# US 11,113,418 B2 · De-identification of electronic medical records for continuous data development > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,113,418 B2 - Document ID: US11113418B2 - Status: Granted - Kind: B2 - Application number: 16/205,423 - Filed: 2018-11-30 - Published: 2020-06-04 - Granted: 2021-09-07 - Earliest claimed: 2018-11-30 - Assignees: International Business Machines Corporation - Applicants: International Business Machines Corporation - Inventors: Corville O. Allen; Aysu Ezen Can; Roberto Delima; Robert C. Sizemore - Web page: https://patentgrep.com/patent/US11113418B2 ## CPC - G06F 21/6254: {by anonymising data, e.g. decorrelating personal data from the owner's identification} - G06F 16/81: Indexing, e.g. XML tags; Data structures therefor; Storage structures - G16H 10/60: for patient-specific data, e.g. for electronic patient records - G06F 2221/2101: Auditing as a secondary aspect - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA ## Abstract A method for de-identifying protected health information (PHI) associated with electronic medical records (EMRs) based on a common analysis structure (CAS) is provided. The method may include detecting a system event associated with a system comprising the EMRs. The method may further include in response to detecting the system event, detecting a first CAS associated with the EMRs. The method may further include extracting first CAS data associated with the first CAS, wherein the first CAS data comprises unstructured data associated with the EMRs and normalized annotations based on CAS objects that are associated with the unstructured data. The method may further include obfuscating the unstructured data associated with the first CAS. The method may also include generating a second CAS comprising the obfuscated unstructured data and a copied version of the normalized annotations, wherein the copied version of normalized annotations are correlated with the obfuscated unstructured data. ## Claims ### Claim 1 A method for providing de-identified protected health information (PHI) associated with electronic medical records (EMRs) based on a common analysis structure (CAS), the method comprising: generating a first common analysis structure (CAS) for representing the PHI associated with the EMRs, wherein generating the first CAS comprises logically representing unstructured data associated with the EMRs and including the PHI as objects to create an object-based data structure associated with the electronic medical records (EMRs), wherein the objects comprise normalized annotations; in response to detecting a system event, extracting first CAS data associated with the first CAS from one or more log files, wherein the first CAS data comprises the unstructured data and the normalized annotations based on the objects that are associated with the unstructured data; obfuscating the unstructured data associated with the first CAS based on the extracted first CAS data; and generating and providing a second CAS comprising the obfuscated unstructured data and a copied version of the normalized annotations, wherein the copied version of the normalized annotations are correlated with the obfuscated unstructured data. ### Claim 2 (depends on 1) The method of claim 1, wherein the system event is selected from a group comprising a request to access the EMRs and a system failure. ### Claim 3 (depends on 1) The method of claim 1, wherein the extracted first CAS data comprises extracted XML Metadata Interchange (XMI) files. ### Claim 4 (depends on 1) The method of claim 1, wherein obfuscating the identified unstructured data further comprises: replacing each alphanumeric character associated with the unstructured data with a designated character. ### Claim 5 (depends on 1) The method of claim 1, wherein the copied version of normalized annotations are copied based on a log correlation process that detects whether the copied version of the normalized annotations include the protected health information (PHI) as the normalized annotations are copied. ### Claim 6 (depends on 1) The method of claim 1, wherein the copied version of the normalized annotations are correlated with the obfuscated unstructured data using associated universally unique identifiers (UUIDs). ### Claim 7 (depends on 1) The method of claim 1, further comprising: enabling usage of the generated second CAS in response to the detected system event. ### Claim 8 A computer system for providing de-identified protected health information (PHI) associated with electronic medical records (EMRs) based on a common analysis structure (CAS), comprising: one or more processors, one or more computer-readable memories, one or more computer-readable tangible storage devices, and program instructions stored on at least one of the one or more storage devices for execution by at least one of the one or more processors via at least one of the one or more memories, wherein the computer system is capable of performing a method comprising: generating a first common analysis structure (CAS) for representing the PHI associated with the EMRs, wherein generating the first CAS comprises logically representing unstructured data associated with the EMRs and including the PHI as objects to create an object-based data structure associated with the electronic medical records (EMRs), wherein the objects comprise normalized annotations; in response to detecting a system event, extracting first CAS data associated with the first CAS from one or more log files, wherein the first CAS data comprises the unstructured data and the normalized annotations based on the objects that are associated with the unstructured data; obfuscating the unstructured data associated with the first CAS based on the extracted first CAS data; and generating and providing a second CAS comprising the obfuscated unstructured data and a copied version of the normalized annotations, wherein the copied version of the normalized annotations are correlated with the obfuscated unstructured data. ### Claim 9 (depends on 8) The computer system of claim 8, wherein the system event is selected from a group comprising a request to access the EMRs and a system failure. ### Claim 10 (depends on 8) The computer system of claim 8, wherein the extracted first CAS data comprises extracted XML Metadata Interchange (XMI) files. ### Claim 11 (depends on 8) The computer system of claim 8, wherein obfuscating the identified unstructured data further comprises: replacing each alphanumeric character associated with the unstructured data with a designated character. ### Claim 12 (depends on 8) The computer system of claim 8, wherein the copied version of normalized annotations are copied based on a log correlation process that detects whether the copied version of the normalized annotations include the protected health information (PHI) as the normalized annotations are copied. ### Claim 13 (depends on 8) The computer system of claim 8, wherein the copied version of the normalized annotations are correlated with the obfuscated unstructured data using associated universally unique identifiers (UUIDs). ### Claim 14 (depends on 8) The computer system of claim 8, further comprising: enabling usage of the generated second CAS in response to the detected system event. ### Claim 15 A computer program product for providing de-identified protected health information (PHI) associated with electronic medical records (EMRs) based on a common analysis structure (CAS), comprising: one or more computer-readable storage devices and program instructions stored on at least one of the one or more tangible storage devices, the program instructions executable by a processor, the program instructions comprising: program instructions to generate a first common analysis structure (CAS) for representing the PHI associated with the EMRs, wherein generating the first CAS comprises logically representing unstructured data associated with the EMRs and including the PHI as objects to create an object-based data structure associated with the electronic medical records (EMRs), wherein the objects comprise normalized annotations; in response to detecting a system event, program instructions to extract first CAS data associated with the first CAS from one or more log files, wherein the first CAS data comprises the unstructured data and the normalized annotations based on the objects that are associated with the unstructured data; program instructions to obfuscate the unstructured data associated with the first CAS based on the extracted first CAS data; and program instructions to generate and provide a second CAS comprising the obfuscated unstructured data and a copied version of the normalized annotations, wherein the copied version of the normalized annotations are correlated with the obfuscated unstructured data. ### Claim 16 (depends on 15) The computer program product of claim 15, wherein the system event is selected from a group comprising a request to access the EMRs and a system failure. ### Claim 17 (depends on 15) The computer program product of claim 15, wherein the extracted first CAS data comprises extracted XML Metadata Interchange (XMI) files. ### Claim 18 (depends on 15) The computer program product of claim 15, wherein the program instructions to obfuscate the identified unstructured data further comprises: program instructions to replace each alphanumeric character associated with the unstructured data with a designated character. ### Claim 19 (depends on 15) The computer program product of claim 15, wherein the copied version of normalized annotations are copied based on a log correlation process that detects whether the copied version of the normalized annotations include the protected health information (PHI) as the normalized annotations are copied. ### Claim 20 (depends on 15) The computer program product of claim 15, wherein the copied version of the normalized annotations are correlated with the obfuscated unstructured data using associated universally unique identifiers (UUIDs).