A Classification Approach for Effective Noninvasive Diagnosis of Coronary Artery Disease

1
A Classification Approach for Effective
Noninvasive Diagnosis of Coronary Artery Disease

• Advisor??? ??
• Student??? D95402001
• ???D95402005
• ???D95402007

2
Outline

• Background
• Motivation
• The Data Mining Process
• Conclusion
• Limitation

3
Background

• Heart disease is the leading cause of death in
  Taiwan.
• The third on the rank of the number of people
  died
• The number of people died is 12,970
• The death rate is 57.1 per one hundred thousand
  people
• Coronary artery disease (CAD) is the most common
  type of heart disease.

4
The illustration of CAD
Source http//images.medicinenet.com/images/illus
trations/heart_attack.jpg
5
The Diagnosis of CAD

• Noninvasive approaches
• Laboratory tests
• Electrocardiogram (ECG)
• Ultrasound tests
• Invasive approach
• Coronary angiography

6
The Important Risk Factors of CAD

• Smoking
• High blood pressure
• High blood cholesterol
• Diabetes
• Being overweight or obese
• Physical inactivity

7
Motivation

• Invasive approach is higher risk and cost than
  noninvasive approach
• Is noninvasive approach is sufficient to diagnose
  the possibility of occurring CAD?
• Whats the performance of noninvasive approaches?

8
Motivation

• Invasive approach is higher risk and cost than
  noninvasive approach
• Is noninvasive approach is sufficient to diagnose
  the possibility of occurring CAD?
• Whats the performance of noninvasive approaches?

9
The Data Mining Procedure Step 1

• Use some medically examinations to predict
  whether some people have heart disease.
• A Classification problem

10
The Data Mining Procedure Step 2

• UCI KDD archive web
• Those row data come from three hospitals in
  United States

11
The Data Mining Procedure Step 3
Attributes Range
age Min28 Max77 Average54
Sex Male1 Female0
Chest pain type 1Typical angina 2Atypical angina 3Non- angina pain 4Asymptomatic
resting blood pressure 0,120 0 121, 8) 0
cholestoral 0 gt200 1 200,240) 2 gt240
fasting blood sugar 0 lt120 1 gt120
electrocardiographic 0Normal 1Having ST-T wave abnormality 2Left ventricular hypertrophy
maximum heart rate 60,138
Attributes Range
exercise induced angina Yes 1 No 0
ST depression induced by exercise
The slope of peak exercise ST segment Upsloping 1 flat 2 Downsloping 3
resting blood pressure gt120 1 lt120 0
Number of major vessels 0,1,2,3
thal Normal 3 Fixed defect 6 Reversable defect 7
diagonsis lt 50 diameter narrowing 0 gt 50 diameter narrowing 1
12
The Data Mining Procedure Step 4

• Source UCI KDD Archive
• Training set Cleveland Clinic Foundation, 303
  records
• Testing set Hungarian Institute of Cardiology,
  294 records

13
The Data Mining Procedure Step 5

• The Problem of data
• Missing Value
• Approach
• Discard the records containing missing values

14
The Data Mining Procedure Step 6

• Skip this step due to the uselessness of
  aggregating records or combining original
  attributes

15
The Data Mining Procedure Step 7

• In order to obtain rules from models to support
  medical decision
• Decision tree C4.5 and Bays Network are used as
  our data mining approaches
• WEKA is used as our data mining tool

16
The Data Mining Procedure Step 7 (Cont.)

• WEKA tools screenshot

17
The Data Mining Procedure Step 8

• In order to assess the models, we conduct two
  phrases experiments with comprehensive measures
  which include sensitivity, specificity and
  accuracy.

18
The Data Mining Procedure Step 8 (Cont.)

• First Phrase
• The diverse combinations of fields were used as
  input variables. The fields are divided into four
  groups

19
The Data Mining Procedure Step 8Model
Assessment

• We use sensitivity, specificity and accuracy as
  our model measures.
• Sensitivity could represent the probability of
  mistake in diagnosis
• Specificity could represent the probability of
  unnecessary medical resource wasting

20
The Data Mining Procedure Step 8The Result of
First Phase
21
The Data Mining Procedure Step 8 The Result of
First Phase (Cont.)
22
The Data Mining Procedure Step 8 The Result of
Second Phrase
23
The Data Mining Procedure Step 9

• In this step, due to we have not enough medical
  resource to support our project, it is difficult
  to deploy our models in practical. Although we
  cannot fulfill our models in the real business
  environment, we still obtain copious experience
  and knowledge throughout data mining process.

24
Conclusion

• Two classification approaches decision tree and
  Bayesian network.
• Using noninvasive and invasive approaches step
  by step.

25
Limitation

• Limited noninvasive approaches
• Apply other non-invasive examinations to increase
  performance of data mining model, such as
  ultrasound tests.
• Lack of explanation of rules with domain
  knowledge