Personalised monitoring SYstems for Care in mental HEalth (ICT-247777)

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.

Within PSYCHE project  an innovative, personal, cost-effective, multi-parametric monitoring system has been developed. The new system is based on textile platforms and portable sensing devices for the long term and the short term acquisition of data, from a selected class of patients affected by mood disorders.  A novel portable devices for the monitoring of biochemical markers has been developed, the system allows to perform voice analysis and to collect  behavioral indexes correlated to patient state.  Patient data are processed and analyzed in the  platform that takes into consideration the Electronic Health Records (EHR), the personalized data reference system, as well as the medical analysis in order to verify the diagnosis and help in the prognosis of the disease. Finally communication  with the physician and feedback to the patient are performed through a closed loop approach that facilitated the management of the disease by fostering an icreased level of collaboration, with more autonomy and empowerment for the patient. The constant generation of feedbacks and the possibility to perform daily monitoring is used to imptove the quality of  illness management, to give patients support, to facilitate interaction between patient and physician as well as to alert the care givers in case of  relapse and insorgence of depressive or manic episodes, as the ultimate goal is to identify signal trends indicating detection and prediction of critical events. The physiological data that are 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 renal failure.

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).

PSYCHE project focused on the following activities:

  1. Integration of sensors for physiological and behavioral data into a monitoring system for patients affected by bipolar disorders.
  2. Development of novel portable devices for the monitoring of biochemical markers, voice analysis and a behavioral index correlated to mental illness. Special emphasis has been placed on the reliability of these systems and user acceptability;
  3. Implementation of an integrated system to collect data from bipolar patients. Bipolar patients in different states of the illness (mania or depression episodes, remission) have been considered. Controlled environments enabled the concurrent assessment of patient status by the medical professionals that has been used to annotate the recorded signals. The collected data along with the subjective annotations have been recorded in a reference database, where information from the EHR such as medication, patient history and exams, were integrated. 
  4. Data managing: the large amount of data was 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 was to identify signal trends indicating detection and prediction of critical events.
  5. User interface: once the group of patients has been selected, the most adequate input and feedback methods were 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.
  6. Professional interface: mental health professionals involved in PSYCHE performed patient monitoring tasks. A user friendly environment was developed where, through easily formulated queries, medical professionals are able to view current patient data as well as information extracted from electronically stored medical files. Embedded system intelligence allows the modeling and the prediction of patient status and was used for the development of an alert mechanism to identify situations requiring special attention.

  1. Psyche1bPsyche2b

Phyche platform combines physiological data with  biochemical measurements, voice analysis for emotional assessment and  attitudinal indicators based on questionarries,  sleep study, galvanic skin response, activity and gesture to assess the patient state and to extrapolate predictive indexes.

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 has  been created for content-based searches, tools for the extraction and signal processing, as well as tools for the integration with Electronic Health Record information. Moreover, it  constitutes 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 is automatically 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 makes up the flow of communication between the physician and patient and  helps 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  increases the success rate of treatment with prevention of painful depressive and life-devastating manic episodes, reducing the length of hospitalisation and out of work periods and sustaining patient’s hope through shorter therapeutic trial.