Design and Implementation of an On-Chip Patient-Specific Closed-Loop Seizure Onset and Termination Detection System

• Published in: IEEE journal of biomedical and health informatics Vol. 20; no. 4; pp. 996 - 1007
• Main Authors: Chen Zhang, Awais Bin Altaf, Muhammad, Yoo, Jerald
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.07.2016; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Biomedical monitoring; Classification; Design engineering; Detection algorithms; Dual-detector architecture (D2A); Electroencephalography; Electroencephalography - methods; Epilepsy - diagnosis; Epilepsy - physiopathology; epileptic seizure; Feature extraction; Hardware; Humans; machine learning; patient-specific; Patients; scalp electroencephalography (EEG); Seizing; seizure onset and termination detection; Seizures - diagnosis; Seizures - physiopathology; Sensitivity and Specificity; Signal Processing, Computer-Assisted; Stimulation; Support Vector Machine; Support vector machines; System-on-chip; transcranial electrical stimulation (tES)
• ISSN: 2168-2194; 2168-2208
• DOI: 10.1109/JBHI.2016.2553368

This paper presents the design of an area- and energy-efficient closed-loop machine learning-based patient-specific seizure onset and termination detection algorithm, and its on-chip hardware implementation. Application- and scenario-based tradeoffs are compared and reviewed for seizure detection and suppression algorithm and system which comprises electroencephalography (EEG) data acquisition, feature extraction, classification, and stimulation. Support vector machine achieves a good tradeoff among power, area, patient specificity, latency, and classification accuracy for long-term monitoring of patients with limited training seizure patterns. Design challenges of EEG data acquisition on a multichannel wearable environment for a patch-type sensor are also discussed in detail. Dual-detector architecture incorporates two area-efficient linear support vector machine classifiers along with a weight-and-average algorithm to target high sensitivity and good specificity at once. On-chip implementation issues for a patient-specific transcranial electrical stimulation are also discussed. The system design is verified using CHB-MIT EEG database [1] with a comprehensive measurement criteria which achieves high sensitivity and specificity of 95.1% and 96.2%, respectively, with a small latency of 1 s. It also achieves seizure onset and termination detection delay of 2.98 and 3.82 s, respectively, with seizure length estimation error of 4.07 s.