Personalized Detection of Epileptic Seizure in the Internet of Things (IoT) Era

Research Partners

CHUV CHUV (Centre hospitalier universitaire vaudois)
UNILUniversité de Lausanne

Sources of Funding

Personalized Detection of Epileptic Seizure in the Internet of Things (IoT) Era
RESoRT
SNF ML-edge
Hasler MyPreHealth
Compusapien
Fvllmonti


Description



Epilepsy is affecting over 60 million individuals worldwide (70.000 in Switzerland), one third of whom suffer unpredictable recurrent seizures despite treatment, translating into a major medical, social and economic burden. However, part of this burden would be relieved if seizures could be reliably detected and forecasted by non-invasive monitoring of patients in their daily routine. This would allow triggering alarms and taking immediate actions to protect patients from the many severe consequences of seizures (including death), help physicians optimising treatment based on more accurate information about patients’ seizure frequency, and help patients planned their activities with knowledge about their risk of suffering a seizure in a given time period.

Current available methods for very long-term non-invasive ambulatory tracking of seizures only detect generalized tonic-clonic seizures (GTCS), which account for less than 15% of all seizures. While a large number of algorithms aiming at detecting focal seizures were developed and mostly tested off-line, no solution is yet available to perform long-term non-invasive ambulatory detection of such seizures with an appropriate sensitivity and specificity.

The development of multi-parametric wearable devices and breakthrough progress in the fields of seizure forecasting and Internet of Health (IoH) offer novel opportunities to tackle this issue. To achieve more general seizure detection and forecasting, we advocate that multi-biosignals shall be monitored. Indeed, currently detectable biosignals known to be sensitive to epileptic seizures, including 3D-accelerometry (3D-ACC), heart rate (HR), pulse oximetry (SpO2), electrodermal activity (EDA) and electroencephalography (EEG), all have advantages and drawbacks which make them poorly effective if used in isolation. Novel technologies, including those developed by our consortium, offer new possibilities to perform multimodal recordings using both wrist-worn multisensors combined with wearable EEG adapted to very long term recordings.

On top of this multi-biosignals, seizure detection and forecasting algorithms should be personalized according to the large inter-individual variability and strong intra-individual stereotypy of epileptic seizures and patterns of recurrence, with a capacity to learn from the false detections and missed seizures recorded in each individual. Coupling seizure detection and forecasting creates a virtuous circle through which improved seizure detection helps optimising forecasting and vice versa. Finally, running such complex multi-biosensor wearable device with embedded machine learning engine comes with very challenging energy requirements that need to be tackled.

To achieve breakthrough seizure detection and forecasting, we thus propose an ambitious multi-disciplinary project that will deliver an ultra-low-energy embedded system connected to multi-parametric sensing wearables, and a central computing platform to tune the machine learning technology and lead to optimal personalized seizure detection and forecasting algorithms. The project will use an agile and adaptive organisation to optimize interaction between the data science and engineering groups developing these innovative IoH solutions and the clinical studies providing patients’ data and testing the performance of these solutions in hospital and ambulatory environments. Retrospective and prospectively collected datasets of more than 1200 patients will be used during this project, including EEG, ECG, PPG, SPO2, EDA, 3D-ACC and arm surface EMG. These data will be used to develop novel interpretable machine learning algorithms and specify the requirements for an optimal IoH solution. In parallel, several prototypes of wearables EEG, including behind the ear EEG for sleep-friendly night time recording and e-Glasses EEG for non-stigmatising day time recording, will be developed and integrated with non-EEG biosensors and low-energy embedded machine learning processor to achieve personalized and coupled seizure detection and forecasting.

Videos



Documentation

Personalized Detection of Epileptic Seizure in the Internet of Things (IoT) Era
Systematic Assessment of Hyperdimensional Computingfor Epileptic Seizure Detection

