Prediction of Epileptic Seizures PhD Conversion Seminar

32
Prediction of Epileptic Seizures PhD Conversion Seminar Elma O’Sullivan-Greene Life Sciences, NICTA VRL Dept. Electrical & Electronic Engineering, The University of Melbourne [email protected] Supervisors: Prof. Iven Mareels Dr. Levin Kuhlmann A/Prof. Anthony Bur Dr. Chung-Yao Kao

description

Prediction of Epileptic Seizures PhD Conversion Seminar. Elma O’Sullivan-Greene Life Sciences, NICTA VRL Dept. Electrical & Electronic Engineering, The University of Melbourne [email protected]. Supervisors: Prof. Iven Mareels Dr. Levin Kuhlmann A/Prof. Anthony Burkitt - PowerPoint PPT Presentation

Transcript of Prediction of Epileptic Seizures PhD Conversion Seminar

Page 1: Prediction of Epileptic Seizures  PhD Conversion Seminar

Prediction of Epileptic Seizures PhD Conversion Seminar

Elma O’Sullivan-Greene

Life Sciences, NICTA VRL

Dept. Electrical & Electronic Engineering, The University of Melbourne

[email protected]

Supervisors:

Prof. Iven Mareels Dr. Levin Kuhlmann A/Prof. Anthony Burkitt Dr. Chung-Yao Kao

Page 2: Prediction of Epileptic Seizures  PhD Conversion Seminar

Talk Outline

1. Epilepsy: a disorder of the brain

2. Data available for engineering analysis

3. Current approaches to epileptic seizure prediction, and their limitations

4. Work completed and in progress

5. Proposed avenues for project

Page 3: Prediction of Epileptic Seizures  PhD Conversion Seminar

Talk Outline

1. Epilepsy: a disorder of the brain

2. Data available for engineering analysis

3. Current approaches to epileptic seizure prediction, and their limitations

4. Work completed and in progress

5. Proposed avenues for project

Page 4: Prediction of Epileptic Seizures  PhD Conversion Seminar

Epilepsy: a disorder of the brain

• Epilepsy is a neurological disorder – Characterised by recurrent “seizures”– Associated with abnormally excessive or synchronous

neuronal activity in the brain

• Most common serious neurological condition– Prevalence of epilepsy varies across geographical regions

within the range of 0.5% to 4% of the total population (WHO)

• Current Treatment– AED (Antiepileptic Drugs) - undesirable side-effects– Surgical removal of the epileptic brain tissue

Page 5: Prediction of Epileptic Seizures  PhD Conversion Seminar

Motivation For Seizure Prediction

• The ability to predict seizures would have a profound impact on the quality of life of epilepsy suffers.

• Our proposed solution– An Implantable device incorporating

• seizure prediction• short-term electric stimulation treatment for seizure prevention

• Continuous electric stimulation is in use, and shows good results in many patients (unknown side effects for long term use)

• No robust seizure prediction algorithm has been published to date

Page 6: Prediction of Epileptic Seizures  PhD Conversion Seminar

Talk Outline

1. Epilepsy: a disorder of the brain

2. Data available for engineering analysis

3. Current approaches to epileptic seizure prediction, and their limitations

4. Work completed and in progress

5. Proposed avenues for project

Page 7: Prediction of Epileptic Seizures  PhD Conversion Seminar

Data Source: Electroencephalography (EEG)

• Recordings of the fluctuating electric fields of the brain

– Electric fields due to ionic currents in the extra cellular fluid– Neurons (nerve cells) choose when to fire impulses based on

this ionic current information

Page 8: Prediction of Epileptic Seizures  PhD Conversion Seminar

Data Source: Electroencephalography (EEG)

• Recordings of the fluctuating electric fields of the brain

• Scalp EEG data • Intracranial EEG data

Page 9: Prediction of Epileptic Seizures  PhD Conversion Seminar

Talk Outline

1. Epilepsy: a disorder of the brain

2. Data available for engineering analysis

3. Current approaches to epileptic seizure prediction, and their limitations

4. Work completed and in progress

5. Proposed avenues for project

Page 10: Prediction of Epileptic Seizures  PhD Conversion Seminar

Can Seizures Be Predicted?

