1.  Datamining @ ARTreat Veljko Milutinovi ć vm@etf.rs Zoran Babovi ć zbabovic@gmail.com Nenad Korolija nenadko@gmail.com Goran Rako č evi ć g.rakocevic@gmail.com Marko Novakovi ć atisha34@yahoo.com

2. 2/28 Agenda  ARTReat – the project  Arteriosclerosis – the basics  Plaque classification  Hemodynamic analysis  Data mining for the hemodynamic problem  Data mining from patent records

3. 3/28 ARTreat – the project  ARTreat targets at providing a patient-specific computational model of the cardiovascular system, used to improve the quality of prediction for the atherosclerosis progression and propagation into life-threatening events.  FP7 Large-scale Integrating Project (IP) ‏  16 partners  Funding: 10,000,000 €

4. 4/28 Atherosclerosis  Atherosclerosis is the condition in which an artery wall thickens as the result of a build-up of fatty materials such as cholesterol

5. 5/28 Artheriosclerotic plaque  Begins as a fatty streak, an ill-defined yellow lesion–fatty plaque, develops edges that evolve to fibrous plaques, whitish lesions with a grumous lipid-rich core

6. 6/28 Plaque components  Fibrous, Lipid, Calcified, Intra-plaque Hemorrhage

7. 7/28 Plaque classification  Different types of plaque pose different risks  Manual plaque classification (done by doctors) is a difficult task, and is error prone  Idea: develop an AI algorithm to distinguish between different types of plaque  Visual data mining

8. 8/28 Plaque classification (2) ‏  Developed by Foundation for Research and Technology  Based on Support Vector Machines  Looks at images produced by IVUS and MRI and are hand labeled by physicians  Up to 90% accurate

9. 9/28 Data mining task in Belgrade  Two separate paths:  Data mining from the results of hemodynamic simulations  Data mining form medical patient records  Goal: to provide input regarding the progression of the disease to be used for medical decision support

10. 10/28 Hemodynamics – the basics  Study of the flow of blood through the blood vessels  Maximum Wall Shear Stress – an important parameter for plaque development prognoses

11. 11/28 Hemodynamics - CFD  Classical methods for hemodynamic calculations employ Computer Fluid Dynamics (CFD) methods  Involves solving the Navier-Stokes equation:  …but involves solving it millions of times!  One simulation can take weeks

12. 12/28 Data mining form hemodynamic simulations (first path) ‏  Idea: use results of previously done simulations  Train a data mining AI system capable of regression analysis  Use the system to estimate the desired values in a much shorter time

13. 13/28 Neural Networks - background  Systems that are inspired by the principle of operation of biological neural systems (brain)

14. 14/28 Neural Networks – the basics  A parallel, distributed information processing structure  Each processing element has a single output which branches (“fans out”) into as many collateral connections as desired  One input, one output and one or more hidden layers

15. 15/28 Artificial neurons  Each node (neuron) consists of two segments:  Integration function  Activation function  Common activation function  Sigmoid

16. 16/28 Neural Networks - backpropagation  A training method for neural networks  Try to minimize the error function: by adjusting the weights  Gradient descent:  Calculate the “blame” of each input for the output error  Adjust the weights by: ( γ - the learning rate)

17. 17/28 Input data set  Carotid artery  11 geometric parameters and the MWSS value

18. 18/28 The model  One hidden layer  Input layer: linear  Hidden and output: sigmoid  Learning rate 0.6  500K training cycles  Decay and momentum

19. 19/28 Current results  Average error: 8.6%  Maximum error 16,9%

20. 20/28 The “dreaded” line 4  Line 4 of the original test set proved difficult to predict  Error was over 30%  Turned out to be an outlier  Combination of parameters was such that it couldn’t  But the CFD worked, NN worked  Visually the geometry looked fine  Goes to show how challenging the data preprocessing can be

21. Dataset analysis  Two distinct areas of MWSS values:  the subset with lower values of MWSS, where a similar clear pattern can be seen against all of the input variables,  scattered cloud of values in the subset with higher MWSS values.  Histogram shows the majority of values grouped in the lower half of the values in the set, with only a small number of points in the higher half. 21

22. MWSS value prediction  Two approaches:  Single model  Two models:  one for the low MWSS value data,  one for higher values,  classifier to choose the appropriate model  Models based on Linear Regression and SVM 22

23. Results ModelRoot square mean errorCorrelation coef. Single model LR19%0.7 Single model SVM17%0.77 Low value model LR11%0.81 Low value model SVM7%0.91 High value model LR42%0.21 High value model SVM31%0.07 23 ClassifierCorrectly classifiedKappaF measure SVM93.2%0.640.517  Poor results for higher values of MWSS – insufficient values to train a model

24. MWSS position  A few outliers and “strange” values in the data set  After elimination: 24 CoordinateLRSVM RSMECCRSMECC X0.23890.97210.2770.9691 Y0.17330.89530.16710.9136 Z0.07360.80860.12210.8304  Further investigation needed into the data and the “outlier” values, although it is only a small number of them

25. 25/28 Genetic data  Single coronary angiography  Blood chemistry  Medications  Single Nucleotide Polymorphism (SNP) data on selected DNA sequences

26. 26/28 …and now for something completely different

27. 27/28 Questions

28.  Datamining @ ARTreat Project Veljko Milutinovi ć vm@etf.rs Zoran Babovi ć zbabovic@gmail.com Nenad Korolija nenadko@gmail.com Goran Rako č evi ć g.rakocevic@gmail.com Marko Novakovi ć atisha34@yahoo.com