Posts Tagged detection

[Abstract + References] Evaluation of an Activity Tracker to Detect Seizures Using Machine Learning

Abstract

Currently, the tracking of seizures is highly subjective, dependent on qualitative information provided by the patient and family instead of quantifiable seizure data. Usage of a seizure detection device to potentially detect seizure events in a population of epilepsy patients has been previously done. Therefore, we chose the Fitbit Charge 2 smart watch to determine if it could detect seizure events in patients when compared to continuous electroencephalographic (EEG) monitoring for those admitted to an epilepsy monitoring unit. A total of 40 patients were enrolled in the study that met the criteria between 2015 and 2016. All seizure types were recorded. Twelve patients had a total of 53 epileptic seizures. The patient-aggregated receiver operating characteristic curve had an area under the curve of 0.58 [0.56, 0.60], indicating that the neural network models were generally able to detect seizure events at an above-chance level. However, the overall low specificity implied a false alarm rate that would likely make the model unsuitable in practice. Overall, the use of the Fitbit Charge 2 activity tracker does not appear well suited in its current form to detect epileptic seizures in patients with seizure activity when compared to data recorded from the continuous EEG.

References

1.Sander, JW . The epidemiology of epilepsy revisited. Curr Opin Neurol. 2003;16(2):165–170.
Google Scholar | Crossref | Medline
2.Jory, C, Shankar, R, Coker, D, McLean, B, Hanna, J, Newman, C. Safe and sound? A systematic literature review of seizure detection methods for personal use. Seizure. 2016;36:4–15.
Google Scholar | Crossref | Medline
3.Beniczky, S, Jeppesen, J. Non-electroencephalography-based seizure detection. Curr Opin Neurol. 2019;32(2):198–204.
Google Scholar | Crossref | Medline
4.Ryvlin, P, Ciumas, C, Wisniewski, I, Beniczky, S. Wearable devices for sudden unexpected death in epilepsy prevention. Epilepsia. 2018;59(suppl 1):61–66.
Google Scholar | Crossref | Medline
5.Poh, MZ, Loddenkemper, T, Reinsberger, C, et al. Convulsive seizure detection using a wrist-worn electrodermal activity and accelerometry biosensor. Epilepsia. 2012;53(5):e93–e97.
Google Scholar | Crossref | Medline
6.Feehan, LM, Geldman, J, Sayre, EC, et al. Accuracy of Fitbit devices: systematic review and narrative syntheses of quantitative data. JMIR mHealth uHealth. 2018;6(8):e10527.
Google Scholar | Crossref | Medline
7.Fisher, RS, Cross, JH, French, JA, et al. Operational classification of seizure types by the International League Against Epilepsy: position paper of the ILAE Commission for Classification and Terminology. Epilepsia. 2017;58(4):522–530.
Google Scholar | Crossref | Medline
8.Fisher, RS, Cross, JH, D’Souza, C, et al. Instruction manual for the ILAE 2017 operational classification of seizure types. Epilepsia. 2017;58(4):531–542.
Google Scholar | Crossref | Medline
9.Scheffer, IE, Berkovic, S, Capovilla, G, et al. ILAE classification of the epilepsies: position paper of the ILAE Commission for Classification and Terminology. Epilepsia. 2017;58(4):512–521.
Google Scholar | Crossref | Medline
10.Lee, J, Finkelstein, J. Consumer sleep tracking devices: a critical review. Stud Health Technol Inform. 2015;210:458–460.
Google Scholar | Medline
11.Montgomery-Downs, HE, Insana, SP, Bond, JA. Movement toward a novel activity monitoring device. Sleep Breath. 2012;16(3):913–917.
Google Scholar | Crossref | Medline | ISI
12.Moreno-Pino, F, Porras-Segovia, A, Lopez-Esteban, P, Artes, A, Baca-Garcia, E. Validation of Fitbit charge 2 and Fitbit alta HR against polysomnography for assessing sleep in adults with obstructive sleep apnea. J Clin Sleep Med. 2019;15(11):1645–1653.
Google Scholar | Crossref | Medline
13.Regalia, G, Onorati, F, Lai, M, Caborni, C, Picard, RW. Multimodal wrist-worn devices for seizure detection and advancing research: focus on the Empatica wristbands. Epilepsy Res. 2019;153:79–82.
Google Scholar | Crossref | Medline
14.Van Ness, PC . Are seizure detection devices ready for prime time? Epilepsy Curr. 2019;19(1):36–37.
Google Scholar | SAGE Journals
15.Halford, JJ, Sperling, MR, Nair, DR, et al. Detection of generalized tonic-clonic seizures using surface electromyographic monitoring. Epilepsia. 2017;58(11):1861–1869.
Google Scholar | Crossref | Medline
16.Patterson, AL, Mudigoudar, B, Fulton, S, et al. SmartWatch by SmartMonitor: assessment of seizure detection efficacy for various seizure types in children, a large prospective single-center study. Pediatr Neurol. 2015;53(4):309–311.
Google Scholar | Crossref | Medline
17.van Andel, J, Leijten, F, van Delden, H, van Thiel, G. What makes a good home-based nocturnal seizure detector? A value sensitive design. PLoS One. 2015;10(4):e0121446.
Google Scholar | Crossref | Medline
18.Bruno, E, Simblett, S, Lang, A, et al. Wearable technology in epilepsy: the views of patients, caregivers, and healthcare professionals. Epilepsy Behav. 2018;85:141–149.
Google Scholar | Crossref | Medline
19.Patel, AD, Moss, R, Rust, SW, et al. Patient-centered design criteria for wearable seizure detection devices. Epilepsy Behav. 2016;64(pt A):116–121.
Google Scholar | Crossref | Medline
20.Kurada, AV, Srinivasan, T, Hammond, S, Ulate-Campos, A, Bidwell, J. Seizure detection devices for use in antiseizure medication clinical trials: a systematic review. Seizure. 2019;66:61–69.
Google Scholar | Crossref | Medline
21.Benedetto, S, Caldato, C, Bazzan, E, Greenwood, DC, Pensabene, V, Actis, P. Assessment of the Fitbit charge 2 for monitoring heart rate. PLoS One. 2018;13(2):e0192691.
Google Scholar | Crossref | Medline
22.Gutierrez, EG, Crone, NE, Kang, JY, Carmenate, YI, Krauss, GL. Strategies for non-EEG seizure detection and timing for alerting and interventions with tonic-clonic seizures. Epilepsia. 2018;59(suppl 1):36–41.
Google Scholar | Crossref | Medline
23.Beniczky, S, Ryvlin, P. Standards for testing and clinical validation of seizure detection devices. Epilepsia. 2018;59(suppl 1):9–13.
Google Scholar | Crossref | Medline

