Presentation of: Microdialysis Monitoring as a Mean to Detect Cerebral Ischemia by use of Data Minin

1
Presentation ofMicrodialysis Monitoring as a
Mean to Detect Cerebral Ischemia by use of Data
Mining
Project group 859a

• Tuesday the 29th of June 2004
• 9.00

2
Agenda

• Introduction (Nicolaj) E
• Data Mining Overview (Nicolaj)
• Results Clustering (Svend)
• Results Linear Regression (Svend)
• Results Neural Networks (Tue)
• Conclusion (Michael)
• Future Work (Michael)

3
Introduction (1/6)

• aSAH is a bleeding from an aneurysm in the
  subarachnoid space.

Aneurysm
4
Introduction (2/6)

• Facts about aSAH
• Incidence 15 per 100000 per year.
• aSAH is combined with a high rate of mortality
  and morbidity.
• 15 die before they reach the hospital.
• a total of 40 die in the acute phase.
• More than half of the survivors must live with
  weak or severe morbidity.

5
Introduction (3/6)

• Many of the complications are directly or
  indirectly related to cerebral energy metabolism.
• It is ususally caused by the impaired blood flow
  (substrate supply).
• Cerebral ischemia a local lack of blood in the
  brain.

6
Introduction (4/6)

• Microdialysis is a way to measure the
  concentration of energy related metabolites.

7
Introduction (5/6)

• Energy related metabolites
• Glucose
• Pyruvate
• Lactate
• Glycerol

• Role of Oxygen

8
Introduction (6/6)

• Is it possible to predict complications related
  to metabolism?
• Microdialysis can provide the needed information
  about the current cerebral metabolism.
• Data mining can be used to analyze the collected
  data in order to produce knowledge from the data.

9
Agenda

• Introduction (Nicolaj)
• Data Mining Overview (Nicolaj) E
• Results Clustering (Svend)
• Results Linear Regression (Svend)
• Results Neural Networks (Tue)
• Conclusion (Michael)
• Future Work (Michael)

10
Data Mining Overview (1/10)

• Data mining is a process that turns data into
  knowledge.
• Methodologies like CRISP-DM add stability to the
  project.

11
Data Mining Overview (2/10)

• Data Preprocessing steps are very time consuming.
• Cleaning - garbage in, garbage out.
• Includes 4 mis'es
• Missing values.
• Mis-measurements.
• Mis-placements.
• Mis-spellings.
• Transformations, DB- technology saves time.

12
Data Mining Overview (3/10)

• How to deal with mis-measurements?
• Remove outlier values.
• Slide window of size 5 over the data.
• Calculate mean and std.dev.
• Remove outliers, i.e. values greater than /-
  2std.dev.
• Replace with the mean value.
• Noise Reduction.
• Replace each value with a moving average.

13
Data Mining Overview (4/10)

• Data Warehouse Technology can help save time for
  producing Transformations.
• In a DW data are stored in a summarized manner.
• It allows instant answers to rapid questions.
• OnLine Analytical Processing (OLAP).

14
Data Mining Overview (5/10)

• Data are stored in Cubes (metaphore).
• A cube has multiple dimensions.
• The content of the cube is measures.
• In our case
• dimensions are
• clinical outcome, age, time, sex, events etc.
• measures are
• glucose, pyruvate, lactate, glycerol, L/P, L/G.

15
Data Mining Overview (6/10)
16
Data Mining Overview (7/10)

• OLAP Example What was the average metabolism for
  patients who died, had ischemia, had normal
  outcome over time?
• This question has been answered using a DW tool.

17
Data Mining Overview (8/10)
18
Data Mining Overview (9/10)
19
Data Mining Overview (10/10)
20
Agenda

• Introduction (Nicolaj)
• Data Mining Overview (Nicolaj)
• Results Clustering (Svend) E
• Results Linear Regression (Svend)
• Results Neural Networks (Tue)
• Conclusion (Michael)
• Future Work (Michael)

21
Clustering

• Want to find homogeneous groups of data
• Averge distance to the centroid
• Cluster at global normalized data
• Glucose
• Glycerol
• Lactate
• Pyruvate
• L/G ratio
• L/P - ratio

22
Clustering with 5 clusters (1/4)
6.73 1.09
0.54 0.15
354 88.5
84.2 35.8
Severe ischemia found by Schulz,2000
23
Clustering with 5 clusters (2/4)
97.8 32.2
16.7 4.70
Severe ischemia found by Schulz,2000
24
Clustering with 5 clusters (3/4)
25
Clustering with 5 clusters (4/4)

• Cluster 5 is a ischemic pattern cluster, but with
  only 4 patients, who had a ischemic pattern.
• Patient js085 two instance are measured under
  surgery and has non ischemic pattern described.

26
Agenda

• Introduction (Nicolaj)
• Data Mining Overview (Nicolaj)
• Results Clustering (Svend)
• Results Linear Regression (Svend)E
• Results Neural Networks (Tue)
• Conclusion (Michael)
• Future Work (Michael)

27
Linear regression (1/2)

• Why linear regression?
• High correlation between lactate and pyruvate
• Will there be differents between gorups of
  patients?
• Normal pattern
• Ischemic pattern
• Dead patients

28
Linear regression (2/2)

• Are there a linear regression in data?
• Simple linear regrsssion model
• y ß0 ß1x e gt E(y) ß0 ß1x
• Estimated simple linear regrsssion equation
• y b0 b1x
• Testing for significance H0ß1 0 Ha ß1 ? 0
• t-Test F-Test
• Can it be used to define ischemia pattern?

29
Normal group

• 20 patients
• 1892 instances
• Lac0,5016,70Pyr
• Hoß10 Reject , with a 0.01

99 predicted
30
Ischemia group

• 9 patients
• 791 instances
• Lac0,4024,38Pyr
• Hoß10 Reject, with a 0.01

99 predicted
31
Dead group

• 6 patients
• 410 instances
• Lac1,8318,29Pyr
• Hoß10 Reject, with a 0.01

99 predicted
32
The 3 groups compared

• It is difficult to make decision about ischemic
  pattern from the linear regression

99 predicted normal
33
Patient variation (1/2)
Patients in the Ischemic pattern group
Lac 6.73 1.09
L/P 97,8 32.2
Pyr 0.084 0.036
Severe ischemia found by Schulz,2000
34
Patient variation (2/2)
Patients in the Dead group
Lac 6.73 1.09
L/P 97,8 32.2
Pyr 0.084 0.036
Severe ischemia found by Schulz,2000
35
Trend for patient
js059
js106
js071
36
Agenda

• Introduction (Nicolaj)
• Data Mining Overview (Nicolaj)
• Results Clustering (Svend)
• Results Linear Regression (Svend)
• Results Neural Networks (Tue) E
• Conclusion (Michael)
• Future Work (Michael)

37
Neural network introduction
38
Modelling with NN

• Different approaches
• With time and without time
• Different sizes of the hidden layer
• Different combinations of input

39
Fundamentals of each neural network

• Each neural network consists of an input layer,
  hidden layer, and output layer
• Each network has been trained using 15 neurons in
  the hidden layer
• Each network follows the principles of the back
  propagation technique
• A sigmoid tranfer function has been used in
  determining output by the neurons

40
First models(1/3)
The network is used to predict 40 values from the
40 actual values
41
First models(2/3)
The network is used to predict 40 values from the
40 actual values plus the 10 timestamps
42
First models(3/3)
And so on toward the 10th forecasted value...
The second neural network in the series
The third neural network in the series
The first neural network in the series
43
Final model
And so on toward the 10th forecasted value...
The second neural network in the series
The third neural network in the series
The first neural network in the series
44
Results by visual inspection
45
Result by tests(1/3)

• MSE and Pearsons correlation coefficient
• Value of error and linarity
• Range of PCC at 10 0.53-0.79
• Range of PCC at 7 0.70-0.83
• MSE ranges between 0.001-0.039
• Significance test is needed

