SlideShare a Scribd company logo
1 of 46
Download to read offline
Machine Learning for Alzheimer Disease
Prediction
Oleksandr Kazakov.
Big Data Dev @Wajam
Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 1 / 41
Alzheimer Quick Facts
More than 5 million people in US and 35 million worldwide are living
with Alzheimer’s
Every 66 seconds someone in the US develops disease
Kills more than breast and prostate cancer combined
6th leading cause of death in the US and Canada
No current cure
Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 2 / 41
Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 3 / 41
Raman Spectroscopy
Why Raman Spectroscopy?
It is cheap!
It can provide fingerprinting-type information on the total biochemical
state of blood or cerebrospinal fluid.
Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 6 / 41
Why Raman Spectroscopy?
It is cheap!
It can provide fingerprinting-type information on the total biochemical
state of blood or cerebrospinal fluid.
It is super cheap and...portable(true if number of handles<=2).
Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 6 / 41
Dataset
The Data
Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 8 / 41
Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 9 / 41
Data Serum
Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 10 / 41
Data CSF
Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 11 / 41
Goals
Classification.
Feature Selection.
Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 12 / 41
Goals Realization
Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 13 / 41
Goals Realization
Classification → {NeuralNets : {RBF, MLP}, SV M};
Feature Selection → {GA};
Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 14 / 41
Neural Networks
Biological Neuron
yi = f(
d
i
wixi + w0)
Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 16 / 41
Feed Forward Neural Network with Backpropagation
Learning
Activity of ith neuron:
xi = f( i)
Where:
i = woi +
j⊂Γi
wijxj
Applying chain rule to compute each weight in the network for any
arbitrary error function E
∂E
∂wij
=
∂E
∂ i
∂ i
∂neti
∂neti
∂wij
Once we know partial derivative of each weight the minimization is done
via gradient descent:
wij(t + 1) = wij − λ
∂E
∂wij
(t)
Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 17 / 41
Typical three layers feed-forward neural network
Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 18 / 41
RBF Network
f(x) =
N
i
wih(x)i
Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 20 / 41
f(x) =
N
i
wih(x)i
Most Popular choices of radial basis function are:
Gaussian: e
−( v2
β2 )
Multiquadric: (v2 + β2)
1
2
Inverse Multiquadric: 1
(v2+β2)
1
2
Where v = x − c and represents distance from the input vector to the
radial basis function centre, and β is a width of a radial basis function.
Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 20 / 41
Canonical RBF Network
Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 21 / 41
SVM
Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 22 / 41
Some Theory
Classifier for SVM:
F(x) = sign(
n
j=1
ωjxj − ω0) = sign( ω, x − w0) (1)
Where x = (x1, ...., xn)- evidential description of an object X; vector
ω = (ω1, ...., ωn) and value of ω0 are some parameters of the algorithm.
Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 23 / 41
Some Theory
Classifier for SVM:
F(x) = sign(
n
j=1
ωjxj − ω0) = sign( ω, x − w0) (1)
Where x = (x1, ...., xn)- evidential description of an object X; vector
ω = (ω1, ...., ωn) and value of ω0 are some parameters of the algorithm.
If set is linear separable then error function can be described as following:
E(ω, ω0) =
l
i=1
[yi( ω, xi − ω0) < 0] (2)
Such condition gives a numerous sets of hyperplanes but we want the one
that will be a maximum distance from the separable set.
−1 < ω, x − ω0 < 1
Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 23 / 41
Hyperplane Selection
Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 24 / 41
Width of The Separation Plane
Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 25 / 41
Non-linear SVM Classification
The idea is to map given feature space X to the new H using transition
ψ : X → H and if H has enough dimensionality we can hope that set will
be separated. Kernel will be defined as K(x, x ) = ψ(x), ψ(x ) and
classifier can be rewritten as:
F(x) = sign(
l
j=1
λiyiK(xi, x) − w0)
Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 26 / 41
Non-linear SVM Classification
The idea is to map given feature space X to the new H using transition
ψ : X → H and if H has enough dimensionality we can hope that set will
be separated. Kernel will be defined as K(x, x ) = ψ(x), ψ(x ) and
classifier can be rewritten as:
F(x) = sign(
l
j=1
λiyiK(xi, x) − w0)
Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 26 / 41
Types of Kernel
Polynomial: K(x, x ) = ( x, x + const)d Example
Radial Basis Function: K(x, x ) = e−γ x−x 2
, γ > 0
Gaussian Radial basis function: K(x, x ) = e−0.5 x−x 2(σ−2)
Sigmoid: K(x, x ) = tanh(k x, x + c), k > 0, c > 0
Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 27 / 41
Similarity with Neural Networks
SVM structure:
Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 28 / 41
GA
Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 29 / 41
Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 30 / 41
GA Basics
Randomly choose initial population P of N individuals.
Determine the fitness of each individual.
Assign probability of reproduction pi to each individual.
Create a new population selecting individuals according to pi. Then
selected individuals will generate offsprings via crossovers or
mutations.
Repeat if needed.
Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 31 / 41
Results
Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 32 / 41
RBF and MLP result for Serum
Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 33 / 41
SVM for AD vs HC
Class Sensitivity(%) Specificity(%)
Healthy Control 87 90
Alzheimer dementia 84 87
Healthy Control 81 93
Mild Alzheimer dementias 67 90
Moderate Alzheimer dementias 74 94
Healthy Control 86 88
Mild Alzheimer dementia 88 87
Healthy Control 82 83
Moderate Alzheimer dementia 81 82
Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 34 / 41
MLP and SVM for AD vs HC for CSF
For MLP:
Class Sensitivity(%) Specificity(%)
Healthy Control 81 83
Mild Alzheimer dementia 82 81
Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 35 / 41
MLP and SVM for AD vs HC for CSF
For MLP:
Class Sensitivity(%) Specificity(%)
Healthy Control 81 83
Mild Alzheimer dementia 82 81
And even below 74% Sensitivity and Specificity for SVM.
Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 35 / 41
MLP for AD vs OD for Serum
Class Sensitivity(%) Specificity(%)
Other dementias 95 98
Alzheimer dementia 96 95
Other dementias 92 97
Mild Alzheimer dementias 95 92
Moderate Alzheimer dementias 93 99
Other dementias 91 94
Mild Alzheimer dementia 84 82
Other dementias 96 95
Moderate Alzheimer dementia 92 99
Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 36 / 41
SVM for AD vs OD for Serum
Class Sensitivity(%) Specificity(%)
Other dementias 90 95
Alzheimer dementia 95 90
Other demetias 94 87
Mild Alzheimer demetias 89 94
Moderate Alzheimer demetias 93 92
Other dementias 92 93
Mild Alzheimer dementia 84 82
Other dementias 92 93
Moderate Alzheimer dementia 93 92
Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 37 / 41
Selected Networks Architectures
Type of Network Network Structure Sensitivity(%) Specificity(%)
MLP 5-20-20-1 97 95
MLP 5-50-10-1 96 96
MLP 5-100-1 96 95
MLP 5-200-20-1 96 94
RBF 5-20-20-1 95 94
RBF 5-50-20-1 96 95
RBF 5-100-1 94 94
RBF 5-200-20-1 94 94
Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 38 / 41
Genetic Algorithm Results for Serum
Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 39 / 41
Genetic Algorithm Results for CSF
Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 40 / 41
Conclusions
We demonstrated power of Raman Spectroscopy as diagnostic tool
for AD detection.
We demon- strated the high probability for single subject to be
correctly assigned to the particular diagnostic category.
Our results are consistent with current AD biomarker findings.
Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 41 / 41

More Related Content

Viewers also liked

Survey on data mining techniques in heart disease prediction
Survey on data mining techniques in heart disease predictionSurvey on data mining techniques in heart disease prediction
Survey on data mining techniques in heart disease predictionSivagowry Shathesh
 
HEART DISEASE PREDICTION USING NAIVE BAYES ALGORITHM
HEART DISEASE PREDICTION USING NAIVE BAYES ALGORITHMHEART DISEASE PREDICTION USING NAIVE BAYES ALGORITHM
HEART DISEASE PREDICTION USING NAIVE BAYES ALGORITHMamiteshg
 
Introduction to Radial Basis Function Networks
Introduction to Radial Basis Function NetworksIntroduction to Radial Basis Function Networks
Introduction to Radial Basis Function NetworksESCOM
 
Health Prediction System - an Artificial Intelligence Project 2015
Health Prediction System - an Artificial Intelligence Project 2015Health Prediction System - an Artificial Intelligence Project 2015
Health Prediction System - an Artificial Intelligence Project 2015Maruf Abdullah (Rion)
 
Coursera work: Understanding the Brain: The Neurobiology of Everyday Life
Coursera work: Understanding the Brain: The Neurobiology of Everyday LifeCoursera work: Understanding the Brain: The Neurobiology of Everyday Life
Coursera work: Understanding the Brain: The Neurobiology of Everyday Lifepaulabrillos
 
Alzheimer disease and treatment
Alzheimer disease and treatment Alzheimer disease and treatment
Alzheimer disease and treatment Shourav Ahmed
 
Alzheimer’s disease 2
Alzheimer’s disease 2Alzheimer’s disease 2
Alzheimer’s disease 2HARSHITA
 
Alzheimer’s Disease - Causes, Symptoms & Treatment
Alzheimer’s Disease - Causes, Symptoms & TreatmentAlzheimer’s Disease - Causes, Symptoms & Treatment
Alzheimer’s Disease - Causes, Symptoms & Treatmentakajay201988
 
Radial basis function network ppt bySheetal,Samreen and Dhanashri
Radial basis function network ppt bySheetal,Samreen and DhanashriRadial basis function network ppt bySheetal,Samreen and Dhanashri
Radial basis function network ppt bySheetal,Samreen and Dhanashrisheetal katkar
 
WCSMO-WFLO-2015-mehmani
WCSMO-WFLO-2015-mehmaniWCSMO-WFLO-2015-mehmani
WCSMO-WFLO-2015-mehmaniOptiModel
 
Neural Networks: Radial Bases Functions (RBF)
Neural Networks: Radial Bases Functions (RBF)Neural Networks: Radial Bases Functions (RBF)
Neural Networks: Radial Bases Functions (RBF)Mostafa G. M. Mostafa
 
Alzheimer disease
Alzheimer diseaseAlzheimer disease
Alzheimer diseaseViksn Vik
 
Alzheimer Disease and Mind Function
Alzheimer Disease and Mind FunctionAlzheimer Disease and Mind Function
Alzheimer Disease and Mind FunctionUNIMAS
 
Alzheimer\'s Disease
Alzheimer\'s DiseaseAlzheimer\'s Disease
Alzheimer\'s DiseaseMarquezSelene
 

Viewers also liked (20)

Survey on data mining techniques in heart disease prediction
Survey on data mining techniques in heart disease predictionSurvey on data mining techniques in heart disease prediction
Survey on data mining techniques in heart disease prediction
 
HEART DISEASE PREDICTION USING NAIVE BAYES ALGORITHM
HEART DISEASE PREDICTION USING NAIVE BAYES ALGORITHMHEART DISEASE PREDICTION USING NAIVE BAYES ALGORITHM
HEART DISEASE PREDICTION USING NAIVE BAYES ALGORITHM
 
Introduction to Radial Basis Function Networks
Introduction to Radial Basis Function NetworksIntroduction to Radial Basis Function Networks
Introduction to Radial Basis Function Networks
 
Health Prediction System - an Artificial Intelligence Project 2015
Health Prediction System - an Artificial Intelligence Project 2015Health Prediction System - an Artificial Intelligence Project 2015
Health Prediction System - an Artificial Intelligence Project 2015
 
Coursera work: Understanding the Brain: The Neurobiology of Everyday Life
Coursera work: Understanding the Brain: The Neurobiology of Everyday LifeCoursera work: Understanding the Brain: The Neurobiology of Everyday Life
Coursera work: Understanding the Brain: The Neurobiology of Everyday Life
 
Radial Basis Function
Radial Basis FunctionRadial Basis Function
Radial Basis Function
 
Alzheimer Disease
Alzheimer DiseaseAlzheimer Disease
Alzheimer Disease
 
Alzheimer disease and treatment
Alzheimer disease and treatment Alzheimer disease and treatment
Alzheimer disease and treatment
 
Alzheimer’s disease 2
Alzheimer’s disease 2Alzheimer’s disease 2
Alzheimer’s disease 2
 
Alzheimer’s Disease - Causes, Symptoms & Treatment
Alzheimer’s Disease - Causes, Symptoms & TreatmentAlzheimer’s Disease - Causes, Symptoms & Treatment
Alzheimer’s Disease - Causes, Symptoms & Treatment
 
Alzheimer disease
Alzheimer diseaseAlzheimer disease
Alzheimer disease
 
Radial basis function network ppt bySheetal,Samreen and Dhanashri
Radial basis function network ppt bySheetal,Samreen and DhanashriRadial basis function network ppt bySheetal,Samreen and Dhanashri
Radial basis function network ppt bySheetal,Samreen and Dhanashri
 
WCSMO-WFLO-2015-mehmani
WCSMO-WFLO-2015-mehmaniWCSMO-WFLO-2015-mehmani
WCSMO-WFLO-2015-mehmani
 
Neural Networks: Radial Bases Functions (RBF)
Neural Networks: Radial Bases Functions (RBF)Neural Networks: Radial Bases Functions (RBF)
Neural Networks: Radial Bases Functions (RBF)
 
hopfield neural network
hopfield neural networkhopfield neural network
hopfield neural network
 
Alzheimer disease
Alzheimer diseaseAlzheimer disease
Alzheimer disease
 
Alzheimer Disease and Mind Function
Alzheimer Disease and Mind FunctionAlzheimer Disease and Mind Function
Alzheimer Disease and Mind Function
 
Alzheimer disease (ad)
Alzheimer disease (ad)Alzheimer disease (ad)
Alzheimer disease (ad)
 
Alzheimer\'s Disease
Alzheimer\'s DiseaseAlzheimer\'s Disease
Alzheimer\'s Disease
 
Hopfield Networks
Hopfield NetworksHopfield Networks
Hopfield Networks
 

Similar to Meetup_talk

Clustering and Visualisation using R programming
Clustering and Visualisation using R programmingClustering and Visualisation using R programming
Clustering and Visualisation using R programmingNixon Mendez
 
Machine learning for_finance
Machine learning for_financeMachine learning for_finance
Machine learning for_financeStefan Duprey
 
Computational Motor Control: Optimal Estimation in Noisy World (JAIST summer ...
Computational Motor Control: Optimal Estimation in Noisy World (JAIST summer ...Computational Motor Control: Optimal Estimation in Noisy World (JAIST summer ...
Computational Motor Control: Optimal Estimation in Noisy World (JAIST summer ...hirokazutanaka
 
Signal Discrimination in Cells Through A Negative Feedback
Signal Discrimination in Cells Through A Negative FeedbackSignal Discrimination in Cells Through A Negative Feedback
Signal Discrimination in Cells Through A Negative FeedbackVimalathithan Devaraj
 
ESAI-CEU-UCH solution for American Epilepsy Society Seizure Prediction Challenge
ESAI-CEU-UCH solution for American Epilepsy Society Seizure Prediction ChallengeESAI-CEU-UCH solution for American Epilepsy Society Seizure Prediction Challenge
ESAI-CEU-UCH solution for American Epilepsy Society Seizure Prediction ChallengeFrancisco Zamora-Martinez
 
Inria Tech Talk - La classification de données complexes avec MASSICCC
Inria Tech Talk - La classification de données complexes avec MASSICCCInria Tech Talk - La classification de données complexes avec MASSICCC
Inria Tech Talk - La classification de données complexes avec MASSICCCStéphanie Roger
 
ch10-graphs2.pptx
ch10-graphs2.pptxch10-graphs2.pptx
ch10-graphs2.pptxarkian3
 
Neural Networks: Model Building Through Linear Regression
Neural Networks: Model Building Through Linear RegressionNeural Networks: Model Building Through Linear Regression
Neural Networks: Model Building Through Linear RegressionMostafa G. M. Mostafa
 
maXbox starter67 machine learning V
maXbox starter67 machine learning VmaXbox starter67 machine learning V
maXbox starter67 machine learning VMax Kleiner
 
. An introduction to machine learning and probabilistic ...
. An introduction to machine learning and probabilistic .... An introduction to machine learning and probabilistic ...
. An introduction to machine learning and probabilistic ...butest
 
Big Data Analysis
Big Data AnalysisBig Data Analysis
Big Data AnalysisNBER
 

Similar to Meetup_talk (20)

Clustering and Visualisation using R programming
Clustering and Visualisation using R programmingClustering and Visualisation using R programming
Clustering and Visualisation using R programming
 
6조
6조6조
6조
 
Machine learning for_finance
Machine learning for_financeMachine learning for_finance
Machine learning for_finance
 
Computational Motor Control: Optimal Estimation in Noisy World (JAIST summer ...
Computational Motor Control: Optimal Estimation in Noisy World (JAIST summer ...Computational Motor Control: Optimal Estimation in Noisy World (JAIST summer ...
Computational Motor Control: Optimal Estimation in Noisy World (JAIST summer ...
 
Signal Discrimination in Cells Through A Negative Feedback
Signal Discrimination in Cells Through A Negative FeedbackSignal Discrimination in Cells Through A Negative Feedback
Signal Discrimination in Cells Through A Negative Feedback
 
Bioinformatics life sciences_v2015
Bioinformatics life sciences_v2015Bioinformatics life sciences_v2015
Bioinformatics life sciences_v2015
 
ESAI-CEU-UCH solution for American Epilepsy Society Seizure Prediction Challenge
ESAI-CEU-UCH solution for American Epilepsy Society Seizure Prediction ChallengeESAI-CEU-UCH solution for American Epilepsy Society Seizure Prediction Challenge
ESAI-CEU-UCH solution for American Epilepsy Society Seizure Prediction Challenge
 
Inria Tech Talk - La classification de données complexes avec MASSICCC
Inria Tech Talk - La classification de données complexes avec MASSICCCInria Tech Talk - La classification de données complexes avec MASSICCC
Inria Tech Talk - La classification de données complexes avec MASSICCC
 
ch10-graphs2.pptx
ch10-graphs2.pptxch10-graphs2.pptx
ch10-graphs2.pptx
 
Statistical Physics Studies of Machine Learning Problems by Lenka Zdeborova, ...
Statistical Physics Studies of Machine Learning Problems by Lenka Zdeborova, ...Statistical Physics Studies of Machine Learning Problems by Lenka Zdeborova, ...
Statistical Physics Studies of Machine Learning Problems by Lenka Zdeborova, ...
 
Neural Networks: Model Building Through Linear Regression
Neural Networks: Model Building Through Linear RegressionNeural Networks: Model Building Through Linear Regression
Neural Networks: Model Building Through Linear Regression
 
ch10-graphs2.pdf
ch10-graphs2.pdfch10-graphs2.pdf
ch10-graphs2.pdf
 
CSC446: Pattern Recognition (LN8)
CSC446: Pattern Recognition (LN8)CSC446: Pattern Recognition (LN8)
CSC446: Pattern Recognition (LN8)
 
maXbox starter67 machine learning V
maXbox starter67 machine learning VmaXbox starter67 machine learning V
maXbox starter67 machine learning V
 
. An introduction to machine learning and probabilistic ...
. An introduction to machine learning and probabilistic .... An introduction to machine learning and probabilistic ...
. An introduction to machine learning and probabilistic ...
 