, , , , , , ,

Leave a comment

[WEB SITE] Tele-Epilepsy and Remote Seizure Monitoring – Case Study

Case Study

Tele-Epilepsy and Remote Seizure Monitoring using Shimmer Sensors

Introduction

Shimmer offers a wireless sensor platform along with low power connections and host software to enable researchers, whether clinical, applied or academic, to use wearable sensing technologies in many different applications.

Research Objective

The World Health Organization calls epilepsy a chronic noncommunicable disorder of the brain. It is known to affect more than 50 million people all over the world.

Researchers from the Netherlands are currently studying the role of Tele-Epilepsy and Remote Seizure Monitoring, using the Shimmer platform. The research is a joint project between UMC Utrecht, Kempaenhaeghe-Heeze, and SEIN-Zwolle. The aims of the study are:

Detection and alarm triggering when a major nocturnal epileptic seizure occurs: this is done using an integrated Multi-Sensor Detection Instrument (MSDI) which uses a combination of electrocardiography (ECG) and 3-D accelerometry data. This data is collected with the help of Shimmer sensors, with linkage to audio and automated video frame analysis.

Research Method

The objective of this project is to bring out a new device that uses multiple modes of sensing to detect the occurrence of nocturnal epileptic seizures as well as to set off an alarm so as to alert caregivers in this case. The system uses an MSDI which uses Shimmer sensors, audio signals and video streams, yielding both ECG and 3-D accelerometry data.

A diagnostic trial was first conducted to arrive at the best combinations of patient factors and sensory modalities from among the four used in the MSDI, which could reliably detect a seizure. The groups targeted by the study included children under 16 who were staying at home, adolescents who were mentally challenged, and adults living under care, either at home or in another care environment.

Two Shimmer sensors were used per patient, with the accelerometer worn on the right upper arm and the accelerometer-ECG combination on the left upper arm. The data arriving from the sensors was fed to a PC which integrated the input and sent an alarm if the resulting output went beyond the set threshold. Real-time video and audio streams were set up between the PC and a monitoring device.

Data-Driven Results

The Shimmer sensors were preferred in this study because they were easily adaptable as well as being capable of being set to required configurations. The researchers were able to take advantage of the open platform and its easy interfacing with developer tools such as MATLAB, which was not easily available with other providers at the time of the research at a price which was competitive.

The images below show the MSDI as well as the algorithms that the team developed to analyze the four signal modalities with some examples of acquired data. This was taken from recordings of two patients, the one on the left showing a tonic seizure and that on the right a tonic-clonic seizure.

Concept to Delivery – 90% Efficiency

The choice of the Shimmer platform was based upon the CE certification, among other reasons. This hardware was already classified as a medical device, which made it possible to integrate it into a model used for research on human patients, unlike other research projects.

The MSDI using Shimmer sensors has now been tested in more than 50 patients who were in hospital, in four different centers, comparing the yield against the gold-standard for EEG-video monitoring which is the established method to monitor patients who may potentially develop seizures. This reliance upon EEG-video monitoring is because of the reliability of neural feedback in this type of event.

However, this research was favorably assessed in the hospital setting before being tested on patients who were at home. The latest study also showed excellent results with 90% efficacy in detecting nocturnal seizures as compared to the EEG monitoring technology. More work remains to be done, including refining the software which runs real-time analysis of the data, integrating the sensor data and validating the results in this domestic situation.

