Computer system and method for suggesting treatments for physical trauma

• US 4,839,822 A
• Filed: 08/13/1987
• Issued: 06/13/1989
• Est. Priority Date: 08/13/1987
• Status: Expired due to Fees

• Current Assignee: Synthes USA LLC (Johnson & Johnson)
• Original Assignee: 501 Synthes
• Inventors: Dormond, Kenneth, Friedman, Robert J.
• Primary Examiner(s): Ruggiero, Joseph
• Application Number:
  US07/085,511
• Time in Patent Office: 670 Days
• Field of Search: 364/513, 364/413, 364/415, 364/300, 364/200 MS File, 364/900 MS File, 364/413.01, 364/413.02, 128/630
• US Class Current: 706/45
• CPC Class Codes: A61B 10/00 Other methods or instruments for diagnosis, e.g. instruments for taking a cell sample, for biopsy, for vaccination diagnosis vaccination prophylaxis, vaccination therapy A61B17/20; Sex determination; Ovulation-period determination menstruation tables G06C3/00; Throat striking implements
• CPC Class Codes: G16H 20/30 relating to physical therapies or activities, e.g. physiotherapy, acupressure or exercising
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16H 70/20 relating to practices or guidelines
• CPC Class Codes: Y10S 128/924 using artificial intelligence
• CPC Class Codes: Y10S 706/924 Medical

Abstract

An expert system which provides one or more suggested treatments for a patient with physical trauma is disclosed. The system includes a computing device having a memory, a plurality of data bases in the memory, an application program and an inference engine program. The data bases include graphical illustrations of different types of physical trauma, and a knowledge base which contains treatment information. The application program is executed in the computing device and interactively displays a series of screens including at least some of the graphical illustrations, to elicit responses from the user concerning the specific types of physical trauma and specific characteristics of the patient. The inference engine program, which is also executed in the computing device, uses the knowledge base and information related to the responses elicited from the user, for selecting one or more suggested treatments. The application program presents the suggested treatments to the user after execution of the inference engine program.

Claims

1. An expert system for providing to a user one or more suggested treatments for a patient with physical trauma, comprising:

a computing device having a memory;

a plurality of data bases in the memory including graphical illustrations of different types of physical trauma, and a knowledge base having rules for relating trauma and patient characteristics to treatments for said different types of physical trauma;

an application program, for execution in the computing device, for interactively displaying a series of screens including at least some of the graphical illustrations, to thereby elicit responses from the user concerning the specific type of physical trauma and specific characteristics of the patient, to thereby produce a further data base containing said trauma and patient characteristics; and

an inference engine program, for execution in the computing device, for use with said rules and said further data base, for selecting the one or more suggested treatments by stepping through a forward chaining sequence of rules relating to a particular treatment, and then by stepping through a backward chaining sequence of rules, the reverse of the forward chainin sequence, in which said rules are tested, based on said trauma and patient characteristics, to determine the desirability of said particular treatment;

the application program presenting the suggested treatments to the user after execution of the inference program.

2. An expert system for providing to a user one or more suggested treatments for a patient with an orthopedic fracture, comrising:

a computing device having a memory;

a plurality of data base in the memory, including graphical illustrations of different classifications of orthopedic fractures; and

a knowledge base having rules for relating trauma and patient characteristics to treatments for said different types of physical trauma;

an aplication program, for execution by the computing device, for interatively displaying a series of screens on a display, including at least some of the graphical illustrations, to thereby elicit responses from the user concerning the specific classification of orthopaedic fracture, and specific characteistics of the patient;

to thereby produce a further data base containing said trauma and patient characteristics; and

an inference engine program, for execution in the computing device, for use with said rules and said further data base, for selecting the one or more suggested treatments by stepping through a forward chaining sequence of rules relating to a particular treatment, and then by stepping through a backward chaining sequence of rules, the reverse of the forward chaining sequence, in which said rules are tested, based on said trauma and patient characteristics, to determine the desirability of said particular treatment;

the application program presenting the suggested treatments to the user after execution of the inference program.

3. A method for providing to a user a suggested treatment for a patient having physical trauma, comprising the steps of:

creating at least one knowledge base containing rules that relate different types of physical trauma characteristics and patient characteistics to different types of treatments for physical trauma;

eliciting information from said user concerning characteristics of said patient including the type of physical trauma substained by said patient, to thereby develop at least one database containing patient and trauma characteristics;

applying said knowledge base and database to a computer; and

using said computer to infer the apropriate treatment for said patient from said rules and said database, by forward chaining, in which a sequence of rules relating to a particular treatment is established, and backward chaining, in which said sequence of rules es reversed and said rules are tested based on said trauma and patient characteristics, to determine the desirability of said particular treatment.

4. The method of claim 3, wherein said step of creating said knowledge base includes the step of creating rules that relate said trauma and patient characteristc to characteristics of said treatments, said step of forward chaining establishes a sub-sequence of rules relating to a particular treatment characteristic, and said step of backward chaining reverses said subsequence of rules, and testes said sub-sequence of rules based on said trauma and patient characteristics, to thereby determine the desirability of said particular treatment characteristic.

5. The method of claim 3, wherein said step of sliciting information concerning the type of physical trauma sustained by said patient includes the step of interactively desplaying different classifications of trauma to said user.

6. The method of claim 5, wherein the step of interactively displaying includes the step of displaying graphical representations of said classifications of trauma.

7. The method of claim 6, wherein said differeent types of trauma are orthopedic fractures.

8. The method of claim 4, wherein the step of using a computer includes the step of employing an inference engine to infer the appropriate treatment.

9. The method of claim 5, wherein the step of eliciting information includes the use of a touch-screen CRT.

10. The method of claim 3, wherein said step of using the computer to infer the appropriate treatment further includes the steps of assingning a value to each of a plurality of possible treatments, and adjusting said values according to a treatment hierarchy, wherein values assigned to specific treatments are more heavily weighted than values assigned to general treatments.

11. An expert system for providing to a user a suggested treatment for a patient having physical trauma, comprising:

at least one knowledge base containing rules that relate different types of physical trauma characteristics and patient characteristics to different types of treatments for physical trauma,

a computer for receiving said knowledge base and information from said user concerning characteristics of said patient, including the type of physical trauma sustained by said patient, to thereby develop at least one database containing patient and trauma characteristics; and

an processor within said computer to infer the appropriate treatment for said patient from said rules and said database by forward chaining, in which a sequence of rules relating to a particular treatment is established, an then by backward chaining, in which said sequence of rules is reversed and said rules are tested based on said trauma and patient characteristics, to determine the desirability of said particular treatment.

12. The expert system of claim 11, wherein said knowledge base includes rules that relate said trauma and patient characteristics to characteristics of said treatments, said forward chaining establishes a sub-sequence of rules relating to a particular treatment characteristic, and said backward chaining reverses said sub-sequence of rules an tests said sub-sequence of rules based on said trauma and patient characteristics, to thereby determine teh desirability of said particular treatment characteristic.

13. The expert system of claim 11, wherein said computer elicits information concerning the type of physical trauma sustained by said patient by interactively displaying different classification of trauma to said user.

14. The expert system of claim 13, wherein said computer displays graphical representations of said classifications of trauma.

15. The expert system of claim 14, wherein said different types of trauma are orthopedic fractures.

16. The expert system of claim 13, wherein said computer employs a touch-screen CRT.

17. The expert system of claim 11, wherein said computer assigns a value to each of a plurality of possible treatments, and adjusts said values according to a treatment hierarchy, wherein values assigned to specific treatments are more heavily weighted than values assigned to general treatments.