Actigraphy Pattern Analysis for Outpatient Monitoring
The actigraphy is a cost-effective method for assessing specific sleep disorders such as diagnosing insomnia, circadian rhythm disorders, or excessive sleepiness. Due to recent advances in wireless connectivity and motion activity sensors, the new actigraphy devices allow the non-intrusive and non-stigmatizing monitoring of outpatients for weeks or even months facilitating treatment outcome measure in daily life activities. This possibility has propitiated new studies suggesting the utility of actigraphy to monitor outpatients with mood disorders such as major depression, or patients with dementia. However, the full exploitation of data acquired during the monitoring period requires the use of automatic systems and techniques that allow the reduction of inherent complexity of the data, the extraction of most informative features, and the interpretability and decision-making. In this study we purpose a set of techniques for actigraphy patterns analysis for outpatient monitoring. These techniques include actigraphy signal pre-processing, quantification, nonlinear registration, feature extraction, detection of anomalies, and pattern visualization. In addition, techniques for daily actigraphy signals modelling and simulation are included to facilitate the development and test of new analysis techniques in controlled scenarios.
Key wordsActigraphy Outpatient monitoring Functional data analysis Feature extraction Kernel density estimation Simulation
This work was partially funded by the European Commission: Help4Mood (contract no. FP7-ICT-2009-4: 248765). E. Fuster Garcia acknowledges to Programa Torres Quevedo from Ministerio de Educación y Ciencia, co-founded by the European Social Fund (PTQ-12-05693).
- 13.Help4mood project website. http://help4mood.info
- 14.Optimi project website. http://www.optimiproject.eu
- 15.Texas Instrumetns (TI) Chronos watch information [Online] Available: http://processors.wiki.ti.com/index.php/EZ430-Chronos
- 16.Mahdavi H et al. (2012) A wireless under-mattress sensor system for sleep monitoring in people with major depression. A: IASTED International Conference Biomedical Engineering (BioMed). Proceedings of the ninth IASTED International Conference Biomedical Engineering (BioMed 2012). Innsbruck, 2012. p 1–5Google Scholar
- 17.Fuster-Garcia E et al. (2014) Fusing actigraphy signals for outpatient monitoring. Informat Fusion (in press). http://www.sciencedirect.com/science/article/pii/S156625351400089X
- 22.Ramsay JO, Silverman BW (2005) Functional data analysis, Springer series in statistics. Springer, New YorkGoogle Scholar
- 23.Software available at http://www.psych.mcgill.ca/misc/fda/
- 26.Jolliffe IT (2002) Principal component analysis. Springer, New YorkGoogle Scholar
- 27.Lee DD, Seung HS (2000) Algorithms for non-negative matrix factorization. In: NIPS. MIT Press, Cambridge, pp 556–562Google Scholar
- 30.Fuster-Garcia E, Juan-Albarracin J, Breso A, Garcia-Gomez JM (2013) Monitoring changes in daily actigraphy patterns of free-living patients. International work-conference on bioinformatics and biomedical engineering (IWBBIO) proceedings, pp 685–693Google Scholar