Personalised monitoring SYstems for Care in mental HEalth
(ICT-247777, EU funded project)

Starting date: 01/01/2010; closing date: 30/04/2013; total project cost: 3,820,363 Euros; total EC funding: 2,909,971 Euros.

One of the areas of great demand for the need of continuous monitoring, patient participation and medical prediction is that of mood disorders, more specifically bipolar disorders. Due to the unpredictable and episodic nature of bipolar disorder, it is necessary to take the traditional standard procedures of mood assessment through the administration of rating scales and questionnaires and integrate this with tangible data found in emerging research on central and peripheral changes in brain function that may be associated to the clinical status and response to treatment throughout the course of bipolar disorder.

PSYCHE project will develop a personal, cost-effective, multi-parametric monitoring system based on textile platforms and portable sensing devices for the long term and short term acquisition of data from selected class of patients affected by mood disorders. The project will develop novel portable devices for the monitoring of biochemical markers, voice analysis and a behavioral index correlated to patient state. Additionally, brain functional studies will be performed under specific experimental protocols in order to correlate central measures with the clinical assessment, and the parameters measured by Psyche platform. The acquired data will be processed and analyzed in the established platform that takes into consideration the Electronic Health Records (EHR) of the patient, a personalized data referee system, as well as medical analysis in order to verify the diagnosis and help in prognosis of the disease. Finally communication and feedback to the patient and physician will be performed through a closed loop approach that will facilitated diseases management by fostering a new collaboration, with more autonomy and empowerment for the patient. Constant feedback and monitoring will be used to manage the illness, to give patients support, to facilitate interaction between patient and physician as well as to alert professionals in case of patients relapse and depressive or manic episodes income, as the ultimate goal is to identify signal trends indicating detection and prediction of critical events. The physiological data that will be collected with these non-invasive devices include heart rate variability, respiratory rate, activity and movement. These devices are currently available and have been successfully tested for the management of diseases such as heart diseases, chronic obstructive pulmonary disease, metabolic disorders and diabetes.

Data acquisition will also take place using behavioral sensors based on the correlation of data deriving from biochemical measurements, voice analysis for emotional assessment and detection of attitudinal indicators (social interaction, sleep quality, galvanic skin response, activity and gesture) that can be implemented to extrapolate predictive indexes.

While no biological markers are available for clinical purposes, different research strategies are however employed to measure potentially relevant central and peripheral changes in brain function that may be associated with the clinical status, response treatment and course of the disease. Other parameters to be taken into consideration include the study of sleep pattern alteration, peripheral measures in cardiovascular and respiratory functioning, electrodermal response, as well as the secretion of stress-related hormones, including change in the diurnal variations of all these measurements (circadian rhythms).

As result of the acquisition phases of the project, a reference database with annotated physiological and behavioral signals from patients with bipolar disorder, cyclothymic subjects and healthy individuals will be created that will become the main part of an integrated platform offering a basis for content-based searches, tools for feature extraction and signal processing, as well as tools for integration with Electronic Health Record information. Moreover, it will constitute the basis for the extraction of correlations between combinations of signals and disorder status leading to the identification of signal patterns and trends predicting a critical state of the disorder. Once these data are acquired and processed, the physicians will be updated to patient response to treatment and alerted in case of critical predicting indexes. The professional loop will help the psychiatrics in preventing relapse by the early detection of change in behaviors, sleep, physiological or biochemical signs. This will make up the flow of communication between the physician and patient and will help in detecting fluctuations in mood behavior. Empowering the patient to take control of his or her mental health along with the constant help of a physician will greatly increase the success rate of treatment with prevention of painful depressive and life-devastating manic episodes, thereby reducing the length of hospitalisation and out of work periods and sustaining patient’s hope through shorter therapeutic trial.

PSYCHE project will focus on the following objectives:

i) Integration of sensors for physiological and behavioral data into a monitoring system for patients affected by bipolar disorders.

ii) Development of novel portable devices for the monitoring of biochemical markers, voice analysis and a behavioral index correlated to mental illness. Special emphasis will be placed on the reliability of these systems and user acceptability;

iii) Implementation of an integrated system to collect data from bipolar patients. Bipolar patients in different states of the illness (mania or depression episodes, remission) will be considered. Controlled environments will enable the concurrent assessment of patient status by the medical professionals that will be used to annotate the recorded signals. The collected data along with the subjective annotations will be recorded in a reference database, where information from the EHR such as medication, patient history and exams, will be integrated. Semantic technologies will be exploited to enable content-based searches.

iv) Data managing: the large amount of data will be analyzed using state-of-the-art signal processing and data mining methods to correlate patient status assessment (from health professional annotations and other clinical findings) with the measured parameters. The ultimate goal is to identify signal trends indicating detection and prediction of critical events.

v) User interface: once the group of patients has been selected, the most adequate input and feedback methods will be defined. Adequate devices will be chosen depending on user needs and expectations, and therefore different dialogue strategies will be defined depending on the selected devices and interaction techniques. Different techniques will be studied in order to adapt the information and presentation to the use scenarios.

vi) Professional interface: mental health professionals involved in PSYCHE will perform patient monitoring tasks. A user friendly environment will be developed where, through easily formulated queries, medical professionals will be able to view current patient data as well as information extracted from electronically stored medical files. Embedded system intelligence will allow for the modeling and prediction of patient status and will be used for the development of an alert mechanism to identify situations requiring special attention.