Systems and methods for processing patient information

• US 9,710,431 B2
• Filed: 08/19/2013
• Issued: 07/18/2017
• Est. Priority Date: 08/18/2012
• Status: Active Grant

• Current Assignee: Edifecs
• Original Assignee: Health Fidelity, Inc.
• Inventors: Riskin, Daniel, Friedman, Carol
• Primary Examiner(s): Albertalli, Brian
• Application Number:
  US14/372,562
• Publication Number:
  US 20140365210A1
• Time in Patent Office: 1,429 Days
• CPC Class Codes: G06F 40/103 Formatting, i.e. changing of presentation of documents automatic justification G06F40/189; automatic line break hyphenation G06F40/191
• CPC Class Codes: G06F 40/279 Recognition of textual entities
• CPC Class Codes: G06F 40/284 Lexical analysis, e.g. tokenisation or collocates
• 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: G16Z 99/00 Subject matter not provided for in other main groups of this subclass

Abstract

Systems and methods described herein are for transforming narrative content into structured output. In some embodiments the narrative content is processed using a natural language processing (NLP) engine and a clinical model. The structured output can include a section, a clinical assertion, and a plurality of elements, wherein the elements may include section elements and clinical assertion elements that annotate the section and clinical assertions respectively. The elements can be labeled based on the clinical model.

Claims

1. A method for transforming narrative content into structured output that defines where individual information resides within the output, the method comprising the steps of:

receiving narrative content;

scanning the narrative content using a natural language processing engine to identify at least one section and at least one clinical assertion within that section;

extracting information from the narrative content, wherein the extracted information includes clinical assertions and contextual information; and

identifying one or more clinical assertion elements which define a clinical assertion and assigning a clinical assertion element label to at least one clinical assertion element of the one or more clinical assertion elements based on a clinical model, wherein the label assigned to the at least one clinical assertion element is selected from a predetermined list, wherein the list is predetermined based on a clinical assertion type.

2. The method of claim 1, further comprising a step of organizing the clinical concepts and contextual information within a schema.

3. The method of claim 1, further comprising a step of integrating the structured output with at least one of an application component, infrastructure application, application, and end-user application.

4. The method of claim 1, further comprising a step of storing or using the information within an electronic health record, data warehouse, or health information exchange.

5. The method of claim 1, further comprising a step of providing processed unstructured data to an application for one of analytics, quality measures, regulatory compliance, revenue cycle management, quality improvement, and cost reduction.

6. The method of claim 1, wherein the section is a heading within the narrative content that provides context for subsequent text.

7. The method of claim 1, wherein the clinical assertion describes clinical information related to a patient.

8. The method of claim 1, wherein the at least one clinical assertion elements include section elements, and wherein a section label is assigned to a first section element of the section elements, the section label describing at least one of title, text, and code.

9. The method of claim 8, further comprising a step of identifying a secondary section element that qualifies or modifies a second section element of the section elements.

10. The method of claim 1, wherein the clinical assertion element label qualifies or modifies a clinical assertion element of the clinical assertion elements.

11. The method of claim 10, wherein the clinical assertion element label is identified from a subset of properties, wherein the subset of properties is determined based on a clinical assertion type.

12. The method of claim 11, wherein the subset of properties includes groups of related properties.

13. The method of claim 1, wherein property groups assigned to a clinical assertion are determined by a clinical assertion type.

14. A method for transforming narrative content into structured output that defines where individual information resides within the output, the method comprising the steps of:

receiving narrative content;

scanning the narrative content using a natural language processing engine to identify one section, one clinical assertion within that section, and one element that annotates at least one of the section and the clinical assertion;

extracting information from the narrative content including the section, the clinical assertion, and the element; and

describing the element with a label selected from a predetermined list of labels within a clinical model, wherein the predetermined list of labels differs according to a type of information to be described.

15. The method of claim 14, further comprising a step of organizing the section, clinical assertion, and element within an XML schema.

16. The method of claim 14, further comprising a step of integrating the structured output with at least one of an application component, infrastructure application system, application, and end-user application.

17. The method of claim 14, further comprising a step of storing or using the information within at least one of an electronic health record, data warehouse, or health information exchange.

18. The method of claim 14, further comprising a step of providing processed unstructured data to an application for analytics, quality measures, regulatory compliance, revenue cycle management, quality improvement, and cost reduction.

19. The method of claim 14, wherein the section is a heading within the narrative content that provides context for subsequent text.

20. The method of claim 19, wherein the subsequent text includes at least one clinical assertion.

21. The method of claim 20, wherein the at least one clinical assertion is an assertion within the narrative content that describes clinical information related to a patient.

22. The method of claim 14, further comprising a step of identifying at least one secondary element that modifies the element.

23. The method of claim 14, wherein the predetermined list of labels within the clinical model differs according to a clinical assertion type of the clinical assertion.