Automated transformation documentation of medical data

Patent metadata

Field	Value
Publication number	US-12334199-B2
Application number	US-202117497324-A
Country	US
Kind code	B2
Filing date	Oct 8, 2021
Priority date	Dec 10, 2020
Publication date	Jun 17, 2025
Grant date	Jun 17, 2025

Abstract

Systems, methods, and storage media useful in a healthcare cloud computing platform to transform, deduplicate and store medical data from third-party databases to a patient's primary medical record in the healthcare cloud computing platform. Exemplary implementations may: load and read data from third-party databases, and determine if it is duplicative of what is in the patient's primary record. Other embodiments, provide a method for ranking medical data from two different third-party databases to determine which medical data should be written to the patient's primary medical record in the healthcare computing platform.

First claim

The invention claimed is:

1. A method for documenting transformations of medical data maintained by a healthcare cloud computing platform, the method comprising:
loading medical data from a third-party database into a healthcare cloud computing platform, the medical data comprising a first medical record and a second medical record;
identifying a medical concept included in the medical data, wherein the medical concept includes a first plurality of medical properties in the first medical record and a second plurality of medical properties in the second medical record;
transforming the medical data using a state machine having a state machine definition for the medical concept, to result in transformed medical data, by:
providing the medical data to the state machine;
determining a normalized plurality of medical properties for the medical concept according to the state machine definition; and
normalizing the first plurality of medical properties and the second plurality of medical properties according to the state machine definition to generate a first normalized plurality of medical properties for the first medical record and a second normalized plurality of medical properties for the second medical record;

mapping the transformed medical data to a primary medical record in the healthcare cloud computing platform based on the transformed medical data and the primary medical record being associated with a same patient identifier;
evaluating the first medical record and the second medical record by accessing deduplication rules for the cloud computing platform to determine if the first medical record and the second medical record satisfy a rule set for the medical concept;
if the first medical record and the second medical record satisfy the rule set:
determining whether one of the first medical record and the second medical record is in the primary record;
if the first medical record is in the primary record and the second medical record is not in the primary record: storing the second medical record in a provenance module;
if the first medical record and the second medical record are not in the primary record:
ranking the first medical record and the second medical record to determine a higher-ranking medical record and a lower-ranking medical record;
writing the higher-ranking medical record into the primary medical record; and
writing the lower-ranking medical record into the provenance module;

if the first medical record and the second medical record do not satisfy the rule set:
writing data from the first medical record and the second medical record that is not stored in the primary medical record into the primary medical record; and
storing the determination that the first medical record and the second medical record do not satisfy the rule set in the provenance module.

2. The method of claim 1 , comprising:
reconciling a first read of medical data with a second read of medical data according to a state machine definition; and
transforming a property of the primary medical record according to the reconciliation of the first read of medical data with the second read of medical data.

3. The method of claim 1 , wherein
a first read of medical data from a first, third party database is reconciled with a second read of medical data from a second, third party database utilizing state transformation rules for a standardization of the medical data, and wherein the transformation of a property of the primary medical record is determined according to the state transformation rules.

4. The method of claim 1 , wherein
a plurality of reads of medical data are performed from a plurality of third-party databases by the healthcare cloud computing platform.

5. The method of claim 4 , wherein:
the plurality of reads of medical data are ranked according to a time rule, a clinical status rule, and a verification status rule; and the method comprises transforming a property of the primary medical record based a result of the ranking.

6. The method of claim 1 , wherein the method further comprises:
providing access to the medical data from the third-party database to a user accessing the primary medical record for the patient maintained by the healthcare cloud computing platform.

7. The method of claim 1 , wherein
the medical data for the medical concept is converted to the second plurality of medical properties using a defined standard.

8. The method of claim 7 , wherein
the second plurality of medical properties includes name identifiers, medical coding, text data, date of onset, date of documentation, condition type, and diagnosis coding.

9. The method of claim 1 , wherein
the third-party database is one of a health information exchange, immunization registry, governmental healthcare registry, pharmaceutical registry, and/or third-party electronic medical record provider.

10. The method of claim 1 , wherein
the medical concept includes one or more of: a healthcare organization, practitioner, encounters, problems, encounter diagnosis, allergies, medications, immunizations, clinical notes, pathology documents, cardiology documents, radiology documents, and microbiology documents.

11. The method of claim 1 , wherein
the primary medical record is a longitudinal patient record having data from multiple third-party databases.

12. The method of claim 1 , wherein
the first plurality of medical properties comprises a third-party database identifier.

13. The method of claim 12 , further comprising:
matching the third-party database identified in the medical data to a known third party by the healthcare cloud computing platform.

14. The method of claim 1 , wherein the state machine:
creates, during a record retrieval state of the state machine, (1) a first record retrieval queue for the first medical record and a (2) a second record retrieval queue for the second medical record;
normalizes the first plurality of medical properties and the second plurality of medical properties during a normalization state of the state machine;
maps the medical data to a primary medical record in the healthcare cloud computing platform based on the medical data and the primary medical record being associated with a same patient identifier during a patient lookup state; and
evaluates the first medical record and the second medical record by accessing deduplication rules during an organization lookup state; wherein
the record retrieval state is completed before the normalization state, the normalization state is completed before the patient lookup state, and the patient lookup state is completed before the organization lookup state.

15. The method of claim 1 , wherein ranking the first medical record and the second medical record to determine a higher-ranking medical record and a lower-ranking medical record comprises:
evaluating an onset date and time rule for a medical concept;
evaluating a clinical status rule for the medical concept;
evaluating a verification status rule for the medical concept; and
storing the onset date and time, clinical status, and verification status of the higher-ranking medical record and the lower-ranking medical record in the provenance module.

16. The method of claim 15 , comprising:
multiplying a number of occurrences of the medical property by a weighting factor; wherein
the onset date and time rule comprises criteria based on an age of a medical record;
the clinical status rule provides a weighted criteria based on a status selection, the status selection being selected from: resolved, inactive, active, and null;
the verification s

Assignees

• Cerner Innovation Inc

Inventors

• Jackson Margaret M
• Teunissen Peter
• HERNANDEZ Andres
• Ger Steven
• Holder Daniel
• Smith Mark L

Classifications

• G16H10/60

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

• G06F16/215

  Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors · CPC title

• G06F16/256

  in federated or virtual databases · CPC title

• G16H15/00 Primary

  ICT specially adapted for medical reports, e.g. generation or transmission thereof · CPC title

• G06F16/258 Primary

  Data format conversion from or to a database · CPC title