ismptt

Information about ismptt

Published on May 2, 2008

Author: Marigold

Source: authorstream.com

Content

Survival-Time Classification of Breast Cancer Patients and Chemotherapy ISMP-2003 Copenhagen August 18-22, 2003:  Survival-Time Classification of Breast Cancer Patients and Chemotherapy ISMP-2003 Copenhagen August 18-22, 2003 Y.-J. Lee, O. L. Mangasarian & W.H. Wolberg Data Mining Institute University of Wisconsin - Madison Breast Cancer Estimates American Cancer Society & World Health Organization :  Breast Cancer Estimates American Cancer Society & World Health Organization Breast cancer is the most common cancer among women in the United States. 212,600 new cases of breast cancer will be diagnosed in the United States in 2003: 211,300 in women, 1,300 in men 40,200 deaths will occur from breast cancer in the United States in 2003: 39,800 in women, 400 in men WHO estimates: More than 1.2 million people worldwide were diagnosed with breast cancer in 2001 and 0.5 million died from breast cancer in 2000. Key Objective:  Key Objective Identify breast cancer patients for whom chemotherapy prolongs survival time Similar patients must be treated similarly Good group does not need chemotherapy Intermediate group benefits from chemotherapy Poor group not likely to benefit from chemotherapy Outline:  Outline Tools used Support vector machines (Linear & Nonlinear SVMs) Feature selection & classification Clustering (k-Median algorithm not k-Means) Cluster into chemo & no-chemo groups Cluster chemo patients into 2 groups: good & poor Cluster no-chemo patients into 2 groups: good & poor Merge into three final classes Good (No-chemo) Poor (Chemo) Intermediate : Remaining patients (chemo & no-chemo) Generate survival curves for three classes Use SSVM to classify new patients into one of above three classes Data description Cell Nuclei of a Fine Needle Aspirate:  Cell Nuclei of a Fine Needle Aspirate Thirty Cytological Features Collected at Diagnosis Time:  Thirty Cytological Features Collected at Diagnosis Time Two Histological Features Collected at Surgery Time:  Two Histological Features Collected at Surgery Time Slide8:  Features Selected by Support Vector Machine 1- Norm Support Vector Machines Maximize the Margin between Bounding Planes:  1- Norm Support Vector Machines Maximize the Margin between Bounding Planes A+ A- Support Vector Machine Algebra of 2-Category Linearly Separable Case:  Support Vector Machine Algebra of 2-Category Linearly Separable Case Feature Selection Using 1-Norm Linear SVM Classification Based on Lymph Node Status:  Feature Selection Using 1-Norm Linear SVM Classification Based on Lymph Node Status Features selected: 6 out of 31 by above SVM: Tumor size from surgery Nonlinear SVM for Classifying New Patients:  Nonlinear SVM for Classifying New Patients The Nonlinear Classifier:  The Nonlinear Classifier Where K is a nonlinear kernel, e.g.: Clustering in Data Mining:  Clustering in Data Mining General Objective Given: A dataset of m points in n-dimensional real space Problem: Extract hidden distinct properties by clustering the dataset into k clusters Concave Minimization Formulation of 1-Norm Clustering Problem (k-Median):  Concave Minimization Formulation of 1-Norm Clustering Problem (k-Median) Clustering via Finite Concave Minimization:  Clustering via Finite Concave Minimization K-Median Clustering Algorithm Finite Termination at Local Solution:  K-Median Clustering Algorithm Finite Termination at Local Solution Feature Selection & Initial Cluster Centers:  Feature Selection & Initial Cluster Centers Perform k-Median algorithm in 6-dimensional input space Initial cluster centers used: Medians of Good1 & Poor1 Good1: Patients with Lymph = 0 AND Tumor < 2 Typical indicator for chemotherapy Overall Clustering Process:  Overall Clustering Process 253 Patients (113 NoChemo, 140 Chemo) Survival Curves for Good, Intermediate & Poor Groups (Classified by Nonlinear SSVM):  Survival Curves for Good, Intermediate & Poor Groups (Classified by Nonlinear SSVM) Survival Curves for Intermediate Group: Split by Chemo & NoChemo:  Survival Curves for Intermediate Group: Split by Chemo & NoChemo Survival Curves for Overall Patients: With & Without Chemotherapy:  Survival Curves for Overall Patients: With & Without Chemotherapy Survival Curves for Intermediate Group Split by Lymph Node & Chemotherapy:  Survival Curves for Intermediate Group Split by Lymph Node & Chemotherapy Survival Curves for Overall Patients Split by Lymph Node Positive & Negative:  Survival Curves for Overall Patients Split by Lymph Node Positive & Negative Conclusion:  Conclusion Good – No chemotherapy recommended Intermediate – Chemotherapy likely to prolong survival Poor – Chemotherapy may or may not enhance survival 3 groups have very distinct survival curves Talk & Paper Available on Web:  Talk & Paper Available on Web www.cs.wisc.edu/~olvi Y.-J. Lee, O. L. Mangasarian & W. H. Wolberg: “Computational Optimization and Applications” Volume 25, 2003, pages 151-166”

