System for converting medical information into representative abbreviated codes with correction capability

• US 5,809,476 A
• Filed: 03/23/1995
• Issued: 09/15/1998
• Est. Priority Date: 03/23/1994
• Status: Expired due to Term

• Current Assignee: John Kevin Ryan
• Original Assignee: John Kevin Ryan
• Inventors: Ryan, John Kevin
• Primary Examiner(s): Weinhardt, Robert A.
• Application Number:
  US08/408,603
• Time in Patent Office: 1,272 Days
• Field of Search: 395/202, 395/203, 395/204, 395/759, 395/751, 395/760, 705/2, 705/3, 705/4, 704/1, 704/9, 704/10
• US Class Current: 705/2
• CPC Class Codes: G06F 40/151 Transformation
• CPC Class Codes: G16H 70/00 ICT specially adapted for the handling or processing of medical references

Abstract

The present invention relates to a system for coding data. An example implementation is disclosed whereby the coding system is a computer program especially suited to analysing text input to the computer by for example a keyboard, optical character recognition or voice recognition. The data to be coded may, for example, comprise information relating to an event, item or operation. In the preferred form of the invention, the input data is text describing a medical diagnosis and operation which would be dictated or recorded by a surgeon subsequent to an operation being performed on a patient. The coding system of the present invention analyses each word or term of the medical information in conjunction with specialised and generalised dictionaries of words and terms, along with the relationships between individual words or terms. In this way, in addition to producing a compressed symbolic representation of the original information which may later be interrogated or used for statistical analysis, the present invention is also capable of correcting or supplementing the original information.

Claims

1. A method of coding data representing diagnoses and/or operations which is carried out by a computer in which representative codes are assigned to said data comprising the steps of:

i) inputting said data to said computer,

ii) dividing said data into sub-parts, each said sub-part being of a particular sub-part type,

iii) preliminarily grouping said sub-parts into sub-groups by introducing divisions between some sub-parts in said data, each sub-part in a particular sub-group sharing an association with all other sub-parts in said particular sub-group,

iv) examining each said sub-group for completeness in regard to each sub-group containing a predetermined distribution of sub-part types,

v) if the examination of step (iv) reveals that the sub-group is not complete, completing said sub-groups by amending the constituent sub-parts so that each sub-group contains said predetermined distribution of sub-part types, and

vi) outputting said completed sub-groups as coded data for later interrogation or analysis.

2. A method of coding data as claimed in claim 1 wherein at least one list of records is provided and said data is a sequential stream of text and wherein said step of dividing said data into sub-parts comprises parsing said data whereby each word, or group of words, of said text is differentiated by comparing each said sub-part to records in said at least one list of records, said at least one list of records also indicating the type of records in said list.

3. A method of coding data as claimed in claim 2 wherein said step of dividing said data into sub-parts includes the step of associating the name of said list of records which contained the sub-part with the sub-part.

4. A method of coding data as claimed in claim 2 wherein said step of preliminarily grouping said sub-parts into sub-groups comprises the steps of:

i) comparing each said sub-part to records in said at least one list of records, said at least one list of records also indicating the type of records in the list, and

ii) representing each sub-part by a related record in said list or by an associated related record if the sub-part matches a record in one of said lists.

5. A method of coding data as claimed in claim 2 wherein said step of completing said sub-groups comprises the steps of:

i) carrying out a first examination of any sub-parts which may have a dual meaning in order to determine their appropriate meaning in the context of the surrounding sub-parts and inserting associated records from said at least one list of records to alter said sub-part or sub-group,

ii) examining the sub-groups adjacent each said sub-group in order to extract or copy sub-parts into an incomplete sub-group, and

iii) carrying out a second examination of sub-parts which may have a dual meaning to determine their appropriate meaning in the context of the surrounding sub-parts and inserting records from said at least one list of records to alter said sub-part or sub-group.

6. A method of coding data as claimed in claim 2 wherein at least one of said at least one list of records comprise terms relating to medical applications, at least one of said at least one list of records comprises anatomical terms relating to common names or descriptions of the bodily structure, at least one of said at least one list of records comprises clinical terms relating to the treatment of patients, and at least one of said at least one list of records comprises terms relating to the position of said anatomical terms.

7. A method of coding data as claimed in claim 1 wherein said divisions are introduced into said data in order to group associated sub-parts together and the positioning of said divisions is determined by one of a predetermined set of reasons and said step of preliminarily grouping said sub-parts also includes keeping a record of the reason for the positioning of divisions between sub-groups and identifying the list in which each sub-part was found.

8. A method of coding data as claimed in claim 1 wherein said divisions are introduced into said data in order to group associated sub-parts together and the positioning of said divisions is determined by one of a predetermined set of reasons and symbolic indicative codes represent said sub-parts, and wherein said symbolic representative codes are stored in a table along with said sub-part type and said reason for the positioning of divisions between said sub-groups.

