Algorithms for sleep–wake identification using actigraphy: a comparative study and new results

Authors


  • At the time of this study Dr Sanjeev V. Kothare was with the Section of Sleep Medicine, Division of Neurology, Department of Pediatrics, St Christopher’s Hospital for Children, Drexel University College of Medicine, Philadelphia, PA, USA.

Dr Sanjeev V. Kothare, Sleep Center for Children, Children’s Hospital, and Department of Neurology, Harvard Medical School, Fegan 9, 300 Longwood Avenue, Boston, MA 02115, USA. Tel.: (617) 355 6663; fax: (617) 730 0463; e-mail: sanjeev.kothare@childrens.harvard.edu

Summary

The aim of this study was to investigate two new scoring algorithms employing artificial neural networks and decision trees for distinguishing sleep and wake states in infants using actigraphy and to validate and compare the performance of the proposed algorithms with known actigraphy scoring algorithms. The study employed previously recorded longitudinal physiological infant data set from the Collaborative Home Infant Monitoring Evaluation (CHIME) study conducted between 1994 and 1998 [http://dccwww.bumc.bu.edu/ChimeNisp/Main_Chime.asp; Sleep26 (1997) 553] at five clinical sites around the USA. The original CHIME data set contains recordings of 1079 infants <1 year old. In our study, we used the overnight polysomnography scored data and ankle actimeter (Alice 3) raw data for 354 infants from this data set. The participants were heterogeneous and grouped into four categories: healthy term, preterm, siblings of SIDS and infants with apparent life-threatening events (apnea of infancy). The selection of the most discriminant actigraphy features was carried out using Fisher’s discriminant analysis. Approximately 80% of all the epochs were used to train the artificial neural network and decision tree models. The models were then validated on the remaining 20% of the epochs. The use of artificial neural networks and decision trees was able to capture potentially nonlinear classification characteristics, when compared to the previously reported linear combination methods and hence showed improved performance. The quality of sleep–wake scoring was further improved by including more wake epochs in the training phase and by employing rescoring rules to remove artifacts. The large size of the database (approximately 337 000 epochs for 354 patients) provided a solid basis for determining the efficacy of actigraphy in sleep scoring. The study also suggested that artificial neural networks and decision trees could be much more routinely utilized in the context of clinical sleep search.

Ancillary