OBJECTIVE: Automated seizure detection in the home environment has attracted increasing interest in recent decades. Heart rate-based seizure detection is a way to detect temporal lobe epilepsy seizures at home, but patient-independent classifiers have been shown to be insufficiently accurate. This is due to the high patient-dependence of heart rate features, whereas this method does not use patient-specific data. Patient-specific classifiers take into account patient-specific data, but often not enough patient data are available for a fully robust patient-specific classifier. Therefore a real-time adaptive seizure detection algorithm is proposed here. APPROACH: The algorithm starts with a patient-independent classifier, but gradually adapts to the patient-specific characteristics while they are obtained 'on the go'. This is done by using real-time user feedback to annotate previously generated alarms, causing an immediate update to the used support vector machine classifier. Data annotated as seizures are automatically removed from the updating procedure if their detection would lead to too many false alarms. This is done in order to cope with potentially incorrect feedback. MAIN RESULTS: The adaptive classifier resulted in an overall sensitivity of 77.12% and 1.24 false alarms per hour when applied to over 2833 h of heart rate data from 19 patients with 153 clinical seizures. This is around 30% fewer false alarms compared to a patient-independent classifier with a similar sensitivity. SIGNIFICANCE: This low-complexity adaptive algorithm is able to deal well with incorrect feedback, making it ideal for a seizure warning system, and in the future it will also include complementary modalities to improve its performance.
OBJECTIVE: Automated seizure detection in the home environment has attracted increasing interest in recent decades. Heart rate-based seizure detection is a way to detect temporal lobe epilepsy seizures at home, but patient-independent classifiers have been shown to be insufficiently accurate. This is due to the high patient-dependence of heart rate features, whereas this method does not use patient-specific data. Patient-specific classifiers take into account patient-specific data, but often not enough patient data are available for a fully robust patient-specific classifier. Therefore a real-time adaptive seizure detection algorithm is proposed here. APPROACH: The algorithm starts with a patient-independent classifier, but gradually adapts to the patient-specific characteristics while they are obtained 'on the go'. This is done by using real-time user feedback to annotate previously generated alarms, causing an immediate update to the used support vector machine classifier. Data annotated as seizures are automatically removed from the updating procedure if their detection would lead to too many false alarms. This is done in order to cope with potentially incorrect feedback. MAIN RESULTS: The adaptive classifier resulted in an overall sensitivity of 77.12% and 1.24 false alarms per hour when applied to over 2833 h of heart rate data from 19 patients with 153 clinical seizures. This is around 30% fewer false alarms compared to a patient-independent classifier with a similar sensitivity. SIGNIFICANCE: This low-complexity adaptive algorithm is able to deal well with incorrect feedback, making it ideal for a seizure warning system, and in the future it will also include complementary modalities to improve its performance.
Authors: Anouk van Westrhenen; Thomas De Cooman; Richard H C Lazeron; Sabine Van Huffel; Roland D Thijs Journal: Clin Auton Res Date: 2018-10-30 Impact factor: 4.435