J. Low Power Electron. Appl. 2011, 1(1), 150-174; doi:10.3390/jlpea1010150
Review

Data-Driven Approaches for Computation in Intelligent Biomedical Devices: A Case Study of EEG Monitoring for Chronic Seizure Detection

1 Princeton University, Engineering Quadrangle B-226, Olden Street, Princeton, NJ 08544, USA 2 Massachusetts General Hospital & MIT , 77 Massachusetts Avenue, Cambridge, MA 02139, USA
* Authors to whom correspondence should be addressed.
Received: 25 November 2010; in revised form: 13 April 2011 / Accepted: 20 April 2011 / Published: 26 April 2011
PDF Full-text Download PDF Full-Text [3385 KB, Updated Version, uploaded 27 April 2011 11:01 CEST]
The original version is still available [3377 KB, uploaded 26 April 2011 17:15 CEST]
Abstract: Intelligent biomedical devices implies systems that are able to detect specific physiological processes in patients so that particular responses can be generated. This closed-loop capability can have enormous clinical value when we consider the unprecedented modalities that are beginning to emerge for sensing and stimulating patient physiology. Both delivering therapy (e.g., deep-brain stimulation, vagus nerve stimulation, etc.) and treating impairments (e.g., neural prosthesis) requires computational devices that can make clinically relevant inferences, especially using minimally-intrusive patient signals. The key to such devices is algorithms that are based on data-driven signal modeling as well as hardware structures that are specialized to these. This paper discusses the primary application-domain challenges that must be overcome and analyzes the most promising methods for this that are emerging. We then look at how these methods are being incorporated in ultra-low-energy computational platforms and systems. The case study for this is a seizure-detection SoC that includes instrumentation and computation blocks in support of a system that exploits patient-specific modeling to achieve accurate performance for chronic detection. The SoC samples each EEG channel at a rate of 600 Hz and performs processing to derive signal features on every two second epoch, consuming 9 μJ/epoch/channel. Signal feature extraction reduces the data rate by a factor of over 40×, permitting wireless communication from the patient’s head while reducing the total power on the head by 14×.
Keywords: biomedical; body-area networks; electroencephalography; implantable; low-noise amplifiers; low-power electronics; machine-learning; subthreshold

Article Statistics

Load and display the download statistics.

Citations to this Article

Cite This Article

MDPI and ACS Style

Verma, N.; Lee, K.H.; Shoeb, A. Data-Driven Approaches for Computation in Intelligent Biomedical Devices: A Case Study of EEG Monitoring for Chronic Seizure Detection. J. Low Power Electron. Appl. 2011, 1, 150-174.

AMA Style

Verma N, Lee KH, Shoeb A. Data-Driven Approaches for Computation in Intelligent Biomedical Devices: A Case Study of EEG Monitoring for Chronic Seizure Detection. Journal of Low Power Electronics and Applications. 2011; 1(1):150-174.

Chicago/Turabian Style

Verma, Naveen; Lee, Kyong Ho; Shoeb, Ali. 2011. "Data-Driven Approaches for Computation in Intelligent Biomedical Devices: A Case Study of EEG Monitoring for Chronic Seizure Detection." J. Low Power Electron. Appl. 1, no. 1: 150-174.

J. Low Power Electron. Appl. EISSN 2079-9268 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert