Presentation is loading. Please wait.

Presentation is loading. Please wait.

Fuzzy logic and its applications in medicine Nguyen Hoang Phuong, Vladik Kreinovich International Journal of Medical Informatics Volume: 62, Issue: 2-3,

Similar presentations


Presentation on theme: "Fuzzy logic and its applications in medicine Nguyen Hoang Phuong, Vladik Kreinovich International Journal of Medical Informatics Volume: 62, Issue: 2-3,"— Presentation transcript:

1 Fuzzy logic and its applications in medicine Nguyen Hoang Phuong, Vladik Kreinovich International Journal of Medical Informatics Volume: 62, Issue: 2-3, July, 2001, pp. 165 – 173 Presented by: Zhe-Hao Chen ( 陳哲豪 ) Date:2003/11/25

2 Outline Introduction Notion of fuzzy logic Rule-based fuzzy systems in medicine Application of fuzzy logic in medicine Conclusion Comments

3 Introduction Fuzzy logic is a powerful tools for decision- marking system, such as expert system In traditional rule-based approaches, knowledge is encoded in the form of antecedent-consequent structure

4 Notion of fuzzy logic (1/4) Medical fuzziness is impreciseness: A fuzzy proposition may be true to some degree. Fuzzy logic has two different meanings Narrow sense Wide sense

5 Notion of fuzzy logic (2/4) Traditionally mathematics uses crisp properties P(x) Zadeh proposed fuzzy (non-crisp) properties. A crisp property : X  {0,1} A fuzzy property :X  [0,1] Define: a set {x|x has a property P}

6 Notion of fuzzy logic (3/4) An example of representing a medical concept “high fever” X is greater than 39 。 C  membership functoin μ(x) =1 X is less than 38.5 。 C  membership functoin μ(x) =0 X is in the interval 38.5-39 。 C  membership functoin μ(x)=[0,1]

7 Notion of fuzzy logic (4/4) T-norms used for reasoning in fuzzy medical systems T-conorms used for reasoning in fuzzy medical systems t-norm (a) a ∧ b = min( a, b)a ∨ b = (a ’ ∧ b ’ ) ’ =1 -(1 - a) ∧ (1 - b)=max(a, b) (b) a ∧ b = a. b.a ∨ b = 1 - (1 - a).(1 - b)= a + b - a. b. (c) a ∧ b = max(a + b - 1,0)a ∨ b = min( a + b, 1) t-conorms (d) a ∨ b = max(a, b)a ∧ b = 1 - (1 - a) ∨ (1 - b)=min(a, b) (e) a ∨ b = a + b-a. ba ∧ b = 1 - (1 - a).(1 - b) = a. b. (f) a ∨ b = min(a + b, 1)a ∧ b = max(a + b - 1, 0)

8 Rule-based fuzzy systems in medicine (1/2) If-Then rules in the rule base of expert systems. If X 1 is A 1,…,X n is A n then z is C. μ cond =μA 1 (X 1 ) ∧ … ∧ μA n (X n ). μ rule =μ cond ∧ μ c (z). μ(z)=μ r1 (z) ∨ … ∨ μ rn (z).,i.e.

9 Rule-based fuzzy systems in medicine (2/2) In rule-based fuzzy systems in medicine IF x is A, and y is B, then z is C x is patient’s pain, A is “severe” y is patient’s age, B is “old” z describes treatment time, C is “long time”

10 Application of fuzzy logic in medicine (1/4) DoctorMoon Programmed in Borland Delphi 4.0 Knowledge base Managed by Borland Paradox Database Consisting of 700 records Knowledge acquisition Provided by doctors in the VNITLD Program is automatically formed Patient database Stores all patient’s medicine record information

11 Application of fuzzy logic in medicine (2/4) Developing the reasoning engine Input data: the symptoms form patients Search all rules that match the input data

12 Application of fuzzy logic in medicine (3/4) Diagnosing more than one disease DoctorMoon is able to diagnose an unlimited of disease Upgrade the DoctorMoon’s knowledge base and rules Explaining the diagnostic results DoctorMoon records all the reasoning steps in the patient’s record and stored in the patient database

13 Application of fuzzy logic in medicine (4/4) Testing and evaluation DoctorMoon has undergone several tests in the VNITLD System was given the clinical status form patients’ record storage Experts gave DoctorMoon some special combinations of symptoms as some rare special patient

14 Conclusion A medical expert system combining disease diagnosis of Western medicine and Eastern medicine such as for diagnosis of Lung Disease using fazzy logic DoctorMoon’s diagnoses were acceptable In order to improve the system’s performance, knowledge base needs to be strengthened

15 Comments Knowledge base is the key component of the system It’s not to explain the fuzzy logic in it’s system clearly Don’t depend on the expert system excessively


Download ppt "Fuzzy logic and its applications in medicine Nguyen Hoang Phuong, Vladik Kreinovich International Journal of Medical Informatics Volume: 62, Issue: 2-3,"

Similar presentations


Ads by Google