Systems and methods for coding information

• US 7,233,938 B2
• Filed: 04/15/2003
• Issued: 06/19/2007
• Est. Priority Date: 12/27/2002
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Dictaphone Corporation (Microsoft Corporation)
• Inventors: Titemore, Robert G., Carus, Alwin B., Ogrinc, Harry J., Heyvaert, Stefaan, Boone, Keith, Speth, David, Wilson, Brian, Fonza, Don, Macpherson, Melissa, Deplonty, Tom, Rankins, Ray
• Primary Examiner(s): Wong; Don
• Assistant Examiner(s): BROWN, SHEREE N
• Application Number:
  US10/413,405
• Publication Number:
  US 20040220895A1
• Time in Patent Office: 1,526 Days
• Field of Search: 704/9, 707 1- 5, 705 1- 3, 705/34
• US Class Current: 705/2
• 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 40/67 for remote operation
• CPC Class Codes: G16H 70/00 ICT specially adapted for the handling or processing of medical references
• CPC Class Codes: Y10S 707/99931 Database or file accessing
• CPC Class Codes: Y10S 707/99932 Access augmentation or optimizing
• CPC Class Codes: Y10S 707/99933 Query processing, i.e. searching
• CPC Class Codes: Y10S 707/99934 Query formulation, input preparation, or translation
• CPC Class Codes: Y10S 707/99935 Query augmenting and refining, e.g. inexact access

Abstract

The invention includes a medical document handling system and method and automated coding systems and methods for assigning predetermined medical codes to medical documents based on the documents'"'"' contents. The invention functions by analyzing electronic medical records and extracting medical information using natural language processing and machine learning. The system collects and amalgamates medical documentation in various formats from multiple sources and locations, normalizes the information, analyzes the information, recognizes information indicating contents corresponding to classification codes, assigns classification codes, and presents information in context correlated to medical records for billing and other purposes.

Claims

1. A method for coding at least one medical record having a format and textual content using a computer, said computer associated with at least one data storage device configured to store each said medical record, the method comprising the steps of:

receiving medical documents for coding from multiple clients, wherein the medical documents from each client are received in client-specific directories on the data storage device;

normalizing the format of the medical documents into a predetermined format, wherein the predetermined format is determined based upon information in the medical documents or based upon from which directory in the date storage device the medical documents are received;

normalizing the textual content of the medical documents;

identifying coded items in the textual content of the medical documents, wherein the coded items are identified based on a comparison of the textual content in the medical documents and a standardized classification system, the standardized classification system selected from the group consisting of;

SNOMED, ICD-9, ICD-10, ICD-9-CM, ICD-10-CM, and CPT;

filtering the coded items, wherein the coded items are filtered based on a probabilistic filter, where the probabilistic filter includes;

determining a precision threshold for each medical document;

gathering client specific probability data;

creating a probability array from the client specific probability data;

sorting probability codes from a coding table;

creating a coding index based on the client specific probability data and the sorted probability codes, where the coding index is used to determine the location of the medical document in relation to the precision threshold; and

extracting probability codes located after the precision threshold in the coding index; and

creating a coded document, wherein the coded document contains text justifying the filtered coded items, and the filtered coded items.

2. The method of claim 1 further comprising the step of identifying at least one element to be coded based upon a location of the at least one element within the medical records.

3. The method of claim 1, further comprising the step of converting the coded document into a format compatible with viewing software.

4. The method of claim 1, further comprising the step of converting the medical document to XML format.

5. A system for coding at least one medical record comprising:

a computer having a central processing unit and being configured to normalize the at least one medical record to conform to a predetermined format;

a coding engine associated with the central processing unit, the coding engine associated with at least one medical standard and being configured to identify at least one element to be coded within the at least one normalized medical record;

at least one data storage device associated with the computer, the at least one data storage device configured to store each medical record;

the computer further configured to select the coding engine based on the predetermined format the computer configured to create a coded document, wherein the coded document contains text justifying the filtered coded items, and the filtered coded items;

wherein the predetermined format is determined from information in the medical record from which directory on the computer the medical records are stored;

and wherein the at least one coding engine is further configured to assign coded items based on a probabilistic filter where the probabilistic filter includes;

determining a precision threshold for each medical document;

gathering client specific probability data;

creating a probability array from the client specific probability data;

sorting probability codes from a coding table;

creating a coding index based on the client specific probability data and the sorted probability codes, where the coding index is used to determine the location of the medical document in relation to the precision threshold; and

extracting probability codes located after the precision threshold in the coding index.

6. The system of claim 5, wherein the coding engine is a Gabriele engine.

7. The system of claim 5, further comprising an application for post-processing the coded document, the post-processing application configured to convert the coded document into a format compatible with viewing software.

8. The system of claim 5, wherein the computer is further configured to convert said normalized medical record into XML format.

9. The system of claim 5, wherein the coding engine provides ICD-9-CM codes.

10. A method for coding at least one medical record using a computer, the computer associated with at least one data storage device configured to store each medical record, the method comprising the steps of:

normalizing the at least one medical record to conform with XML format;

selecting a coding engine based on the XML format, the coding engine associated with at least one medical terminology standard, the at least one medical terminology standard selected from the group consisting of;

SNOMED, ICD-9, ICD-10, ICD-9-CM, ICD-10-CM, and CPT;

identifying at least one element to be coded within the at least one normalized medical record using a probabilistic filter, where the probabilistic filter includes;

determining a precision threshold for each medical document;

gathering client specific probability data;

creating a probability array from the client specific probability data;

sorting probability codes from a coding table;

creating a coding index based on the client specific probability data and the sorted probability codes, where the coding index is used to determine the location of the medical document in relation to the precision threshold; and

extracting probability codes located after the precision threshold in the coding index, and where

the at least one element comprising a word or a phrase, the word or phrase relating to an ailment, an allergy, a medical condition, a diagnosis, a treatment plan, or a medication;

assigning a medical code to the at least one identified element, the medical code relating to the at least one medical terminology standard; and

creating a coded medical record containing the medical code adjacent to each the identified element, the coded medical record being in XML format.