Limits...
Wavelet-based Gaussian-mixture hidden Markov model for the detection of multistage seizure dynamics: a proof-of-concept study.

Chiu AW, Derchansky M, Cotic M, Carlen PL, Turner SO, Bardakjian BL - Biomed Eng Online (2011)

Bottom Line: Using unsupervised training method, the HMM and the clustering parameters were obtained simultaneously.Minimum redundancy maximum relevance (mRMR) analysis and Akaike Information Criterion (AICc) were applied to reduce the effect of over-fitting.The subjectivity involved in partitioning the observed data prior to training can be eliminated.

View Article: PubMed Central - HTML - PubMed

Affiliation: Biomedical Engineering Department, Louisiana Tech University, Ruston, Louisiana, USA. alanchiu@latech.edu

ABSTRACT

Background: Epilepsy is a common neurological disorder characterized by recurrent electrophysiological activities, known as seizures. Without the appropriate detection strategies, these seizure episodes can dramatically affect the quality of life for those afflicted. The rationale of this study is to develop an unsupervised algorithm for the detection of seizure states so that it may be implemented along with potential intervention strategies.

Methods: Hidden Markov model (HMM) was developed to interpret the state transitions of the in vitro rat hippocampal slice local field potentials (LFPs) during seizure episodes. It can be used to estimate the probability of state transitions and the corresponding characteristics of each state. Wavelet features were clustered and used to differentiate the electrophysiological characteristics at each corresponding HMM states. Using unsupervised training method, the HMM and the clustering parameters were obtained simultaneously. The HMM states were then assigned to the electrophysiological data using expert guided technique. Minimum redundancy maximum relevance (mRMR) analysis and Akaike Information Criterion (AICc) were applied to reduce the effect of over-fitting. The sensitivity, specificity and optimality index of chronic seizure detection were compared for various HMM topologies. The ability of distinguishing early and late tonic firing patterns prior to chronic seizures were also evaluated.

Results: Significant improvement in state detection performance was achieved when additional wavelet coefficient rates of change information were used as features. The final HMM topology obtained using mRMR and AICc was able to detect non-ictal (interictal), early and late tonic firing, chronic seizures and postictal activities. A mean sensitivity of 95.7%, mean specificity of 98.9% and optimality index of 0.995 in the detection of chronic seizures was achieved. The detection of early and late tonic firing was validated with experimental intracellular electrical recordings of seizures.

Conclusions: The HMM implementation of a seizure dynamics detector is an improvement over existing approaches using visual detection and complexity measures. The subjectivity involved in partitioning the observed data prior to training can be eliminated. It can also decipher the probabilities of seizure state transitions using the magnitude and rate of change wavelet information of the LFPs.

Show MeSH

Related in: MedlinePlus

The relationship between the HMM identified late tonic states and the intracellular modes. (a) The temporal relationship between the intracellular modes before chronic seizures and the HMM late tonic firing states for each SLE in the test set is shown. The intracellular modes are shown in solid color (red for prem and blue for pred). The identified states by the HMM are shown as dashed lines (red for early tonic and blue for late tonic states). (b) The boxplot summarizes the relationship between the start of the pred intracellular activity and the onset of the late tonic firing model state. The HMM was able to identify 85.9% of the pred activity as the late tonic firing state. The mean starting times for the electrographical pred activity and the model late tonic state were 16.25 s and 16.77 s prior to chronic seizure onset, respectively. Using pair-wise T-test analysis, no statistically significant difference was found between the two (p > 0.49).
© Copyright Policy - open-access
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC3094216&req=5

Figure 10: The relationship between the HMM identified late tonic states and the intracellular modes. (a) The temporal relationship between the intracellular modes before chronic seizures and the HMM late tonic firing states for each SLE in the test set is shown. The intracellular modes are shown in solid color (red for prem and blue for pred). The identified states by the HMM are shown as dashed lines (red for early tonic and blue for late tonic states). (b) The boxplot summarizes the relationship between the start of the pred intracellular activity and the onset of the late tonic firing model state. The HMM was able to identify 85.9% of the pred activity as the late tonic firing state. The mean starting times for the electrographical pred activity and the model late tonic state were 16.25 s and 16.77 s prior to chronic seizure onset, respectively. Using pair-wise T-test analysis, no statistically significant difference was found between the two (p > 0.49).

Mentions: Finally, we evaluated the correlations between the model tonic firing state from the HMMAIC with the phasic inhibition or excitation in the intracellular activities [35]. It has been suggested that the intracellular whole-cell recordings exhibited a switch from a dominant phasic inhibition (preh) to a dominant phasic excitation (pred) mode in the state transition leading to the chronic seizure onset [35]. An intermediate state (prem) was also reported to compose of a mixture of preh and pred mode. None of the HMM created in this study was able to detect early preh mode using the LFP data. In the HMMopt14D, the states S2 and S5 (Figure 5a) can be considered as a combination of late preh and prem. Figure 10a summarizes the temporal relationship between the HMM-identified early and late tonic firing activities in the LFP with the identified prem and pred modes in the whole-cell recording. Most of the late tonic firing activities identified by the model started earlier than the pred intracellular activities. Out of the 20 test cases, 85.9% of the pred activity was identified as the late tonic firing phase. A paired T-test did not indicate a statistically significant difference between the start of the whole-cell pred activity and the onset of the late tonic HMM state (p > 0.49), as illustrated in Figure 10b.


Wavelet-based Gaussian-mixture hidden Markov model for the detection of multistage seizure dynamics: a proof-of-concept study.

Chiu AW, Derchansky M, Cotic M, Carlen PL, Turner SO, Bardakjian BL - Biomed Eng Online (2011)

The relationship between the HMM identified late tonic states and the intracellular modes. (a) The temporal relationship between the intracellular modes before chronic seizures and the HMM late tonic firing states for each SLE in the test set is shown. The intracellular modes are shown in solid color (red for prem and blue for pred). The identified states by the HMM are shown as dashed lines (red for early tonic and blue for late tonic states). (b) The boxplot summarizes the relationship between the start of the pred intracellular activity and the onset of the late tonic firing model state. The HMM was able to identify 85.9% of the pred activity as the late tonic firing state. The mean starting times for the electrographical pred activity and the model late tonic state were 16.25 s and 16.77 s prior to chronic seizure onset, respectively. Using pair-wise T-test analysis, no statistically significant difference was found between the two (p > 0.49).
© Copyright Policy - open-access
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC3094216&req=5

Figure 10: The relationship between the HMM identified late tonic states and the intracellular modes. (a) The temporal relationship between the intracellular modes before chronic seizures and the HMM late tonic firing states for each SLE in the test set is shown. The intracellular modes are shown in solid color (red for prem and blue for pred). The identified states by the HMM are shown as dashed lines (red for early tonic and blue for late tonic states). (b) The boxplot summarizes the relationship between the start of the pred intracellular activity and the onset of the late tonic firing model state. The HMM was able to identify 85.9% of the pred activity as the late tonic firing state. The mean starting times for the electrographical pred activity and the model late tonic state were 16.25 s and 16.77 s prior to chronic seizure onset, respectively. Using pair-wise T-test analysis, no statistically significant difference was found between the two (p > 0.49).
Mentions: Finally, we evaluated the correlations between the model tonic firing state from the HMMAIC with the phasic inhibition or excitation in the intracellular activities [35]. It has been suggested that the intracellular whole-cell recordings exhibited a switch from a dominant phasic inhibition (preh) to a dominant phasic excitation (pred) mode in the state transition leading to the chronic seizure onset [35]. An intermediate state (prem) was also reported to compose of a mixture of preh and pred mode. None of the HMM created in this study was able to detect early preh mode using the LFP data. In the HMMopt14D, the states S2 and S5 (Figure 5a) can be considered as a combination of late preh and prem. Figure 10a summarizes the temporal relationship between the HMM-identified early and late tonic firing activities in the LFP with the identified prem and pred modes in the whole-cell recording. Most of the late tonic firing activities identified by the model started earlier than the pred intracellular activities. Out of the 20 test cases, 85.9% of the pred activity was identified as the late tonic firing phase. A paired T-test did not indicate a statistically significant difference between the start of the whole-cell pred activity and the onset of the late tonic HMM state (p > 0.49), as illustrated in Figure 10b.

Bottom Line: Using unsupervised training method, the HMM and the clustering parameters were obtained simultaneously.Minimum redundancy maximum relevance (mRMR) analysis and Akaike Information Criterion (AICc) were applied to reduce the effect of over-fitting.The subjectivity involved in partitioning the observed data prior to training can be eliminated.

View Article: PubMed Central - HTML - PubMed

Affiliation: Biomedical Engineering Department, Louisiana Tech University, Ruston, Louisiana, USA. alanchiu@latech.edu

ABSTRACT

Background: Epilepsy is a common neurological disorder characterized by recurrent electrophysiological activities, known as seizures. Without the appropriate detection strategies, these seizure episodes can dramatically affect the quality of life for those afflicted. The rationale of this study is to develop an unsupervised algorithm for the detection of seizure states so that it may be implemented along with potential intervention strategies.

Methods: Hidden Markov model (HMM) was developed to interpret the state transitions of the in vitro rat hippocampal slice local field potentials (LFPs) during seizure episodes. It can be used to estimate the probability of state transitions and the corresponding characteristics of each state. Wavelet features were clustered and used to differentiate the electrophysiological characteristics at each corresponding HMM states. Using unsupervised training method, the HMM and the clustering parameters were obtained simultaneously. The HMM states were then assigned to the electrophysiological data using expert guided technique. Minimum redundancy maximum relevance (mRMR) analysis and Akaike Information Criterion (AICc) were applied to reduce the effect of over-fitting. The sensitivity, specificity and optimality index of chronic seizure detection were compared for various HMM topologies. The ability of distinguishing early and late tonic firing patterns prior to chronic seizures were also evaluated.

Results: Significant improvement in state detection performance was achieved when additional wavelet coefficient rates of change information were used as features. The final HMM topology obtained using mRMR and AICc was able to detect non-ictal (interictal), early and late tonic firing, chronic seizures and postictal activities. A mean sensitivity of 95.7%, mean specificity of 98.9% and optimality index of 0.995 in the detection of chronic seizures was achieved. The detection of early and late tonic firing was validated with experimental intracellular electrical recordings of seizures.

Conclusions: The HMM implementation of a seizure dynamics detector is an improvement over existing approaches using visual detection and complexity measures. The subjectivity involved in partitioning the observed data prior to training can be eliminated. It can also decipher the probabilities of seizure state transitions using the magnitude and rate of change wavelet information of the LFPs.

Show MeSH
Related in: MedlinePlus