Big Data Analysis
Big Data AnalysisBig Data Analysis
Big Data Analysis
 
6
66
6
 
1.pptx
1.pptx1.pptx
1.pptx
 
tutorial.ppt
tutorial.ppttutorial.ppt
tutorial.ppt
 
Hmm and neural networks
Hmm and neural networksHmm and neural networks
Hmm and neural networks
 

Meetup_talk

  • 1. Machine Learning for Alzheimer Disease Prediction Oleksandr Kazakov. Big Data Dev @Wajam Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 1 / 41
  • 2. Alzheimer Quick Facts More than 5 million people in US and 35 million worldwide are living with Alzheimer’s Every 66 seconds someone in the US develops disease Kills more than breast and prostate cancer combined 6th leading cause of death in the US and Canada No current cure Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 2 / 41
  • 3. Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 3 / 41
  • 5.
  • 6. Why Raman Spectroscopy? It is cheap! It can provide fingerprinting-type information on the total biochemical state of blood or cerebrospinal fluid. Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 6 / 41
  • 7. Why Raman Spectroscopy? It is cheap! It can provide fingerprinting-type information on the total biochemical state of blood or cerebrospinal fluid. It is super cheap and...portable(true if number of handles<=2). Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 6 / 41
  • 9. The Data Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 8 / 41
  • 10. Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 9 / 41
  • 11. Data Serum Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 10 / 41
  • 12. Data CSF Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 11 / 41
  • 13. Goals Classification. Feature Selection. Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 12 / 41
  • 14. Goals Realization Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 13 / 41
  • 15. Goals Realization Classification → {NeuralNets : {RBF, MLP}, SV M}; Feature Selection → {GA}; Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 14 / 41
  • 17. Biological Neuron yi = f( d i wixi + w0) Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 16 / 41
  • 18. Feed Forward Neural Network with Backpropagation Learning Activity of ith neuron: xi = f( i) Where: i = woi + j⊂Γi wijxj Applying chain rule to compute each weight in the network for any arbitrary error function E ∂E ∂wij = ∂E ∂ i ∂ i ∂neti ∂neti ∂wij Once we know partial derivative of each weight the minimization is done via gradient descent: wij(t + 1) = wij − λ ∂E ∂wij (t) Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 17 / 41
  • 19. Typical three layers feed-forward neural network Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 18 / 41
  • 21. f(x) = N i wih(x)i Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 20 / 41
  • 22. f(x) = N i wih(x)i Most Popular choices of radial basis function are: Gaussian: e −( v2 β2 ) Multiquadric: (v2 + β2) 1 2 Inverse Multiquadric: 1 (v2+β2) 1 2 Where v = x − c and represents distance from the input vector to the radial basis function centre, and β is a width of a radial basis function. Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 20 / 41
  • 23. Canonical RBF Network Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 21 / 41
  • 24. SVM Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 22 / 41
  • 25. Some Theory Classifier for SVM: F(x) = sign( n j=1 ωjxj − ω0) = sign( ω, x − w0) (1) Where x = (x1, ...., xn)- evidential description of an object X; vector ω = (ω1, ...., ωn) and value of ω0 are some parameters of the algorithm. Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 23 / 41
  • 26. Some Theory Classifier for SVM: F(x) = sign( n j=1 ωjxj − ω0) = sign( ω, x − w0) (1) Where x = (x1, ...., xn)- evidential description of an object X; vector ω = (ω1, ...., ωn) and value of ω0 are some parameters of the algorithm. If set is linear separable then error function can be described as following: E(ω, ω0) = l i=1 [yi( ω, xi − ω0) < 0] (2) Such condition gives a numerous sets of hyperplanes but we want the one that will be a maximum distance from the separable set. −1 < ω, x − ω0 < 1 Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 23 / 41
  • 27. Hyperplane Selection Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 24 / 41
  • 28. Width of The Separation Plane Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 25 / 41
