ARM O R Advanced multi-paRametric Monitoring and analysis for diagnosis and Optimal management of epilepsy and Related brain disorders Prof. Vasileios Megalooikonomou University of Patras, Greece Clustering Workshop: eHealth and the Brain – ICT for Neuropsychiatric Health Brussels, November 5 th

Epilepsy a common, devastating and still incurable disorder treatment needs continuous adjustment and change to retain its efficacy multifactorial causes and paroxysmal nature needs multi-parametric monitoring for: accurate diagnosis, prediction, alerting and prevention, treatment follow-up and presurgical evaluation

ARMORs Main Objective Flexible monitoring optimized for each patient Tested in several case- studies Ambulatory monitoring tool Possibilities for detecting premonito- ry signs Feedback to the patient To manage and analyse a large number of already acquired and new multimodal and advanced technology data from brain and body activities of epileptic patients and controls (multichannel EEG, ECG, GSR, EMG, respiration, acceleration, and assisting modalities such as MEG) aiming to design a more holistic, personalized, medically efficient and economical monitoring system.

Scenarios Offline SCENARIO1 Epilepsy or non- epileptic paroxysmal events (NEPE) SCENARIO2 Delineation of the clinical EEG expression of different types of epilepsy SCENARIO3 Follow up – Medication evaluation SCENARIO5 Research on local signs of idiopathic generalized epilepsy SCENARIO6 Pre-surgical evaluation SCENARIO7 Nocturnal Seizures Online SCENARIO 4 Protection from seizures

Local Site / Home Gateway Offline Data Processing and Management Center User Interfaces EHR Application Server Information Server DSMS Online Analysis Offline: Analysis Fusion Data Mining Real Time: Monitoring Decision Support Personalized Analysis Storage: Sensor Data MRI, fMRI Patients Profile Analysis Results Adjust Model Parameters Online Analysis results ARMOR General View: ICT Components Mobiserv SHACU Mobiserv SHACU Events, Alerts Possible: Preprocessing Feature Extraction Storage Sensors Aggregator Raw Data Raw Data/ Preprocessed Data Local Storage Possible: Occasionally retrieve raw data Features/ Reduced Data Offline Analysis Server Local copies of data Legacy Datasets

ARMOR Middleware Architecture

Multi-parametric Data Processing & Analysis Analysis Creation of models of different types of epilepsy Correlation Analysis Detection of Epileptic Seizures Detection of Events of Interest Offline Data Processing & Analysis Pre-Processing Filtering Outlier Detection Summarization/ Feature Extraction Summarization/ Feature Extraction Data Transformation Support on Decision Making Data Fusion Personalized Patient Health Profiles (PHPs) Pattern Discovery

Multi-parametric Data Processing & Analysis Online Data Processing & Analysis Online analysis involves results from offline analysis in order to adjust parameters according to each patients personal profile. Online Analysis incorporates all necessary processing techniques adopted to the streaming nature of the data, in order to perform real- time : Detection of Seizures Detection of (patient-specific) abnormal values (e.g., excessive techycardia, oxygen level excursions) from several modalities Detection of other possible emergency situations Minimal Data Requirements (e.g. number of sensors) is incorporated with respect to the medical expectations and the desired levels of accuracy Online Processing involves tasks such as: Preprocessing Data Fusion Decision making performed with respect to processing time, memory and communication constraints. Online Processing involves tasks such as: Preprocessing Data Fusion Decision making performed with respect to processing time, memory and communication constraints.

Objectives and Achievements Clinical/Medical Facilitate and increase the yield of diagnostic, treatment and follow-up practice Support health care professionals in their decision making Reduce epilepsy related management costs; Increase understanding of epileptic seizure, epilepsy, and other non-epileptic paroxysmal events (NEPE) Advance the technology of Personal Health Systems (PHS) suitable for chronic diseases of multifactorial causes and unpredictable expression of their symptoms Clinical/Medical Facilitate and increase the yield of diagnostic, treatment and follow-up practice Support health care professionals in their decision making Reduce epilepsy related management costs; Increase understanding of epileptic seizure, epilepsy, and other non-epileptic paroxysmal events (NEPE) Advance the technology of Personal Health Systems (PHS) suitable for chronic diseases of multifactorial causes and unpredictable expression of their symptoms Information and Communication Technologies Develop novel multi-parametric data processing, management and analysis tools, both real time and off-line Design and develop adequate measuring/monitoring methodologies and systems Adopt and adapt prominent coordination/communication platforms providing robust and flexible end-to-end communication and assure security and privacy on sensitive medical data Information and Communication Technologies Develop novel multi-parametric data processing, management and analysis tools, both real time and off-line Design and develop adequate measuring/monitoring methodologies and systems Adopt and adapt prominent coordination/communication platforms providing robust and flexible end-to-end communication and assure security and privacy on sensitive medical data

Consortium Sensing & Control Systems S.L SPAIN Technological Educational Institute of Western Greece GREECE Kings College London UK INTRACOM S.A. Telecom Solutions GREECE Karlsruher Institut fuer Technologie GERMANY University of Patras GREECE AAI Scientific Cultural Services Ltd CYPRUS SYSTEMA Technologies S.A. GREECE