Development and testing of methods for detecting off-wrist in actimetry recordings

• Published in: Sleep (New York, N.Y.) Vol. 45; no. 8; p. 1
• Main Authors: Pilz, Luísa K, de Oliveira, Melissa A B, Steibel, Eduardo G, Policarpo, Lucas M, Carissimi, Alicia, Carvalho, Felipe G, Constantino, Débora B, Tonon, André Comiran, Xavier, Nicóli B, da Rosa Righi, Rodrigo, Hidalgo, Maria Paz
• Format: Journal Article
• Language: English
• Published: US Oxford University Press 11.08.2022
• Subjects: Accelerometers; Algorithms; Analysis; Automation; Bias; Datasets; Humans; Machine learning; Methods; Monitoring, Ambulatory; Self Report; Sensors; Sleep; Wrist; Brazil; temperature; nonwear; accelerometers; time series; actigraphy; rest/activity

Abstract Study Objectives In field studies using wrist-actimetry, not identifying/handling off-wrist intervals may result in their misclassification as immobility/sleep and biased estimations of rhythmic patterns. By comparing different solutions for detecting off-wrist, our goal was to ascertain ho...