Correlation of significant places with self-reported state of bipolar disorder patients

Matthia Sabatelli, Venet Osmani, Oscar Mayora, Agnes Grünerbl, Paul Lukowicz

In: Proceedings of the 4th International Conference on Wireless Mobile Communication and Healthcare (Mobihealth), 2014 EAI. International Conference on Wireless Mobile Communication and Healthcare (MobiHealth-2014) November 3-5 Athens Greece IEEE - Xplore 2014.


Capabilities of smartphones can be utilised to monitor a range of aspects of users' behaviour. This has potential to affect a number of areas where users' behaviour is considered relevant information. Most notably, healthcare in general and mental health in particular are excellent candidates to utilise capabilities of smartphones, since mental disorders typically have a strong behaviour component. This is especially true for bipolar disorder, where mobility and activity of the patients is considered an indicator of a bipolar episode (depressive or manic). In this work we report on results of using capabilities of smartphones to monitor mobility of the patients, monitored over the period of 12 weeks. Through the continuous discovery of Wi-Fi access points we have inferred significant places (where the patient spent majority of the time) for each patient and investigate correlation of these places with patients' self-reported state. The results show that for majority of patients there exists negative correlation between time spent in clinic and their self-assessment score, while there is a positive correlation between self-assessment scores and time spent outside the home or clinic.

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence