CLINICAL DIAGNOSIS SUPPORT METHOD AND SYSTEM BASED ON HIERARCHICAL FUZZY INFERENCE TECHNOLOGY

• US 20130246330A1
• Filed: 08/01/2011
• Published: 09/19/2013
• Est. Priority Date: 01/26/2011
• Status: Active Grant

• Current Assignee: Keimyung University
• Original Assignee: Keimyung University
• Inventors: Son, Chang Sik, Kim, Yoon Nyun, Park, Hee Joon, Seo, Suk Tae, Kim, Min Soo
• Granted Patent: US 9,195,948 B2
• Time in Patent Office: Days
• US Class Current: 706/52
• CPC Class Codes: G06N 5/048 Fuzzy inferencing
• CPC Class Codes: G06N 7/02 using fuzzy logic computing arrangements based on biological models G06N3/00; computing arrangements using knowledge-based models G06N5/00
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16H 70/60 relating to pathologies
• CPC Class Codes: G16Z 99/00 Subject matter not provided for in other main groups of this subclass

Abstract

Disclosed is a clinical diagnosis supporting method and system based on hierarchical fuzzy inference. The clinical diagnosis supporting method includes the steps of: (a) extracting check data of a plurality of check items for each of a plurality of patients from a respective check item database; (b) selecting a characteristic from the check data of each of the check items; (c) hierarchical fuzzy-inferring the check data from which the characteristic is selected, for each check item; (d) extracting a check opinion for each disease based on an output value of the fuzzy inference for each check item; and (e) making a synthetic clinical estimation based on the extracted check opinion.

Claims

1-11. -11. (canceled)

12. A clinical diagnosis supporting method based on hierarchical fuzzy inference, comprising the steps of:

(a) extracting check data of a plurality of check items for each of a plurality of patients from a respective check item database;

(b) selecting a characteristic from the check data of each of the check items;

(c) hierarchical fuzzy-inferring the check data from which the characteristic is selected, for each check item;

(d) extracting a check opinion for each disease based on an output value of the fuzzy inference for each check item; and

(e) making a synthetic clinical estimation based on the extracted check opinion.

13. The clinical diagnosis supporting method according to claim 12, wherein the check items include a blood check, a urine check and radiation check.

14. The clinical diagnosis supporting method according to claim 12, wherein the step (b) includes:

marking each check data with a result of clinical diagnosis; and

calculating a cut-off value for determination of clinical diagnosis for each check item.

15. The clinical diagnosis supporting method according to claim 12, wherein the step (c) has a hierarchical input/output structure of a plurality of fuzzy systems where an output value is generated with an output of one fuzzy system having a check data of each check item as an input and with another check data as an input, and the number of inputs of the fuzzy system is at least 3.

16. The clinical diagnosis supporting method according to claim 13, wherein the step (c) has a hierarchical input/output structure of a plurality of fuzzy systems where an output value is generated with an output of one fuzzy system having a check data of each check item as an input and with another check data as an input, and the number of inputs of the fuzzy system is at least 3.

17. The clinical diagnosis supporting method according to claim 14, wherein the step (c) has a hierarchical input/output structure of a plurality of fuzzy systems where an output value is generated with an output of one fuzzy system having a check data of each check item as an input and with another check data as an input, and the number of inputs of the fuzzy system is at least 3.

18. The clinical diagnosis supporting method according to claim 15, wherein the step (c) includes:

in each fuzzy system,

fuzzy-partitioning check data of each check item; and

generating clinical diagnosis knowledge from the partitioned check data.

19. The clinical diagnosis supporting method according to claim 16, wherein the step (c) includes:

in each fuzzy system,

fuzzy-partitioning check data of each check item; and

generating clinical diagnosis knowledge from the partitioned check data.

20. The clinical diagnosis supporting method according to claim 17, wherein the step (c) includes:

in each fuzzy system,

fuzzy-partitioning check data of each check item; and

generating clinical diagnosis knowledge from the partitioned check data.

21. The clinical diagnosis supporting method according to claim 18, wherein the fuzzy partitioning is divided into a normal group and an abnormal group based on a statistical distribution of the check data.

22. The clinical diagnosis supporting method according to claim 19, wherein the fuzzy partitioning is divided into a normal group and an abnormal group based on a statistical distribution of the check data.

23. The clinical diagnosis supporting method according to claim 20, wherein the fuzzy partitioning is divided into a normal group and an abnormal group based on a statistical distribution of the check data.

24. The clinical diagnosis supporting method according to claim 15, wherein the generation of clinical diagnosis knowledge includes the steps of:

generating primary clinical diagnosis knowledge from the divided check data; and

generating secondary clinical diagnosis knowledge applied to each hierarchical fuzzy system by applying an algorithm to avoid collision between the primary clinical diagnosis knowledge.

25. The clinical diagnosis supporting method according to claim 16, wherein the generation of clinical diagnosis knowledge includes the steps of:

generating primary clinical diagnosis knowledge from the divided check data; and

generating secondary clinical diagnosis knowledge applied to each hierarchical fuzzy system by applying an algorithm to avoid collision between the primary clinical diagnosis knowledge.

26. The clinical diagnosis supporting method according to claim 17, wherein the generation of clinical diagnosis knowledge includes the steps of:

generating primary clinical diagnosis knowledge from the divided check data; and

generating secondary clinical diagnosis knowledge applied to each hierarchical fuzzy system by applying an algorithm to avoid collision between the primary clinical diagnosis knowledge.

27. The clinical diagnosis supporting method according to claim 24, wherein the step (e) includes:

extracting clinical characteristics and criterions presented in each inference layer;

extracting an abnormal case from data of each inference layer; and

making synthetic clinical inference based on the clinical characteristics and criterions and the abnormal case.

28. The clinical diagnosis supporting method according to claim 25, wherein the step (e) includes:

extracting clinical characteristics and criterions presented in each inference layer;

extracting an abnormal case from data of each inference layer; and

making synthetic clinical inference based on the clinical characteristics and criterions and the abnormal case.

29. The clinical diagnosis supporting method according to claim 26, wherein the step (e) includes:

extracting clinical characteristics and criterions presented in each inference layer;

extracting an abnormal case from data of each inference layer; and

making synthetic clinical inference based on the clinical characteristics and criterions and the abnormal case.

30. A clinical diagnosis supporting system using hierarchical fuzzy inference to perform a method according to claim 12, comprising:

a check database storing at least one check data for one or more check items;

a pre-processing unit which selects characteristic data for each check item from the database;

a fuzzy inference unit which performs hierarchical fuzzy inference with the characteristic data for each check item as an input; and

a synthetic estimation unit which makes a synthetic clinical estimation based on a check opinion for each check item, which is extracted through the fuzzy inference.

31. The clinical diagnosis supporting system according to claim 30, wherein the synthetic estimation unit provides clinical characteristics and criterions based on output values of each inference layer.

32. The clinical diagnosis supporting system according to claim 30, wherein an abnormal case is extracted based on output values of each inference layer.