A contextual data mining approach toward assisting the treatment of anxiety disorders

Theodor Chris Panagiotakopoulos, Dimitrios Panagiotis Lyras, Miltos Livaditis, Kyriakos N. Sgarbas, George C. Anastassopoulos, Dimitrios K. Lymberopoulos

Research output: Contribution to journalArticlepeer-review

43 Citations (Scopus)


Anxiety disorders are considered the most prevalent of mental disorders. Nevertheless, the exact reasons that provoke them to patients remain yet not clearly specified, while the literature concerning the environment for monitoring and treatment support is rather scarce warranting further investigation. Toward this direction, in this study a context-aware approach is proposed, aiming to provide medical supervisors with a series of applications and personalized services targeted to exploit the multiparameter contextual data collected through a long-term monitoring procedure. More specifically, an application that assists the archiving and retrieving of the patients' health records was developed, and four treatment supportive services were considered. The three of them focus on the discovery of possible associations between the patient's contextual data; the last service aims at predicting the stress level a patient might suffer from, in a given context. The proposed approach was experimentally evaluated quantitatively (in terms of computational efficiency and time requirements) and qualitatively by experts on the field of mental health domain. The feedback received was very encouraging and the proposed approach seems quite useful to the anxiety disorders' treatment.

Original languageEnglish
Article number5378491
Pages (from-to)567-581
Number of pages15
JournalIEEE Transactions on Information Technology in Biomedicine
Issue number3
Publication statusPublished - May 2010
Externally publishedYes


  • Context awareness
  • Machine learning
  • Mental health
  • User modeling


Dive into the research topics of 'A contextual data mining approach toward assisting the treatment of anxiety disorders'. Together they form a unique fingerprint.

Cite this