Sunteți pe pagina 1din 18

WHAT IS THYROID DISEASE

Thyroid is a butterfly-shaped gland, which is located in front of the


neck and it makes thyroid hormones

Thyroid hormone controls many activities in our body

There are specific kinds o thyroid disorders that includes

• Causes the thyroid gland to not make


Hypothyroidism enough thyroid hormones
Thyroid Nodule
• Causes the thyroid gland to make more
Hyperthyroidism thyroid hormone than the body needs

Women are 5 to 8 times more likely than men to have thyroid


problems

Detection of the disease is difficult at early stage because a kind of


uncertainty is involved in diagnosis of the disease
FUZZY INFERENCE SYSTEM
• The term fuzzy refers to things which are not clear or are vague.
• It is a technique to embody human-like thinking into a control system.
• In the designed to deal with real world problems that involve uncertainty.
• It may not be designed to give accurate reasoning but it is designed to give acceptable
reasoning.
• One of the most important areas of application of fuzzy set theory as developed by Zadeh
is Fuzzy Rule-Based System (FRBS) also called Fuzzy Inference System.
• Fuzzy inference is the process of formulating the mapping from a given input to an output
using fuzzy logic
• Any uncertainties can be easily dealt with the help of fuzzy logic.
• Flexible and easy to implement machine learning technique.
• For example, here we are presenting a fuzzy inference system that will diagnose the
thyroid disease specially a major disorder known as Hypothyroidism
MAMDANI’S FUZZY INTERFACE METHOD
• Membership Function: a membership function for a fuzzy set A on the universe of
discourse X is defined as
µA:X → [0,1]
where each element of X is mapped to a value between 0 and 1. This value, called
membership value or degree of membership, quantifies the grade of membership of
the element in X to the fuzzy set A.
Very
Yes/1
Much/0.9

Is it Cold ? Is it Cold ? Little/0.25


Very
No/0
Less/0.1

Boolean Logic Fuzzy Logic


ARCHITECTURE OF FUZZY SYSTEM
Rule
Rulebase
base

Data base

Crisp Input Knowledge base


Crisp Output
(T3,T4,T3RU,
(class)
TSH,diff)
Fuzzifier Defuzzifier

Inference
engine
APPLICATION OF FUZZY LOGIC IN DIAGNOSING DISEASE

The concept of fuzzy logic was first introduced by Zadeh


in 1965.

The application of Fuzzy Logic in medicine started in


the early 70’s.

Initially Fuzzy member functions were added to rule-


based expert systems

New generation of membership function using


Machine learning techniques for knowledge
representation and medical decision support.
MACHINE LEARNING
It is is the field of study that gives computers the capability to
learn without being explicitly programmed

It gives the computer thae ability which makes it more similar


to humans: The ability to learn

A major focus of machine learning research is to automatically


learn to recognize complex patterns and make intelligent
decisions based on data

Supervised
learning
Machine
learning
Unsupervised
learning
SUPERVISED LEARNING
output of the network is
matched the teacher
information. output of the
network is matched the
teacher information.

supervised
learning

Classification Regression
UNSUPERVISED LEARNING

Unsupervised learning
does not require an
instructor

Unsupervised
learning

Clustering Association
CLUSTERING

Clustering is the assignment of


a set of observations into
subsets (called clusters) so that
observations in the same
cluster are similar in some
sense

Clustering is a method of
unsupervised learning, and a
common technique for
statistical data analysis used in
many fields
ALGORITHM USED FOR CLUSTERING
 Fuzzy c-means clustering algorithm
 Fuzzy c-means (FCM) is a method of clustering which allows one piece of data to belong to two or
more clusters.
 This method is frequently used in pattern recognition. It is based on minimization of the following
objective function:

Where,
m is any real number greater than 1,
uij is the degree of membership of xi in the cluster j,
xi is the ith of d-dimensional measured data,
cj is the d-dimension center of the cluster
and ||*|| is any norm expressing the similarity between any measured data and the center.
ALGORITHM USED FOR CLASSIFICATION
 Fuzzy partitioning is carried out through an iterative optimization of the objective function shown
above, with the update of membership uij and the cluster centres cj by:

 This iteration will stop when

where is a termination criterion between 0 and 1, whereas k are the iteration steps.
ALGORITHMIC STEPS FOR FUZZY C-MEANS CLUSTERING
1. Initialize U=[uij] matrix, U(0)

2. At k-step: calculate the centres vectors C(k)=[cj] with U(k)

3. Update U(k) , U(k+1

4. If then STOP; otherwise return to step 2.


COMPONENT BREAKDOWN FOR THE PROPOSED
SYSTEM
Class T3 T4 T3RU TSH Difference
0 = normal Resin uptake Total serum T3-resin uptake Basal thyroid- Maximal
1 = hyper test(percentage) triiodothyronine test stimulating absolute
2 = hypo hormone (TSH) difference of TSH
as measured by value after
radioimmunoass injection of 200
ay micro grams of
thyrotropin
releasing
hormone as
compared to the
basal value
PREPARING THE DATASET

Step 1 Step 2 Step 3

Process the Transform the


Select the
data data
data

UCI Formatting Scaling

KAGGLE Cleaning Decomposition

NCBI Aggregation
Sampling
STEPS FOLLOWED IN THE SYSTEM
Step-1 : Importing the dataset and preprocessing the data.
Step-2 : Input number of clusters , fuzziness factor and number of iteration.
Step-3 : Randomly create a membership matrix U satisfying the sum of the elements
equal 1
Step-4 : Compute the centroid of clusters.
Step-5 : Calculate the Euclidean distance between each data object and centriod .
Step-6 : Update the membership matrix.
Step-7 : Assign the data object to the membership matrix which is maximum.
Step-8 : Calculate the objective function.
Step-9 : Repeat steps 3 to 8 until change of membership matrix is very small.
Step-10: Train the dataset by using the above steps through 3 to 9.
Step-11: Predict the clusters .
Step-12: Calculate the Accuracy , Precision of the predicted outcome.
CONCLUSION
In this study, a fuzzy rule-based expert system for diagnosing hypothyroidism disorder was developed

Based on this study, future developments of fuzzy control and monitoring technologies in medicine and
healthcare can be forecast

Fuzzy logic provides a means for encapsulating the subjective decision making process in an algorithm
suitable for computer implementation

Furthermore, the principles behind fuzzy logic are straightforward and its implementation in software is
relatively easy

Because of fuzzy system high interpretability, they are close to human's language, easy to interact with
human experts.to use it as a supplementary model for predicting thyroid

In less developed countries due to lack of expertise and equipment, the number of physicians per ordinary
person is very low. In such a situation, the use of an accurate predictive model can be beneficial
References

S-ar putea să vă placă și