Automatic annotation of actigraphy data for sleep disorders diagnosis purposes.
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%.
- [Show abstract] [Hide abstract]
ABSTRACT: Two validation studies were conducted to optimize the sleep-detection algorithm of the Actillume. The first study used home recordings of postmenopausal women (age range: 51 to 77 years), which were analyzed to derive the optimal algorithm for detecting sleep and wakefulness from wrist activity data, both for nocturnal in-bed recordings and considering the entire 24 h. The second study explored the optimal algorithm to score in-bed recordings of healthy young adults (age range: 19 to 34 years) monitored in the laboratory. In Study I, the algorithm for in-bed recordings (n=39) showed a minute-by-minute agreement of 85% between Actillume and polysomnography (PSG), a correlation of.98, and a mean measurement error (ME) of 21 min for estimates of sleep duration. Using the same algorithm to score 24-h recordings with Webster's rules, an agreement of 89%, a correlation of.90, and 1 min ME were observed. A different algorithm proved optimal to score in-bed recordings (n=31) of young adults, yielding an agreement of 91%, a correlation of.92, and an ME of 5 min. The strong correlations and agreements between sleep estimates from Actillume and PSG in both studies suggest that the Actillume can reliably monitor sleep and wakefulness both in community-residing elderly and healthy young adults in the laboratory. However, different algorithms are optimal for individuals with different characteristics.Physiology & Behavior 02/2001; 72(1-2):21-8. · 3.16 Impact Factor
Conference Paper: Sleep/Wakefulness State from Actigraphy.[Show abstract] [Hide abstract]
ABSTRACT: In this paper a definition of the activity (ACT) variable is proposed and a method to estimate it from the noisy actigraph output sensor data is described. A statistical model for the actigraph data generation process is suggested based on its working physical principles and on physiological considerations about human activity. The purposeless nature of the sleeping movements is used to discriminate the Sleep and Wakefulness (SW) states. The estimated ACT signal from the actigraph output signal is correlated with the data from a Sleep Diary to validate the SW oscillations, computed from the ACT. A Sleep electronic Diary (SeD) was implemented in the scope of this work to make it possible an accurate register of the patient activities relevant for the diagnosis of sleep disorders. Examples using real data, illustrating the application of the method, have shown high correlation between the output of the proposed algorithm that characterizes the activity and the data registered in the SeD.Pattern Recognition and Image Analysis, 4th Iberian Conference, IbPRIA 2009, Póvoa de Varzim, Portugal, June 10-12, 2009, Proceedings; 01/2009
- [Show abstract] [Hide abstract]
ABSTRACT: The purpose of this work was to describe the basic statistical properties of the process of production of movements measured with a wrist actimeter, along a complete sleep period in normal human subjects. Two distinct types of random magnitudes were considered to analyze the data, the times between successive groups of movements and the number of movements at each fixed time (1 min) measurement epoch. Suitable probabilistic models for the two variates were chosen, fitting theoretical distribution functions to the observed data. It is concluded that interval data fit a one-parameter exponential distribution, while the number of movements fit a two-parameter negative binomial distribution. The estimated values of these parameters, besides being necessary to perform further statistical analysis, are a measure of the intensity and frequency of the movements. Finally the relationship between polysomnography measures and the elicited parameters was studied.Neuropsychobiology 02/1998; 38(2):108-12. · 2.37 Impact Factor