Duplication detection in clinical documentation

• US 9,921,731 B2
• Filed: 12/31/2014
• Issued: 03/20/2018
• Est. Priority Date: 11/03/2014
• Status: Active Grant

• Current Assignee: Cerner Innovation, Inc. (Oracle Corporation)
• Original Assignee: Cerner Innovation, Inc. (Oracle Corporation)
• Inventors: Finn, Christopher S., Kolm, Margaret C., O'Larte, David J., Crooks, Steven S.
• Primary Examiner(s): Le, Debbie
• Application Number:
  US14/587,695
• Publication Number:
  US 20160125169A1
• Time in Patent Office: 1,175 Days
• CPC Class Codes: G06F 16/1748 De-duplication implemented within the file system, e.g. based on file segments de-duplication techniques in storage systems for the management of data blocks G06F3/0641
• CPC Class Codes: G06F 16/2358 Change logging, detection, and notification replication G06F16/27
• CPC Class Codes: G06F 16/24556 Aggregation; Duplicate elimination
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/2477 Temporal data queries
• CPC Class Codes: G06F 16/248 Presentation of query results
• CPC Class Codes: G06F 16/335 Filtering based on additional data, e.g. user or group profiles filtering in web context G06F16/9535, G06F16/9536
• CPC Class Codes: G06F 16/93 Document management systems
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 3/0484 for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range
• CPC Class Codes: G06F 3/04842 Selection of displayed objects or displayed text elements G06F3/0482 takes precedence
• CPC Class Codes: G06F 40/151 Transformation
• CPC Class Codes: G06F 40/166 Editing, e.g. inserting or deleting
• CPC Class Codes: G06F 40/194 Calculation of difference between files
• CPC Class Codes: G16H 10/60 for patient-specific data, e.g. for electronic patient records
• CPC Class Codes: G16H 15/00 ICT specially adapted for medical reports, e.g. generation or transmission thereof
• CPC Class Codes: G16H 70/00 ICT specially adapted for the handling or processing of medical references

Abstract

Methods, systems, and computer-readable media are provided to detect similarities in clinical documents that might be inaccurate or inappropriate. A first clinical document and a second clinical document that are to be compared are identified. This identification of the documents is based on times associated with the first and second clinical documents, an identity of clinicians who authored the first and second clinical documents, an identity of patients associated with the first and second clinical documents, a type of the first and second clinical documents, or contents of the first and second clinical documents. The first clinical document is compared to a portion of the second clinical document. A report is automatically generated, where the report indicates the similarities between the portion of the first clinical document and the portion of the second clinical document that are potentially inaccurate or inappropriate.

Claims

1. One or more non-transitory computer-readable media having computer-executable instructions embodied thereon that, when executed by a computing device, perform a method of detecting similarities between two or more clinical documents, the method comprising:

identifying a first clinical document;

identifying at least a second clinical document that is to be compared to the first clinical document to detect the similarities, wherein the first clinical document and the at least the second clinical document are either associated with a same patient or authored by a same clinician, and wherein the identifying of the at least second clinical document is based on one or more of,

(A) times associated with the first and second clinical documents,

(B) an identity of one or more clinicians who authored the first and second clinical documents,

(C) an identity of one or more patients associated with the first and second clinical documents,

(D) a type of the first and second clinical documents, or

(E) contents of the first and second clinical documents;

using a set of temporal rules, identifying at least a portion of the first clinical document that is statistically likely to change;

based on the identifying the at least the portion of the first clinical document that is statistically likely to change, comparing the at least the portion of the first clinical document to at least a portion of the at least the second clinical document; and

automatically generating a report without human intervention, the report indicating, at least, the similarities between the at least the portion of the first clinical document and the at least the portion of the at least the second clinical document;

determining a relative risk of the first clinical document having inappropriate duplication from the at least the second clinical document.

2. The media of claim 1, further comprising:

identifying one or more elements in the first and the at least second clinical documents that are unlikely to be repeated; and

computing a ranking for at least one of the one or more identified elements.

3. The media of claim 1, further comprising computing a ranking for the first clinical document in relation to the at least the second clinical document.

4. The media of claim 3, wherein the ranking indicates the relative risk of the first clinical document having inappropriate duplication from the at least the second clinical document.

5. The media of claim 3, wherein the ranking is based on one or more of:

a text similarity measurement,

a quantity of identical phrases or sentences having temporal patterns,

a quantity of identical phrases or sentences that are statistically improbable to be repeated,

a quantity of identical phrases or sentences having charge-related patterns, or

a quantity of phrases or sentences describing clinical procedures or occurrences that are unlikely to repeat from the first point in time corresponding to the first clinical document to the subsequent point in time corresponding to the at least the second clinical document.