9. A method of coding data as claimed in claim 1 wherein said method also includes, for any sub-group which is in error and therefore unable to be completed during said step of completing, the step of outputting a message in order that the data corresponding to that incomplete sub-group may be re-input.

10. A method of coding data as claimed in claim 1 wherein said predetermined distribution of sub-types comprise a clinical sub-part, an anatomical sub-part and a sub-part relating to the position of said anatomical sub-part.

11. A method of coding data as claimed in claim 1 wherein said step of completing said sub-groups includes, for each sub-group, uniformly positioning said sub-parts within each said sub-group to facilitate efficient searching of said coded data wherein only the sub-part at a relevant position within said sub-group need be examined.

12. A computer programmed to analyze input data describing an event, item or operation and produce coded output to represent said input data and also attempts to correct deficiencies in said data, said program comprising:

i) means for inputting said data to said computer,

ii) means for dividing said input data into sub-parts, each said sub-part being of a particular sub-part type,

iii) means for preliminarily grouping said sub-parts into sub-groups by introducing divisions between some sub-parts in said data, each sub-part in a particular sub-group sharing an association with all other sub-parts in said particular sub-group,

iv) means for checking each said sub-group for completeness in regard to each sub-group containing a predetermined distribution of sub-part types,

v) means for determining if the means for checking reveals that the sub-group is not complete, and if not complete, for attempting to complete said sub-groups so that each sub-group contains said predetermined distribution of sub-part types by analyzing said sub-groups in relation to each other and carrying out completion operations on said sub-parts and sub-groups, and

vi) means for outputting said completed sub-groups as coded data for later interrogation or analysis.

13. A computer programmed according to claim 12 wherein at least one list of records is provided and said means for dividing said data into sub-parts comprises means for parsing said data whereby each word or phrase of said text is differentiated by comparing each said sub-part to records in said at least one list of records, said at least one list of records also indicating the type of records in said list.

14. A computer programmed according to claim 13 wherein said means for dividing said data into sub-parts includes means for associating the name of said list of records which contained the sub-part with the sub-part.

15. A computer programmed according to claim 13 wherein said means for preliminarily grouping said sub-parts into sub-groups comprises:

i) means for comparing each said sub-part to records in said at least one list of records, said at least one list of records also indicating the type of records in the list, and

ii) means for representing the sub-part by a related record in said list or by an associated related record if the sub-part matches a record in one of said lists.

16. A computer programmed according to claim 13 wherein said means for completing said sub-groups comprises:

i) means for carrying out a first examination of any sub-parts which may have a dual meaning in order to determine their appropriate meaning in the context of the surrounding sub-parts and inserting associated records from said at least one list of records to alter said sub-part or sub-group,

ii) means for examining the sub-groups adjacent each said sub-group in order to extract or copy sub-parts into an incomplete sub-group, and

iii) means for carrying out a second examination of sub-parts which may have a dual meaning to determine their appropriate meaning in the context of the surrounding sub-parts and inserting records from said at least one list of records to alter said sub-part or sub-group.

17. A computer programmed according to claim 13 wherein at least one of said at least one list of records comprise terms relating to medical applications, at least one of said at least one list of records comprises anatomical terms relating to common names or descriptions of the bodily structure, at least one of said at least one list of records comprises clinical terms relating to the treatment of patients, and at least one of said at least one list of records comprises terms relating to the position of said anatomical terms.

18. A computer programmed according to claim 12 wherein said divisions are introduced into said data in order to group associated sub-parts together and the positioning of said divisions is determined by one of a predetermined set of reasons and said means for grouping said sub-parts also includes means for keeping a record of the reason for the positioning of divisions between sub-groups and identifying the list in which each sub-part was found.

19. A computer programmed according to claim 12 wherein said divisions are introduced into said data in order to group associated sub-parts together and the positioning of said divisions is determined by one of a predetermined set of reasons and symbolic indicative codes represent said sub-parts and wherein said symbolic indicative codes are stored in a table along with said sub-part type and said reason for the positioning of divisions between said sub-groups.

20. A computer programmed according to claim 12 wherein said computer also includes, for any sub-group which is in error and therefore unable to be completed during said means for completing, means for outputting a message in order that the data corresponding to that incomplete sub-group may be re-input.

21. A computer programmed according to claim 12 wherein said predetermined distribution of sub-part types comprise a clinical sub-part, an anatomical sub-part and a sub-part relating to the position of said anatomical sub-part.

22. A computer programmed according to claim 12 wherein said means for completing said sub-groups includes, for each sub-group, uniformly positioning said sub-parts within each said sub-group to facilitate efficient searching of said representative data wherein only the sub-part at a relevant position within said sub-part need be examined.