Related Experiment Video
Updated: Jun 7, 2025
Multi-Modal Home Sleep Monitoring in Older Adults
Published on: January 26, 2019
Evaluating the performance of open-source and proprietary processing of actigraphy sleep estimation in children with
Aliye B Cepni1, Sarah Burkart2, Xuanxuan Zhu2
1Health and Human Performance Department, University of Houston, Houston, TX, USA.
Insights
This study compared actigraphy sleep algorithms in children, finding proprietary software slightly outperformed open-source options. However, the open-source vanHees2015 algorithm is suitable for pediatric clinical use, though different software implementations yield varied sleep estimates.
Area of Science:
- Pediatric Sleep Medicine
- Biomedical Engineering
- Wearable Technology
Background:
- Actigraphy is a non-invasive method for sleep assessment.
- Accurate sleep staging in children is crucial for diagnosing sleep disorders.
- Comparing open-source and proprietary algorithms is essential for clinical validation.
Purpose of the Study:
- To evaluate the performance of open-source and proprietary actigraphy sleep algorithms against polysomnography in children.
- To assess the agreement and equivalence of different algorithms in estimating sleep parameters.
- To determine the suitability of open-source algorithms for pediatric sleep studies.
Main Methods:
- 110 children (5-12 years) with suspected sleep disorders underwent overnight polysomnography with wrist-worn ActiGraph GT9X.
- Actigraphy data were analyzed using open-source GGIR and proprietary ActiLife software.
- Discrepancy, epoch-by-epoch analyses, and equivalence testing were performed.
Main Results:
- The open-source vanHees2015 algorithm demonstrated good accuracy (79.5%) but was slightly outperformed by proprietary ActiLife algorithms.
- Proprietary ActiLife algorithms (Cole-Kripke, Sadeh) showed higher sensitivity for sleep detection.
- Sleep estimates (TST, SE) were statistically equivalent between some implementations (Cole-Kripke ActiLife vs. vanHees2015), but not others (Sadeh/Cole-Kripke ActiLife vs. GGIR).
Conclusions:
- Proprietary actigraphy algorithms slightly outperformed the open-source vanHees2015 algorithm in children.
- The open-source vanHees2015 algorithm is a viable option for pediatric clinical settings.
- Discrepancies in sleep estimates necessitate caution when comparing studies using different software implementations (ActiLife vs. GGIR).
Study Objectives:
Evaluate the performance of actigraphy-based open-source and proprietary sleep algorithms compared to polysomnography in children with suspected sleep disorders.
Methods:
In a sleep clinic, 110 children (5-12 years, 54% female, 50% black, 82% with sleep disorders) wore wrist-placed ActiGraph GT9X during overnight polysomnography. Actigraphy data were scored as sleep or wake using open-source GGIR and proprietary ActiLife software. Discrepancy and epoch-by-epoch analyses were conducted to assess agreement between algorithms and polysomnography, along with equivalence testing.
Results:
The open-source vanHees2015 algorithm showed good accuracy (79.5% ± 12.0%), sensitivity (81.1% ± 13.5%), and specificity (66.0% ± 23.8%) for sleep detection but was outperformed by the proprietary ActiLife algorithms. The magnitude and trend of bias for total sleep time (TST), sleep efficiency (SE), sleep onset latency, and wake after sleep onset were similar between algorithms. TST and SE were statistically equivalent for the Cole-Kripke (Actilife) and vanHees2015 algorithms compared to the Sadeh (Actilife) algorithm. The Cole-Kripke (ActiLife) demonstrated higher sensitivity (90.5%) to detect sleep but lower specificity (61.2%) than Cole-Kripke (GGIR) (sensitivity: 62.7%, specificity: 79.9%). Sadeh and Cole-Kripke estimated sleep outcomes were not statistically equivalent between implementations in ActiLife and GGIR.
Conclusions:
The open-source vanHees2015 algorithm performed well but slightly worse than the proprietary ActiLife algorithms in children. The open-source nature vanHees2015 makes it ideal for clinical pediatric use. Implementation of the Sadeh and Cole-Kripke algorithms in the proprietary ActiLife and open-source GGIR software yield different sleep estimates, so comparisons between studies using these different implementations should be avoided.