Related presentations


Other presentations created by Marigold

High Touch Concept
08. 05. 2008
0 views

High Touch Concept

perfeval 20021108
02. 05. 2008
0 views

perfeval 20021108

hegland track 2
02. 05. 2008
0 views

hegland track 2

Stories
02. 05. 2008
0 views

Stories

lecture01 intro
02. 05. 2008
0 views

lecture01 intro

presentation
30. 04. 2008
0 views

presentation

Oracle Order Management 2006
28. 04. 2008
0 views

Oracle Order Management 2006

WHCE March 06
22. 04. 2008
0 views

WHCE March 06

4th grade Plant Adaptations
03. 01. 2008
0 views

4th grade Plant Adaptations

psychosocial intervention
28. 09. 2007
0 views

psychosocial intervention

8 Geomorphic Regions
02. 10. 2007
0 views

8 Geomorphic Regions

SmokeScreen
10. 10. 2007
0 views

SmokeScreen

Roger Stough and Cheng
16. 10. 2007
0 views

Roger Stough and Cheng

Elfaro
22. 10. 2007
0 views

Elfaro

STOCONT2006SLIDESCOR SO
24. 10. 2007
0 views

STOCONT2006SLIDESCOR SO

Com oraleITB
24. 10. 2007
0 views

Com oraleITB

PC chap1 5
16. 10. 2007
0 views

PC chap1 5

hadron99nakada
17. 10. 2007
0 views

hadron99nakada

324l1 int
29. 10. 2007
0 views

324l1 int

MIS CI
29. 09. 2007
0 views

MIS CI

7bL Romantic Music
23. 11. 2007
0 views

7bL Romantic Music

Melihovs Phillips
23. 11. 2007
0 views

Melihovs Phillips

esf coruna
29. 12. 2007
0 views

esf coruna

The Civil War Presidents
31. 12. 2007
0 views

The Civil War Presidents

uganda 02
04. 01. 2008
0 views

uganda 02

Water Quality for Animals
04. 01. 2008
0 views

Water Quality for Animals

thinking wertheim 14jan05
07. 01. 2008
0 views

thinking wertheim 14jan05

07cury
01. 01. 2008
0 views

07cury

of 10 emiranda MagSc
12. 10. 2007
0 views

of 10 emiranda MagSc

land
04. 10. 2007
0 views

land

Roosevelt and U S Imperialism
25. 10. 2007
0 views

Roosevelt and U S Imperialism

IP FSM fin EN
01. 10. 2007
0 views

IP FSM fin EN

naaman
02. 11. 2007
0 views

naaman

mypyramid calorie salary
04. 03. 2008
0 views

mypyramid calorie salary

ganotherapy
06. 03. 2008
0 views

ganotherapy

06 Steve Blanchet
09. 10. 2007
0 views

06 Steve Blanchet

IEW2005 Maeda
11. 04. 2008
0 views

IEW2005 Maeda

2005 Annual Meeting
13. 04. 2008
0 views

2005 Annual Meeting

supercell morphology2
07. 10. 2007
0 views

supercell morphology2

DA Portals
13. 03. 2008
0 views

DA Portals

Sainsel2 kickoff
24. 10. 2007
0 views

Sainsel2 kickoff

cannone
26. 02. 2008
0 views

cannone

5 Toscanini Ben Avi
06. 12. 2007
0 views

5 Toscanini Ben Avi

Oakland Tech Summit 2
29. 10. 2007
0 views

Oakland Tech Summit 2

03 OceanCirculation
07. 04. 2008
0 views

03 OceanCirculation

TSJMediaRlns
08. 10. 2007
0 views

TSJMediaRlns

14 WebSuche Ranking IV
19. 10. 2007
0 views

14 WebSuche Ranking IV

tacit
19. 02. 2008
0 views

tacit

enssup2004HR
02. 11. 2007
0 views

enssup2004HR

John Fenn
15. 10. 2007
0 views

John Fenn

Torch Presentation 5 01
03. 10. 2007
0 views

Torch Presentation 5 01

6 24 Switzerland
17. 10. 2007
0 views

6 24 Switzerland

JVA WorldeId
20. 03. 2008
0 views

JVA WorldeId

216f06 India Travel Guide
25. 03. 2008
0 views

216f06 India Travel Guide

am studies4
16. 03. 2008
0 views

am studies4

NASAtechnology
15. 11. 2007
0 views

NASAtechnology

Presentation 20April
10. 04. 2008
0 views

Presentation 20April

italy MLB
07. 11. 2007
0 views

italy MLB

Claude Research ALADIN DA
24. 10. 2007
0 views

Claude Research ALADIN DA

OME standards 28mar07
12. 10. 2007
0 views

OME standards 28mar07

Rasmus Christiansen Copenhagen
18. 03. 2008
0 views

Rasmus Christiansen Copenhagen

hinkson
27. 02. 2008
0 views

hinkson

GA27 mm
17. 10. 2007
0 views

GA27 mm

Gromov2006Rome
12. 10. 2007
0 views

Gromov2006Rome

11en
24. 03. 2008
0 views

11en