  • 29. Non-linear SVM Classification The idea is to map given feature space X to the new H using transition ψ : X → H and if H has enough dimensionality we can hope that set will be separated. Kernel will be defined as K(x, x ) = ψ(x), ψ(x ) and classifier can be rewritten as: F(x) = sign( l j=1 λiyiK(xi, x) − w0) Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 26 / 41
  • 30. Non-linear SVM Classification The idea is to map given feature space X to the new H using transition ψ : X → H and if H has enough dimensionality we can hope that set will be separated. Kernel will be defined as K(x, x ) = ψ(x), ψ(x ) and classifier can be rewritten as: F(x) = sign( l j=1 λiyiK(xi, x) − w0) Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 26 / 41
  • 31. Types of Kernel Polynomial: K(x, x ) = ( x, x + const)d Example Radial Basis Function: K(x, x ) = e−γ x−x 2 , γ > 0 Gaussian Radial basis function: K(x, x ) = e−0.5 x−x 2(σ−2) Sigmoid: K(x, x ) = tanh(k x, x + c), k > 0, c > 0 Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 27 / 41
  • 32. Similarity with Neural Networks SVM structure: Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 28 / 41
  • 33. GA Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 29 / 41
  • 34. Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 30 / 41
  • 35. GA Basics Randomly choose initial population P of N individuals. Determine the fitness of each individual. Assign probability of reproduction pi to each individual. Create a new population selecting individuals according to pi. Then selected individuals will generate offsprings via crossovers or mutations. Repeat if needed. Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 31 / 41
  • 36. Results Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 32 / 41
  • 37. RBF and MLP result for Serum Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 33 / 41
  • 38. SVM for AD vs HC Class Sensitivity(%) Specificity(%) Healthy Control 87 90 Alzheimer dementia 84 87 Healthy Control 81 93 Mild Alzheimer dementias 67 90 Moderate Alzheimer dementias 74 94 Healthy Control 86 88 Mild Alzheimer dementia 88 87 Healthy Control 82 83 Moderate Alzheimer dementia 81 82 Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 34 / 41
  • 39. MLP and SVM for AD vs HC for CSF For MLP: Class Sensitivity(%) Specificity(%) Healthy Control 81 83 Mild Alzheimer dementia 82 81 Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 35 / 41
  • 40. MLP and SVM for AD vs HC for CSF For MLP: Class Sensitivity(%) Specificity(%) Healthy Control 81 83 Mild Alzheimer dementia 82 81 And even below 74% Sensitivity and Specificity for SVM. Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 35 / 41
  • 41. MLP for AD vs OD for Serum Class Sensitivity(%) Specificity(%) Other dementias 95 98 Alzheimer dementia 96 95 Other dementias 92 97 Mild Alzheimer dementias 95 92 Moderate Alzheimer dementias 93 99 Other dementias 91 94 Mild Alzheimer dementia 84 82 Other dementias 96 95 Moderate Alzheimer dementia 92 99 Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 36 / 41
  • 42. SVM for AD vs OD for Serum Class Sensitivity(%) Specificity(%) Other dementias 90 95 Alzheimer dementia 95 90 Other demetias 94 87 Mild Alzheimer demetias 89 94 Moderate Alzheimer demetias 93 92 Other dementias 92 93 Mild Alzheimer dementia 84 82 Other dementias 92 93 Moderate Alzheimer dementia 93 92 Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 37 / 41
  • 43. Selected Networks Architectures Type of Network Network Structure Sensitivity(%) Specificity(%) MLP 5-20-20-1 97 95 MLP 5-50-10-1 96 96 MLP 5-100-1 96 95 MLP 5-200-20-1 96 94 RBF 5-20-20-1 95 94 RBF 5-50-20-1 96 95 RBF 5-100-1 94 94 RBF 5-200-20-1 94 94 Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 38 / 41
  • 44. Genetic Algorithm Results for Serum Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 39 / 41
  • 45. Genetic Algorithm Results for CSF Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 40 / 41
  • 46. Conclusions We demonstrated power of Raman Spectroscopy as diagnostic tool for AD detection. We demon- strated the high probability for single subject to be correctly assigned to the particular diagnostic category. Our results are consistent with current AD biomarker findings. Oleksandr Kazakov. Big Data Dev @Wajam Machine Learning for Alzheimer Disease Prediction 41 / 41