• Evidence for a definable pre-ictal (pre-seizure) period

– Clinically undisputed indicative systematic changes are present in some patients prior to seizure onset

• Mood changes, nausea, headache

– Several signal processing studies argue that a pre-ictal state can be defined based on

• Measures of synchronisation between EEG channels• Non-linear dynamics measures

Page 11: Prediction of Epileptic Seizures  PhD Conversion Seminar

Current Prediction Approaches

• Linear Approaches• Spectral analysis• Linear Modelling• Energy measures

– Minimal success: brain function nonlinear?

• Nonlinear Approaches– Based on state space reconstruction

• Dimension• Lyapunov Exponents• Entropy

– Minimal success: initial promising results failed to be reproduced with other data sets

Page 12: Prediction of Epileptic Seizures  PhD Conversion Seminar

State Space Reconstruction/ Delay Embedding

N at least O(1015)

Page 13: Prediction of Epileptic Seizures  PhD Conversion Seminar

State Space Reconstruction/ Delay Embedding

Combine to reconstruct an N-dimensional system

Page 14: Prediction of Epileptic Seizures  PhD Conversion Seminar

Limitations of Delay Reconstruction

• The original framework (Takens’/ Aeyels) for delay reconstruction requires:– Stationarity of the dataset– Noise free data set– A time series from an autonomous dynamical system– Low dimensionality of underlying dynamical system

• However the EEG is ultimately an unsuitable signal for this framework– Highly non-stationary data set– High levels of measurement noise in EEG recordings

(artefact)

– The brain is not an autonomous system (brain processes external inputs)

– No conclusive evidence that the brain/ epileptic events are low dimensional

Page 15: Prediction of Epileptic Seizures  PhD Conversion Seminar

Talk Outline

1. Epilepsy: a disorder of the brain

2. Data available for engineering analysis

3. Current approaches to epileptic seizure prediction, and their limitations

4. Work completed and in progress

5. Proposed avenues for project

Page 16: Prediction of Epileptic Seizures  PhD Conversion Seminar

Work Completed and in Progress

• Modification of the EEG signal for delay reconstruction• Addressing the noise limitation

– Taking the difference between 2 closely spaced intracranial electrodes

Cancel common mode input from far away dynamical subsystems (Stark)

Representation of local dynamics

Significant reduction in common mode artefact (50 Hz mains pick-up)

Consider the Brain as:

• spatially distributed system

• interacting distinct local subsystems

Page 17: Prediction of Epileptic Seizures  PhD Conversion Seminar

Work Completed and in Progress

• Modification of the EEG signal for delay reconstruction

• Addressing the low dimensionality limitation– Hypothesis: The brain is lower-dimensional during a seizure– Perhaps there is enough stationary data in the period just

prior to a seizure to warrant a reconstruction

Page 18: Prediction of Epileptic Seizures  PhD Conversion Seminar

An existing seizure prediction algorithm:

• Dynamical Similarity Index (DSI)

– Le Van Quyen (1999)

– Creates templates of brain dynamics from delay reconstruction of EEG data

– Seizure anticipation state declared for large sustained deviations of dynamic template from reference (far from seizure)

Page 19: Prediction of Epileptic Seizures  PhD Conversion Seminar

Work Completed and in Progress

• Application of modified EEG signal to DSI algorithm– Reference template from pre-ictal data

(low-dimensional/stationarity considerations)

– EEG signal used: difference between 2 closely spaced intracranial electrodes

(noise consideration)

• Preliminary results– Sensitivity: 25%-100% across 3 patients– False Positive rate: 1-6.6 FP/hr across 3 patients