Related Publications

M2D2: Maximum-Mean-Discrepancy Decoder for Temporal Localization of Epileptic Brain Activities
Amirshahi, Alireza; Thomas, Anthony; Aminifar, Amir; Rosing, Tajana; Atienza Alonso, David
2022-09-22IEEE Journal of Biomedical and Health Informatics (JBHI)Publication funded by SNF ML-edge (ML-edge: Enabling Machine-Learning-Based Health Monitoring in Edge Sensors via Architectural Customization)Publication funded by Personalized Detection of Epileptic Seizure in the Internet of Things (IoT) Era (Sinergia – interdisciplinary, collaborative and breakthrough)Publication funded by RESoRT (RESoRT: Reliable Epileptic Seizure Monitoring in Real Time)
INCLASS: Incremental Classification Strategy for Self-Aware Epileptic Seizure Detection
Ferretti, Lorenzo; Ansaloni, Giovanni; Marquis, Renaud; Teijeiro, Tomas; Ryvlin, Philippe; Atienza, David; Pozzi, Laura
2022-03-23Conference PaperPublication funded by Compusapien (Next-gen computing systems inspired by the human brain)Publication funded by SNF ML-edge (ML-edge: Enabling Machine-Learning-Based Health Monitoring in Edge Sensors via Architectural Customization)Publication funded by Fvllmonti ((FETPROACT))
Personalized Real-Time Federated Learning for Epileptic Seizure Detection
Baghersalimi, Saleh; Teijeiro, Tomas; Atienza, David; Aminifar, Amir
2021-07-09IEEE Journal of Biomedical and Health InformaticsPublication funded by Personalized Detection of Epileptic Seizure in the Internet of Things (IoT) Era (Sinergia – interdisciplinary, collaborative and breakthrough)Publication funded by DeepHealth H2020 (Deep-Learning and HPC to Boost Biomedical Applications for Health)Publication funded by SNF ML-edge (ML-edge: Enabling Machine-Learning-Based Health Monitoring in Edge Sensors via Architectural Customization)Publication funded by Hasler MyPreHealth (Predicting Episodic Disorders with Health Companions)Publication funded by RESoRT (RESoRT: Reliable Epileptic Seizure Monitoring in Real Time)
Interpreting deep learning models for epileptic seizure detection on EEG signals
Gabeff, Valentin; Teijeiro, Tomas; Zapater, Marina; Cammoun, Leila; Rheims, Sylvain; Ryvlin, Philippe; Atienza, David
2021-05-01Artificial Intelligence in MedicinePublication funded by RECIPE H2020 (REliable power and time-ConstraInts-aware Predictive management of heterogeneous Exascale systems)
Self-Aware Anomaly-Detection for Epilepsy Monitoring on Low-Power Wearable Electrocardiographic Devices
Forooghifar, Farnaz; Aminifar, Amin; Teijeiro, Tomas; Aminifar, Amir; Jeppesen, Jesper; Beniczky, Sandor; Atienza Alonso, David
2021-04-12Conference PaperPublication funded by SNF ML-edge (ML-edge: Enabling Machine-Learning-Based Health Monitoring in Edge Sensors via Architectural Customization)Publication funded by Personalized Detection of Epileptic Seizure in the Internet of Things (IoT) Era (Sinergia – interdisciplinary, collaborative and breakthrough)Publication funded by RESoRT (RESoRT: Reliable Epileptic Seizure Monitoring in Real Time)
Systematic Assessment of Hyperdimensional Computing for Epileptic Seizure Detection
Pale, Una; Teijeiro, Tomas; Atienza Alonso, David
2021Conference PaperPublication funded by Personalized Detection of Epileptic Seizure in the Internet of Things (IoT) Era (Sinergia – interdisciplinary, collaborative and breakthrough)Publication funded by SNF ML-edge (ML-edge: Enabling Machine-Learning-Based Health Monitoring in Edge Sensors via Architectural Customization)
EpilepsyGAN: Synthetic Epileptic Brain Activities with Privacy Preservation
Pascual Ortiz, Damián; Amirshahi, Alireza; Aminifar, Amir; Atienza, David; Ryvlin, Philippe; Wattenhofer, Roger
2020-11-30IEEE Transactions on Biomedical EngineeringPublication funded by SNF ML-edge (ML-edge: Enabling Machine-Learning-Based Health Monitoring in Edge Sensors via Architectural Customization)Publication funded by Hasler MyPreHealth (Predicting Episodic Disorders with Health Companions)Publication funded by Personalized Detection of Epileptic Seizure in the Internet of Things (IoT) Era (Sinergia – interdisciplinary, collaborative and breakthrough)
Noninvasive detection of focal seizures in ambulatory patients
Ryvlin, Philippe; Cammoun, Leila; Hubbard, Ilona; Ravey, France; Beniczky, Sandor; Atienza, David
2020-06-02Epilepsia
Noise-Resilient and Interpretable Epileptic Seizure Detection
Hitchcock Thomas, Anthony; Aminifar, Amir; Atienza Alonso, David
2020-05-17[2020 IEEE International Symposium on Circuits and Systems (ISCAS). Proceedings]Publication funded by Hasler MyPreHealth (Predicting Episodic Disorders with Health Companions)Publication funded by DeepHealth H2020 (Deep-Learning and HPC to Boost Biomedical Applications for Health)Publication funded by SNF ML-edge (ML-edge: Enabling Machine-Learning-Based Health Monitoring in Edge Sensors via Architectural Customization)
Robust Epileptic Seizure Detection on Wearable Systems with Reduced False-Alarm Rate
Zanetti, Renato; Aminifar, Amir; Atienza Alonso, David
2020Publication funded by Hasler MyPreHealth (Predicting Episodic Disorders with Health Companions)