Automatic Annotation of Actigraphy Data for Sleep Disorders Diagnosis Purposes

Institute for Systems and Robotics / Instituto Superior Técnico, Czech Republic.
Conference proceedings: ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference 08/2010; 2010:5081-4. DOI: 10.1109/IEMBS.2010.5626207
Source: PubMed

ABSTRACT The diagnosis of Sleep disorders, highly prevalent in the western countries, typically involves sophisticated procedures and equipments that are intrusive to the patient. Wrist actigraphy, on the contrary, is a non-invasive and low cost solution to gather data which can provide valuable information in the diagnosis of these disorders. The acquired data may be used to infer the Sleep/Wakefulness (SW) state of the patient during the circadian cycle and detect abnormal behavioral patterns associated with these disorders. In this paper a classifier based on Autoregressive (AR) model coefficients, among other features, is proposed to estimate the SW state. The real data, acquired from 23 healthy subjects during fourteen days each, was segmented by expert medical personal with the help of complementary information such as light intensity and Sleep e-Diary information. Monte Carlo tests with a Leave-One-Out Cross Validation (LOOCV) strategy were used to assess the performance of the classifier which achieves an accuracy of 96%.

8 Reads
    • "Wrist actigraphy, on the contrary, is a noninvasive and low-cost solution to gather data that can provide valuable information in the diagnosis of these disorders, due to its ability to register behavioral data under normal life conditions (Cole et al., 1992; Jean-Louis et al., 2001; Paquet et al., 2007). The acquired data may be used to infer the sleep/wakefulness state of the patient during the circadian cycle and to detect abnormal behavioral patterns (Domingues et al., 2010). Along the circadian cycle, a different pattern of movements occurs during wakefulness and sleep (Lötjönen et al., 2003). "
    [Show abstract] [Hide abstract]
    ABSTRACT: The aim of this study was to evaluate the effect of advanced glaucoma on locomotor activity rhythms and related sleep parameters. Nine normal subjects and nine age-matched patients with bilateral advanced primary open-angle glaucoma, >10 yrs since diagnosis, were included in this observational, prospective, case-control study. Patients were required to record the timing and duration of their sleep and daily activities, and wore an actigraph on the wrist of the nondominant arm for 20 d. Activity rhythm period, MESOR (24-h time-series mean), amplitude (one-half peak-to-trough variation), and acrophase (peak time), plus long sleep episodes during the wake state, sleep duration, efficiency, and latency, as well as mean activity score, wake minutes, and mean wake episodes during the sleep interval were assessed in controls and glaucomatous patients. Glaucomatous patients exhibited significant decrease in nighttime sleep efficiency, and significant increase in the mean activity score, wake minutes, and mean wake episode during the night. These results suggest that alterations of circadian physiology could be a risk to the quality of life of patients with glaucoma.
    Chronobiology International 08/2012; 29(7):911-9. DOI:10.3109/07420528.2012.691146 · 3.34 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Actigraphy is an useful tool for evaluating the activity pattern of a subject; activity registries are usually processed by first splitting the signal into its wakefulness and rest intervals and then analyzing each one in isolation. Consequently, a preprocessing stage for such a splitting is needed. Several methods have been reported to this end but they rely on parameters and thresholds which are manually set based on previous knowledge of the signals or learned from training. This compromises the general applicability of this methods. In this paper we propose a new method in which thresholds are automatically set based solely on the specific registry to be analyzed. The method consists of two stages: (1) estimation of an initial classification mask by means of the expectation maximization algorithm and (2) estimation of a final refined mask through an iterative method which re-estimates both the mask and the classifier parameters at each iteration step. Results on real data show that our methodology outperforms those so far proposed and can be more effectively used to obtain derived sleep quality parameters from actigraphy registries.
    Medical Engineering & Physics 09/2014; 36(12). DOI:10.1016/j.medengphy.2014.08.013 · 1.83 Impact Factor