Page 20: Prediction of Epileptic Seizures  PhD Conversion Seminar

Work Completed and in Progress

• No major improvement seen with preliminary results over original DSI algorithm

• Why?– Pre-ictal low dimensionality of underlying system is an

unproven hypothesis– Other noise: muscle artefact, cardiac artefact …

• Conclusion – Future prediction methods should concentrate on non-

delay-reconstruction based methods

Page 21: Prediction of Epileptic Seizures  PhD Conversion Seminar

Talk Outline

1. Epilepsy: a disorder of the brain

2. Data available for engineering analysis

3. Current approaches to epileptic seizure prediction, and their limitations

4. Work completed and in progress

5. Proposed avenues for project

Page 22: Prediction of Epileptic Seizures  PhD Conversion Seminar

Project Proposal

• Nonlinear System analysis without reconstruction– Data-driven pathway

Brain SystemUnknown state space system, F

xk+1=F (xk , ωk)

Measured EEG DataRepresented by the function, H

zk=H (xk , ωk)

Epilepsy PredictionRepresented by the function, G

yk+1=G (xk , ωk)

?

Page 23: Prediction of Epileptic Seizures  PhD Conversion Seminar

Project Proposal - Entropy via Data Compression

• An entropy measure as a prediction candidate– Low-dimensional object indicative of underlying brain

state

• Entropy, as measured in the brain, can be viewed as – a measure of how “chaotic” the brain system is– a measure of information transfer in the brain

Page 24: Prediction of Epileptic Seizures  PhD Conversion Seminar

Entropy via Data Compression Techniques

Instead of computing entropy via delay reconstruction….

• Estimating entropy via Data-Compression Techniques– Markov Model– Context-Tree Model– Model based on Independent Component Analysis (ICA)

• Let observed time-series data (EEG) be an element of a finite alphabet of symbols

• Advantages of this approach– More robust in the presence of noise– Does not require stationarity of the data set– Can be applied to High Dimensional Systems

Page 25: Prediction of Epileptic Seizures  PhD Conversion Seminar

Entropy Estimation from a Markov Model

• Markov model:– Estimates future symbols

based on k-past past symbols– Symbolic time series analysis

Page 26: Prediction of Epileptic Seizures  PhD Conversion Seminar

Entropy Estimation from a Weighted Context Tree

• Weighted Context tree:– Estimates future symbols based on k-past past symbols– Each node or “context” contains information of symbol history – Automated recursive weight probability associated with each context – Contexts automatically discarded on basis of improved performance– Entropy: h = L / N L=Source Code length N=Time

Page 27: Prediction of Epileptic Seizures  PhD Conversion Seminar

Entropy Estimation from an ICA based model

• Measured EEG Channels: x = A s

• Find the transformation of the data W = A-1 such that the coding lengths of the components are minimised

• Non-linear independent component methods

• Using several EEG channels: spatial information

Statistically Independent components

x = f( s )

y = h( x )

Page 28: Prediction of Epileptic Seizures  PhD Conversion Seminar

Seizure Prediction Proposal

• Have discussed Entropy as a seizure prediction candidate as estimated from data compression techniques.

• Next: An alternative probabilistic approach to data-based seizure prediction……

Page 29: Prediction of Epileptic Seizures  PhD Conversion Seminar

• Bifurcation Phenomenon – prediction by tracking the trajectory of bifurcation parameter, μ, over time

Bifurcation part of thalmo-cortical brain model, Robinson (2003)

Seizure Prediction: Decision Markov Process

• Motivation for a statistical decision model:

• Dynamical systems representations of the epileptic brain:

• Probabilistic Transitions between two chaotic attractors

Normal Epileptic

Phase portrait of computer model of brain’s thalmo-cortical network, Lopes Da Silva (2003)

Page 30: Prediction of Epileptic Seizures  PhD Conversion Seminar

Seizure Prediction: Decision Markov Process

• 3 state model• Transition probabilities tij assigned through

analysis of EEG data• Potential for intervention applications: control

input to minimise the transition to seizure state

Page 31: Prediction of Epileptic Seizures  PhD Conversion Seminar

Conclusion: Research Proposal

• Proposed Avenues for Seizure Prediction:

– Entropy as estimated from data compression techniques• Markov Process• Context Tree• Independent Component Analysis

– Decision Markov Process

• Potential for the theoretical expansion of dynamical system time-series analysis– for the application of real world biological data

Page 32: Prediction of Epileptic Seizures  PhD Conversion Seminar

Thank you for your attention

Questions?

[email protected]