46
Result by test (2/3)

• T-test
• Assumes normal distribution
• Visual inspection

47
Result by test (3/3)

• Glucose H0 rejected from 7 to 10
• Glycerol H0 rejected at 1, 2, 9 and 10
• Lactat H0 rejected at 10
• Pyruvate H0 rejected at 10

48
Conclusion of the neural network

• It is sensible to up to the 4th predicted value
  of each metabolite.
• It is not possible to use time
• if the data was collected at with equal time
  intervals the accuracy might increase

, but
49
Agenda

• Introduction (Nicolaj)
• Data Mining Overview (Nicolaj)
• Results Clustering (Svend)
• Results Linear Regression (Svend)
• Results Neural Networks (Tue)
• Conclusion (Michael) E
• Future Work (Michael)

50
The thought application

• Basic functionality
• Visualizing the past 10 values
• And the 4 predicted values
• Indicator lines based on likelihood of a given
  event
• Individual settings for the patients (Alarm
  settings)

51
Deriving this solution (1/2)

• Cleaning for outliers and such
• Better cleaning principles has been suggested
• Neural network
• Gave information on future values
• Estimated a 3-4 hour future forecast
• Clustering
• Resulted in information that is interesting, and
  relevant, but difficult to implement

52
Deriving this solution (2/2)

• Use Data Warehouse principles by SQL statements
  for store, fetch and visualize data
• Finally, suggestions for clinical use of the
  system

53
Solving the problemFormulation of the problem

• An analysis of the potential in microdialysis
  monitoring is wanted
• Can microdialysis monitoring be used to improve
  the outcome for aSAH patients and can this be
  done by the use of data mining techniques?

54
Is the problem solved?

• To some extend, yes...
• This project has investigated the potential of
  microdialysis
• Positive results for neural network, and
  interesting information on microdialysis
  substrates
• All of which indicating significant possibilities
• A complete implementation of results are
  impossible before real knowledge of its
  influence has been investigated

55
Agenda

• Introduction (Nicolaj)
• Data Mining Overview (Nicolaj)
• Results Clustering (Svend)
• Results Linear Regression (Svend)
• Results Neural Networks (Tue)
• Conclusion (Michael)
• Future Work (Michael) E

56
Follow-up assignments

• The possibilities by the use of EEG in
  conjunction with microdialysis
• Improvements in the CMA equipment
• Optimize ways of collecting data
• Correction of modelling methods

57
EEG as supplement to micordialysis (1/3)

• EEG for clinical use by surgecal procedures
• Quantitative EEG
• Power Spectral Analysis to gain information on
  frequency
• Case shown by next slice
• Reliability has been shown for use of EEG as an
  indicator for Cerebral Ischemia

The reliability of Quantitative
Electroencephalography as an indicator of
Cerebral Ischemia Adams D.C. et al.
58
EEG as supplement to micordialysis (2/3)

• 74 year old patient, having a left posterior MCA
  infact presented by dysphasia and right
  hemiparesis.
• The EEG shows continuous left hemisphere slowing.
• A cortical infact of this size is typically
  continuous.

59
EEG as supplement to micordialysis (3/3)

These two blocks can supplement each other
60
Better registration by automatisation (1/2)

61
Better registration by automatisation (2/2)

• A solution is not eminent.
• Re-evaluate design and collection of data.
• The advantage Less strain on clinical staff and
  more secure measurements (Time variance)

62
...Better registration though is not just
automatisation

• Procedures for collecting data
• Time intervals between measurements
• Incoorperation these in existing rutines
• Standardization of registration (Same way of
  representing data)
• Could easily be accomplished by implementing a
  system like the developed
• Remove the clinical way of collecting data
• Trouble with existing data from collection bias
• Scratch my back, Ill scratch yours

63
Improvements in modelling

• First of Substantual amount of data (Not enough
  data is accessable)
• Perhaps different types of modelling or different
  use of allready used techniques
• E.G. Neural Network Radical Basis Functions
• Different modelling tools, Clementine has its
  limitations
• Hugin may be the solution in cases of Baysian
  Network proposals
• Investigation of inter-cluster likelihood and so
  on...

64
This was the presentation by project-group
859a Thank you for listening
...By further investigation that is