Real-Time Seizure State Tracking Using Two Channels: A Mixed-Filter Approach

Ahmadi, Mohammad Badri; Craik, Alexander; Azgomi, Hamid Fekri; Francis, Joseph T.; Contreras-Vidal, José L.; Faghih, Rose T.

doi:10.1109/ieeeconf44664.2019.9048990

Cited by 15 publications

(14 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To reduce the inter-feature correlation, improve F1 score, or both, we modified the feature selection method from the previous work [1]. Table I presents the change in correlation coefficient and F1 score of the two best features, one continuous and one binary, using the previous feature selection method, where the best features were found individually for each subject and the proposed method.…”

Section: Resultsmentioning

confidence: 99%

“…For feature extraction, the EEG data of a single subject was divided into three data sets: a training set, a validation set, and a testing set. The first session with a recorded seizure within the subjects data set was used as the training set, the session with the second recorded seizure was used for the validation set, and the remaining seizure containing sessions are used as the testing data set [1]. By splitting the training, validation, and testing data in these proportions, the number of seizures needed to train the model is reduced, which limits the necessary training data collection efforts and sets a lower limit to the effectiveness of this model.…”

Section: B Feature Extractionmentioning

confidence: 99%

“…Without using a validation set, there is a possibility that our model would be overfit and would not be able to make an accurate estimation. Changing the stopping criteria from previous paper [1], which was set to one, helps to reduce the inter-feature correlation since candidate LDAs now use the previously selected features as well as one candidate feature to determine if the candidate feature improves the performance.…”

Section: Feature Selectionmentioning

confidence: 99%

“…Furthermore, state-space modeling algorithms are computationally efficient and can model complex systems to a high degree of accuracy, making them ideal for low resource systems [38]. Expanding on previous work [1], where the authors employed a mixed-filter approach to perform seizure state estimation using two EEG channels, we propose that the removal of the self-imposed channel count restriction may lead to increases in accuracy and robustness of the state-estimation and be more applicable to non-focal type seizures [7]. Then, we employ a mixed-filter approach to incorporate both binary and continuous features.…”

Section: Introductionmentioning

confidence: 96%

“…When estimating the seizure state, model selection is incredibly important. In this case, a state-space model is preferred as it can be related to the underlying biology and the output is continuous, rather than binary, which provides information as to the seizure evolution and severity [1], [37]. Furthermore, state-space modeling algorithms are computationally efficient and can model complex systems to a high degree of accuracy, making them ideal for low resource systems [38].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

A Mixed Filtering Approach for Real-Time Seizure State Tracking Using Multi-Channel Electroencephalography Data

Steele

Parekh

Azgomi

et al. 2021

IEEE Trans. Neural Syst. Rehabil. Eng.

Self Cite

View full text Add to dashboard Cite

Real-time continuous tracking of seizure state is necessary to develop feedback neuromodulation therapy that can prevent or terminate a seizure early. Due to its high temporal resolution, high scalp coverage, and non-invasive applicability, electroencephalography (EEG) is a good candidate for seizure tracking. In this research, we make multiple seizure state estimations using a mixed-filter and multiple channels found over the entire sensor space; then by applying a Kalman filter, we produce a single seizure state estimation made up of these individual estimations. Using a modified wrapper feature selection, we determine two optimal features of mixed data type, one continuous and one binary analyzing all available channels. These features are used in a state-space framework to model the continuous hidden seizure state. Expectation maximization is performed offline on the training and validation data sets to estimate unknown parameters. The seizure state estimation process is performed for multiple channels, and the seizure state estimation is derived using a square-root Kalman filter. A second expectation maximization step is utilized to estimate the unknown square-root Kalman filter parameters. This method is tested in a real-time applicable way for seizure state estimation. Applying this approach, we obtain a single seizure state estimation with quantitative information about the likelihood of a seizure occurring, which we call seizure probability. Our results on the experimental data (CHB-MIT EEG database) validate the proposed estimation method and we achieve an average accuracy, sensitivity, and specificity of 92.7%, 92.8%, and 93.4%, respectively. The potential applications of this seizure estimation model are for closed-loop neuromodulation and longterm quantitative analysis of seizure treatment efficacy.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: B Feature Extractionmentioning

confidence: 99%

Section: Feature Selectionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 96%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A Mixed Filtering Approach for Real-Time Seizure State Tracking Using Multi-Channel Electroencephalography Data

Steele

Parekh

Azgomi

et al. 2021

IEEE Trans. Neural Syst. Rehabil. Eng.

Self Cite

View full text Add to dashboard Cite

show abstract

Introduction

Wickramasuriya,

Faghih

2023

Bayesian Filter Design for Computational Medicine

View full text Add to dashboard Cite

The human body is an intricate network of multiple functioning sub-systems. Many unobserved processes quietly keep running within the body even while we remain largely unconscious of them. For decades, scientists have sought to understand how different physiological systems work and how they can be mathematically modeled. Mathematical models of biological systems provide key scientific insights and also help guide the development of technologies for treating disorders when proper functioning no longer occurs. One of the challenges encountered with physiological systems is that, in a number of instances, the quantities we are interested in are difficult to observe directly or remain completely inaccessible. This could be either because they are located deep within the body or simply because they are more abstract (e.g., emotion). Consider the heart, for instance. The left ventricle pumps out blood through the aorta to the rest of the body. Blood pressure inside the aorta (known as central aortic pressure) has been considered a useful predictor of the future risk of developing cardiovascular disease, perhaps even more useful than the conventional blood pressure measurements taken from the upper arm (McEniery et al. (Eur Heart J 35(26):1719–1725, 2014)). However, measuring blood pressure inside the aorta is difficult. Consequently, researchers have had to rely on developing mathematical models with which to estimate central aortic pressure using other peripheral measurements (e.g., Ghasemi et al. (J Dyn Syst Measur Control 139(6):061003, 2017)). The same could be said regarding the recovery of CRH (corticotropin-releasing hormone) secretion timings within the hypothalamus—a largely inaccessible structure deep within the brain—using cortisol measurements in the blood based on mathematical relationships (Faghih (System identification of cortisol secretion: Characterizing pulsatile dynamics, Ph.D. dissertation, Massachusetts Institute of Technology, 2014)). Emotions could also be placed in this same category. They are difficult to measure because of their inherently abstract nature. Emotions, however, do cause changes in heart rate, sweating, and blood pressure that can be measured and with which someone’s feelings can be estimated. What we have described so far, in a sense, captures the big picture underlying this book. We have physiological quantities that are difficult to observe directly, we have measurements that are easier to acquire, and we have the ability to build mathematical models to estimate those inaccessible quantities.

show abstract

State-Space Model with One Binary and One Continuous Observation

Wickramasuriya,

Faghih

2023

Bayesian Filter Design for Computational Medicine

View full text Add to dashboard Cite

In this chapter, we will consider the case where $$x_{k}$$ x k evolves with time following a slightly more complicated state equation and gives rise to both a binary observation $$n_{k}$$ n k and a continuous observation $$r_{k}$$ r k . Prior to looking into the equation derivations, however, as in the previous chapter, we will again first consider a few example scenarios where the need for such a model arises.

show abstract

Real-Time Seizure State Tracking Using Two Channels: A Mixed-Filter Approach

Cited by 15 publications

References 44 publications

A Mixed Filtering Approach for Real-Time Seizure State Tracking Using Multi-Channel Electroencephalography Data

A Mixed Filtering Approach for Real-Time Seizure State Tracking Using Multi-Channel Electroencephalography Data

Introduction

State-Space Model with One Binary and One Continuous Observation

Contact Info

Product

Resources

About