratio to both an accept threshold and a reject threshold,
(c) assigns a record that is between the accept threshold and the reject threshold stored in the database to an exception list for a manual determination whether the records on the exception list match;

wherein the at least one processor further:
(d) receives assertions made by the at least one second medical institution wherein the assertion comprises whether the records on the exception list were accepted or rejected as matching;
(e) compares the records on the exception list that were at least one of accepted and rejected both by the first medical institution and each of the other medical institutions in the federation in order to calculate an assertion acceptance value for each medical institution,
(f) creating a matrix of assertion acceptance values including at least one receiving axis representing the first medical institution, an issuing axis representing the at least one second medical institution. one cell for each intersection between the receiving axis and the issuing axis, wherein each cell contains at least one acceptance value; and
(g) records the assertion acceptance values in the matrix for access by a federation of a plurality of medical institutions, the records being patient records of a federation of medical institutions, the institutions having different medical records systems, some patients having unmatched patient records in the medical systems of a plurality of the medical institutions; and
wherein, at at least a third medical institution, the assertion acceptance value matrix is retrieved from the database and utilized to automaticall accept or reject records on the exception list.

12. The apparatus according to claim 11 , wherein the matrix is accessible by each medical institution in the federation of medical institutions.

13. The apparatus according to claim 1 1 , wherein each cell in the matrix contains separate assert

Assignees

• Vdovjak Richard
• Koninklijke Philips Nv

Inventors

• Vdovjak Richard

Classifications

• G16H10/60 Primary

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

• G06F19/322 Primary

  Physics · mapped topic

• G06Q50/22

  Social work or social welfare, e.g. community support activities or counselling services · CPC title

• G06Q50/24

  Physics · mapped topic

• G16Z99/00

  Subject matter not provided for in other main groups of this subclass · CPC title