ARMOR provides on-line and off-line analysis of data with the help of medical databases and patient's medical file for the purpose of assisting diagnosis, prognosis and treatment as well as for predicting and classifying seizures. New methods and tools are developed for multimodal data pre-processing and fusion, real-time and offline data mining of multi-parametric streaming and archived data to discover patterns and associations between external indicators and mental states, lag correlations, motifs, or outliers (vital signs changing significantly), automatic summarization of results, and efficient medical context data management.

Offline analysis mostly concerns the accurate diagnosis of seizures (recognition and discrimination between epilepsy and non-epileptic paroxysmal events) and the identification of various risks of disease development, recurrence, and generally assistance of the health professionals in suggesting appropriate treatment and evaluating its effectiveness. Computer assisted diagnosis services assist the decision making process when a medical condition needs to be treated, providing plausible explanations related to the abnormal combination of vital sign values. These explanations are mostly based on the outcome (conclusions and guidelines) of the offline data analysis module and are enhanced with the personalized patient health profile together with models created for each different type of epilepsy. Information obtained by the analysis of patient's health condition and their environment is used in the decision support system.

Real time (online) analysis is performed on multi-parametric stream data to detect signals beyond the limits, identify seizure premonitory signs, discover typical patterns of activity followed by seizures, detect atypical patterns of activity/behaviour based on models that are created. Methods for combining the information extracted from the patient's health profile with real-time sensor data are developed, aiming to provide accurate information to the online decision support system and to deliver appropriate alerts to the health professional.

State-of-the-art measuring system and flexible coordination/communication platform are used, allowing long term monitoring, medical management and decision support suited to the patient's medical condition without disrupting the patient's life pattern and normal environment while facing issues of patient and data security, integrity and privacy.

The system is tested in several case studies and evaluated as a wide use ambulatory monitoring tool for seizures efficient diagnosis and management including possibilities for detecting premonitory signs and providing feedback to the health professional.