Shimmer Research – Sensing Solved

While many solutions compete for place in this niche, Shimmer boasts of advanced technology, supporting software and specialized applications which help to control the type of data that is acquired.

This in turn helps researchers look into how to interpret the data collected by the Shimmer platform, as well as to develop new algorithms to make sense of the kinematic and physiological data that pours in with these tools.

In summary, the benefits of using Shimmer technology include:

  • Shimmer suits most research applications because of its ability to help arrive at the meaning of the raw data, and apply this meaning for the benefit of patients and their caregivers
  • Shimmer solutions reduce the time taken for development of an application and its cost by 80%
  • Shimmer technology yields data that is high-quality, robust and accurate
  • The solution is easy to customize to specific applications
  • It gives the researcher full control over what data is captured, as well as over its interpretation and analysis
  • Shimmer solutions can be leveraged with the range of vital support tools available
  • Shimmer solutions are used by a wide range of researchers, both independent, as well as in collaboration with academic and research institutes

About ShimmerShimmer

Since the Shimmer technology was originally conceived in 2006, to when the company was founded in 2008, we have been pioneering wearable sensor technology and solutions, and currently ship to over 80 countries worldwide.

Overview

Shimmer is an ‘end-to-end’ wearable technologies services and sensor manufacture company, that constantly provides best-in-class wearable sensing technology, combined with leading experience and expertise to our customers right across the globe. Our solutions and services range from customization services and volume manufacture to complete wearable sensing solutions of any complexity.

Our Services Include

Shimmer offers full customization of our wearable sensor technology to meet your specific application and end user requirement, with low cost, quick-turn development builds

Consultancy & Systems Integration

Expertise in evaluating, rationalizing and integrating wearable sensing solutions, effectively from initial concept to successful integration with wider systems

Application Development

Our experienced applications Engineers meet the most ambitious and complex requirement from embedded programming, firmware development data processing and display

Custom Design & Manufacture

Hardware evaluation, design and volume manufacture to meet your requirements. Incorporating virtual prototyping and interactive feedback from our ISO accredited production line

Engagement and Development Framework: We offer a range of engagement and pricing models to meet our clients’ diverse needs and stage of business growth. All projects are based upon an agreed and detailed specification of work to ensure the requirements are effectively communicated at all stages of the development cycle.


Sponsored Content Policy: News-Medical.net publishes articles and related content that may be derived from sources where we have existing commercial relationships, provided such content adds value to the core editorial ethos of News-Medical.Net which is to educate and inform site visitors interested in medical research, science, medical devices and treatments.

Last updated: Jun 7, 2018 at 8:07 AM

via Tele-Epilepsy and Remote Seizure Monitoring

, , , ,

Leave a comment

[ARTICLE] Hemisphere-dependent ipsilesional deficits in hemianopia: Sightblindness in the ‘intact’ visual field

Highlights

  • The ipsilesional visual field does not remain intact after a unilateral occipital lesion.
  • The ipsilesional deficit in hemianopes is partially dependent upon the lesion side.
  • Right hemianopes (left brain damaged patients) exhibit a specific deficit for high spatial frequency processing.
  • Left hemianopes (right brain damaged patients) show a global ipsilesional deficit for high and low spatial frequency processing.

Abstract

Objectives: In addition to exhibiting a severe contralesional deficit, hemianopic patients may also show a subtle ipsilesional visual deficit, called sightblindness (the reverse case of ‘blindsight). We have tested for the presence, nature and extent of such an ipsilesional visual field (IVF) deficit in hemianopic patients that we assigned to perform two visual tasks. Namely, we aimed to ascertain any links between this ipsilesional deficit, the lesion side, and the tasks performed or the stimuli used.

Methods: We tested left and right homonymous hemianopic (right brain-damaged RBD and left brain-damaged LBD, respectively) patients and healthy controls. Natural-scene images, either non-filtered or filtered in low or high spatial frequency (LSF or HSF, respectively,) were presented in the IVF of each subject. For the two tasks, detection (“Is an image present?”) and categorization (“Is the image of a forest or a city?”), accuracy and response time were recorded.

Results: In the ipsilesional visual field the RBD (left hemianopes) patients made more errors on the categorization task than did their matched controls, regardless of image type. In contrast, the only task in which the LBD (right hemianopes) patients made more errors than did the controls was the HSF-images task. Furthermore, in both tasks (detection and categorization), the RBD patients performed worse than did the LBD patients.

Discussion: Homonymous hemianopic patients do indeed exhibit a specific visual deficit in their IVF, which was previously thought to be unaffected. We have demonstrated that the nature and severity of this ipsilesional deficit is determined by the side of the occipital lesion as well as by the tasks and the stimuli. Our findings corroborate the idea of hemispheric specialization at the occipital level, which might determine the nature and severity of ipsilesional deficits in hemianopic patients.

via Hemisphere-dependent ipsilesional deficits in hemianopia: Sightblindness in the ‘intact’ visual field.

, , , , , ,

Leave a comment

%d bloggers like this: