Prediction model building and feature selection with SVM in breast cancer diagnosis

1
Prediction model building and feature selection
with SVM in breast cancer diagnosis

• Cheng-Lung Huang, Hung-Chang Liao, Mu-Chen Chen

Expert Systems with Applications 2008
2
Introduction

• Breast cancer is a serious problem for the young
  women of Taiwan.
• Almost 64.1 of women with breast cancer are
  diagnosed before the age of 50 and 29.3 of women
  with breast cancer are diagnosed before the age
  of 40.
• However, the causes are still unknown.

3
Introduction

• This study (Ziegler et al., 1993) shows that
  fibroadenoma shared some risk factors with breast
  cancer.
• HSV-1 (herpes simplex virus type 1)
• EBV (Epstein-Barr virus)
• CMV (cytomegalovirus)
• HPV (human papillomavirus)
• HHV-8 (human herpesvirus-8)

4
Introduction

• DNA viruses, as causes, are closely related to
  the human cancers as part of the high-risk
  factors.
• In order to obtain the relationship between DNA
  viruses and breast tumors.
• This paper uses the support vector machines (SVM)
  to find the pertinent bioinformatics.

5
Two Important Challenge

• When using SVM, two problems are confronted
• How to choose the optimal input feature subset
  for SVM.
• How to set the best kernel parameters.
• These two problems are crucial because the
  feature subset choice influences the appropriate
  kernel parameters and vice versa.

6
Feature Selection

• Feature selection is an important issue in
  building classification systems.
• It is advantageous to limit the number of input
  features in a classifier in order to have a good
  predictive and less computationally intensive
  model.
• This study tried F-score calculation to select
  input features.

7
F-Score
8
F-Score Algorithm
9
Parameters Optimization

• To design a SVM, one must choose a kernel
  function,set the kernel parameters and determine
  a soft margin constant C.
• The grid algorithm is an alternative to finding
  the best C and gamma when using the RBF kernel
  function.
• This study tried grid search to find the best SVM
  model parameters.

10
Grid-Search Algorithm
11
Data collection

• The source of 80 data points (tissue samples)
• 52 specimens of non-familial invasive ductal
  breast cancer.
• 28 mammary fibroadenomas.
• (From Chung-Shan Medical University Hospital )

12
Data partition

• Data set is further randomly partitioned into
  training and independent testing sets via a
  stratified 5-fold cross validation.

13
SVM-based optimize parameters and feature
selection
14
The relative feature importance with F-score
15
The relative importance of DNA virus based on the
F-score
16
The five feature subsets based on the F-score
17
Overall training and testing accuracy for each
feature subset
18
Type I and type II errors

• Type I errors (the "false positive") the error
  of rejecting the null hypothesis given that it is
  actually true
• Type II errors (the "false negative") the error
  of failing to reject the null hypothesis given
  that the alternative hypothesis is actually true

19
Detail testing accuracy for feature subset of
size 2 and 3
20
Linear discriminate analysis (LDA)

• Originally developed in 1936 by R.A. Fisher,
  Discriminate Analysis is a classic method of
  classification.
• Discriminate analysis can be used only for
  classification
• Linear discriminant analysis finds a linear
  transformation ("discriminant function") of the
  two predictors, X and Y, that yields a new set of
  transformed values that provides a more accurate
  discrimination than either predictor alone
• Transformed Target C1X C2Y

21
The P-level of each attribute for LDA
Selection criteria P-level value lt 0.05
22
Training and testing accuracy for LDA
23
Comparison summary between SVM and LDA
24
Conclusion

• In order to find the correlation DNA viruses with
  breast tumor, and to achieve a high
  classificatory accuracy.
• F-score is adapted to find the important
  features.
• grid search approach is used to search the
  optimal SVM parameters.
• The results revealed that the SVM-based model has
  good performance in diagnosing breast cancer
  according to our data set.

25
Conclusion

• The present studys results also show that the
  attributesHSV-1, HHV-8 or HSV-1, HHV-8, CMV
  can achieve identical high accuracy, at 86 of
  average overall hit rate.
• This study suggests simultaneously considering
  HSV-1 and HHV-8 is feasible however, only
  considering HHV-8 or HSV-1 is less accurate.

26
Future Work

• The practical obstacle of the SVM-based (as well
  as neural networks) classification model is its
  black-box nature.
• A possible solution for this issue is the use of
  SVM rule extraction techniques or the use of
  hybrid-SVM model combined with other more
  interpretable models.

27

• Thank You