Genetic Programming of Conventional Features to Detect Seizure Precursors.
Otis Smart1, Hiram Firpi, George Vachtsevanos
1gte851r@mail.gatech.edu , Ph.D. Candidate, Georgia Institute of Technology, Intelligent Control Systems Laboratory, Biomedical Engineering Research Group, 813 Ferst Drive, N.W., Atlanta, GA 30332.
Engineering Applications of Artificial Intelligence
|December 4, 2008
Summary
Genetic programming (GP) optimizes the selection and fusion of conventional features (C-features) for detecting seizure-precursors in intracranial electroencephalogram (IEEG) recordings. A genetically programmed feature significantly outperformed other methods in identifying epileptic events.
Area of Science:
- Neuroscience
- Computational Biology
- Medical Signal Processing
Background:
- Epileptic seizure-precursors in intracranial electroencephalogram (IEEG) recordings are crucial for localizing seizure generation regions.
- Current methods for detecting seizure-precursors often rely on manual review, lacking automated feature selection and fusion.
- Developing robust automated methods is essential for improving epilepsy treatment and diagnosis.
Purpose of the Study:
- To apply genetic programming (GP) for optimal selection and fusion of conventional features (C-features).
- To develop a single, genetically programmed feature for enhanced detection of seizure-precursors.
- To compare the performance of GP-derived features against other feature selection methods.
Main Methods:
- Utilized genetic programming (GP) to evolve and select optimal conventional features (C-features).
- Developed a binary detector incorporating genetically programmed features.
- Compared the performance of genetically programmed features against features selected via GP, forward sequential selection, and visual selection.
Main Results:
- A detector employing a genetically programmed feature demonstrated superior performance compared to other approaches.
- Achieved high performance metrics: 78.5% positive predictive value, 83.5% sensitivity, and 93% specificity.
- Results were validated at the 95% confidence level.
Conclusions:
- Genetic programming offers an optimal approach for automated selection and fusion of features for seizure-precursor detection.
- Genetically programmed features significantly enhance the accuracy and reliability of epileptic waveform detection in IEEG.
- This method holds promise for improving the localization of seizure generation regions and advancing epilepsy treatment.
Related Concept Videos
01:13Seizures: Classification
Epilepsy is primarily characterized by unpredictable seizures, either provoked by an identifiable factor, such as injury or illness, or unprovoked, occurring spontaneously without apparent cause.
Seizures are typically classified into two main categories: focal and generalized seizures.
Focal Seizures
Focal seizures originate from specific regions of the brain. These seizures are further sub-classified into two types:
Seizures are typically classified into two main categories: focal and generalized seizures.
Focal Seizures
Focal seizures originate from specific regions of the brain. These seizures are further sub-classified into two types:
01:24Epilepsy and Seizures: Overview
Epilepsy is a chronic neurological disease marked by recurrent, unpredictable seizures. These seizures are caused by abnormal electrical discharges in the brain, leading to behavior, sensation, or consciousness alterations. They can also cause transient impairment of awareness, interfering with daily activities.
Various factors can trigger epilepsy, including genetic factors, brain damage, metabolic causes, and unknown etiology. Diagnosis of epilepsy involves electroencephalography (EEG), which...
Various factors can trigger epilepsy, including genetic factors, brain damage, metabolic causes, and unknown etiology. Diagnosis of epilepsy involves electroencephalography (EEG), which...
01:20Seizures l: Introduction
Understanding seizures and epilepsy relies on key definitions that help in recognizing, classifying, and managing these disorders. These definitions provide a framework for recognizing, classifying, and managing seizure disorders.DefinitionsA seizure is a sudden, abnormal burst of electrical activity in the brain that can cause changes in awareness, movement, sensation, or behavior, depending on the area involved. Epilepsy is a chronic condition characterized by recurrent, unprovoked seizures,...
01:19Seizures ll: Types
Seizures are sudden bursts of abnormal electrical discharge in the brain that interfere with normal function. They are commonly divided into three groups: focal seizures, generalized seizures, and other types that do not fit neatly into either category.Focal SeizuresFocal seizures begin in a single brain region. When awareness is preserved, they are called focal aware seizures and may cause sensations such as tingling, unusual smells, or flashing lights. When awareness is impaired, they are...