6. The media of claim 5, wherein the temporal patterns reference a point in time or a time span.

7. The media of claim 5, wherein the charge-related patterns reference details of the clinician'"'"'s visit with the patient.

8. The media of claim 5, wherein the ranking is further based on identical phrases or sentences that are repeated that occur infrequently with respect to a corpus of clinical documents.

9. A computerized method carried out by at least one server having at least one processor for detecting similarities in two or more clinical documents, the method comprising:

identifying data of a second clinical document that is same or similar to data of a first clinical document, the first clinical document and the second clinical document being associated with a same patient or being authored by a same clinician;

using a set of temporal rules, identifying one or more first clinical document portions having similar information to one or more second clinical document portions that are statistically unlikely to be repeated between the first clinical document and the second clinical document;

based on the identifying the one or more first clinical document portions having similar information to the one or more second clinical document portions, comparing the one or more first clinical document portions to the one or more second clinical document portions;

computing a ranking for the first clinical document in relation to the second clinical document, the ranking indicating a relative risk of the first clinical document having the data that is the same or similar to the data of the second clinical document, wherein the ranking is based on one or more of;

(A) a text similarity measurement,

(B) a quantity of identical phrases or sentences having temporal patterns,

(C) a quantity of identical phrases or sentences having charge-related patterns, or

(D) a quantity of phrases or sentences describing clinical procedures or occurrences that are unlikely to repeat from a first point in time corresponding to the first clinical document to a subsequent point in time corresponding to the second clinical document;

transforming the one or more first clinical document portions and the one or more second clinical document portions based on the identified data of the second clinical document that is the same or similar to the data of the first clinical document, the transformed data indicating the similarities between the first clinical document and the second clinical document; and

generating a report that includes at least the computed ranking and the transformed data indicating the similarities between the first clinical document and the second clinical document for allowing a user to quickly find and understand the similarities or differences between the two or more clinical documents.

10. The method of claim 9, wherein the identifying is based on one or more times associated with the first and second clinical documents,

an identity of one or more clinicians who authored the first and second clinical documents,

an identity of one or more patients associated with the first and second clinical documents,

a type of the first and second clinical documents, or

contents of the first and second clinical documents.

11. The method of claim 9, wherein the first clinical document is a discharge summary, an inpatient daily progress note, an outpatient clinic visit document, or is associated with a particular department corresponding to a patient visit.

12. The method of claim 9, wherein the generated report is used for an audit of clinical documents, or is used to ensure that the clinical documents are in compliance.

13. The method of claim 9, further comprising:

receiving a selection, on a user interface, of the first clinical document and the second clinical document, the selection indicating that the first clinical document and the second clinical document are to be compared to detect the similarities; and

retrieving the first clinical document and the second clinical document from an electronic storage database corresponding to the patient.

14. A system for detecting similarities in two or more clinical documents, the system comprising:

a computing device having a processor and memory, the computing device comprising;

a document identifying component configured to identify at least a first clinical document and a second clinical document that are to be compared to detect the similarities, wherein the first clinical document and the second clinical document are either associated with a same patient or authored by a same clinician, and wherein the identifying is based on one or more of,

(A) times associated with the first and second clinical documents,

(B) an identity of one or more clinicians who authored the first and second clinical documents,

(C) an identity of one or more patients associated with the first and second clinical documents,

(D) a type of the first and second clinical documents, or

(E) contents of the first and second clinical documents;

an element identifying component configured to, based on a set of temporal rules, identify one or more elements in the first and second clinical documents that are statistically likely to change;

a comparing component configured to compare at least a portion of the first clinical document to at least a portion of the second clinical document; and

a report generating component configured to automatically generate a report without human intervention, the report indicating, at least, the similarities between the at least the portion of the first clinical document and the at least the portion of the second clinical document.

15. The system of claim 14, wherein the one or more elements in the first and second clinical documents that are statistically likely to change are one or more elements that are unlikely to be repeated.

16. The system of claim 15, further comprising a ranking component configured to compute a ranking for at least one of the one or more identified elements and to compute a ranking for the first clinical document in relation to the second clinical document.

17. The system of claim 16, wherein the ranking component computes the rankings based one or more of:

a text similarity measurement,

a quantity of identical phrases or sentences having temporal patterns,

a quantity of identical phrases or sentences that are statistically improbable to be repeated,

a quantity of identical phrases or sentences having charge-related patterns, or

a quantity of phrases or sentences describing clinical procedures or occurrences that are unlikely to repeat from the first point in time corresponding to the first clinical document to the subsequent point in time corresponding to the second clinical document.

18. The system of claim 16, wherein the ranking component computes the rankings based on identical phrases or sentences that are repeated that occur infrequently with respect to a corpus of clinical documents.