Circadian Rhythm Analysis Using Wearable Device Data: A Novel Penalized Machine Learning Approach

Li, Xinyue; Kane, Michael J.; Zhang, Yunting; Sun, Wanning; Song, Yuxuan; Dong, Shumei; Lin, Qingmin; Zhu, Qi; Jiang, Fan; Zhao, Hongyu

doi:10.1101/2020.02.20.957076

Cited by 3 publications

(3 citation statements)

References 34 publications

(40 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By decreasing λ, we identified dominant periodicities sequentially and characterized the daily sleep-activity rhythm at each age. An R package named PML was developed [ 26 ] for the implementation of the PML algorithm [ 27 ].…”

Section: Methodsmentioning

confidence: 99%

Circadian Rhythm Analysis Using Wearable Device Data: Novel Penalized Machine Learning Approach

Li¹,

Kane²,

Zhang³

et al. 2021

J Med Internet Res

Self Cite

View full text Add to dashboard Cite

Background Wearable devices have been widely used in clinical studies to study daily activity patterns, but the analysis remains a major obstacle for researchers. Objective This study proposes a novel method to characterize sleep-activity rhythms using actigraphy and further use it to describe early childhood daily rhythm formation and examine its association with physical development. Methods We developed a machine learning–based Penalized Multiband Learning (PML) algorithm to sequentially infer dominant periodicities based on the Fast Fourier Transform (FFT) algorithm and further characterize daily rhythms. We implemented and applied the algorithm to Actiwatch data collected from a cohort of 262 healthy infants at ages 6, 12, 18, and 24 months, with 159, 101, 111, and 141 participants at each time point, respectively. Autocorrelation analysis and Fisher test in harmonic analysis with Bonferroni correction were applied for comparison with the PML. The association between activity rhythm features and early childhood motor development, assessed using the Peabody Developmental Motor Scales-Second Edition (PDMS-2), was studied through linear regression analysis. Results The PML results showed that 1-day periodicity was most dominant at 6 and 12 months, whereas one-day, one-third–day, and half-day periodicities were most dominant at 18 and 24 months. These periodicities were all significant in the Fisher test, with one-fourth–day periodicity also significant at 12 months. Autocorrelation effectively detected 1-day periodicity but not the other periodicities. At 6 months, PDMS-2 was associated with the assessment seasons. At 12 months, PDMS-2 was associated with the assessment seasons and FFT signals at one-third–day periodicity (P<.001) and half-day periodicity (P=.04), respectively. In particular, the subcategories of stationary, locomotion, and gross motor were associated with the FFT signals at one-third–day periodicity (P<.001). Conclusions The proposed PML algorithm can effectively conduct circadian rhythm analysis using time-series wearable device data. The application of the method effectively characterized sleep-wake rhythm development and identified the association between daily rhythm formation and motor development during early childhood.

show abstract

Section: Methodsmentioning

confidence: 99%

Circadian Rhythm Analysis Using Wearable Device Data: Novel Penalized Machine Learning Approach

Li¹,

Kane²,

Zhang³

et al. 2021

J Med Internet Res

Self Cite

View full text Add to dashboard Cite

show abstract

“…By decreasing λ , we identify dominant periodicities sequentially to characterize the daily sleep-activity rhythm. An R package named PML has been developed ( https://CRAN.R-project.org/package=PML ) for the implementation of the PML algorithm [ 93 ].…”

Section: Methodsmentioning

confidence: 99%

Automated feature extraction from population wearable device data identified novel loci associated with sleep and circadian rhythms

Zhao

2020

PLoS Genet

Self Cite

View full text Add to dashboard Cite

Wearable devices have been increasingly used in research to provide continuous physical activity monitoring, but how to effectively extract features remains challenging for researchers. To analyze the generated actigraphy data in large-scale population studies, we developed computationally efficient methods to derive sleep and activity features through a Hidden Markov Model-based sleep/wake identification algorithm, and circadian rhythm features through a Penalized Multi-band Learning approach adapted from machine learning. Unsupervised feature extraction is useful when labeled data are unavailable, especially in large-scale population studies. We applied these two methods to the UK Biobank wearable device data and used the derived sleep and circadian features as phenotypes in genome-wide association studies. We identified 53 genetic loci with p<5×10 −8 including genes known to be associated with sleep disorders and circadian rhythms as well as novel loci associated with Body Mass Index, mental diseases and neurological disorders, which suggest shared genetic factors of sleep and circadian rhythms with physical and mental health. Further cross-tissue enrichment analysis highlights the important role of the central nervous system and the shared genetic architecture with metabolism-related traits and the metabolic system. Our study demonstrates the effectiveness of our unsupervised methods for wearable device data when additional training data cannot be easily acquired, and our study further expands the application of wearable devices in population studies and genetic studies to provide novel biological insights.

show abstract

“…All analyses were performed using R software (R Core Development Team, 2019), with fast Fourier transformation and harmonic analysis test in the package PML (Li & Kane, 2019). Data were presented as mean ± standard deviation, and p values < 0.05 were considered statistically significant.…”

Section: Methodsmentioning

confidence: 99%

Lack of daily heart rate rhythms in Adélie penguin chicks during the polar day

Xia

Zhang

2019

Polar Record

View full text Add to dashboard Cite

AbstractDaily rhythms enable organisms to adapt to daily fluctuations in environmental factors. Do organisms still exhibit 24-h rhythms when living in habitats without obvious daily cycles in external signals? To answer this question, we measured the heart rates of six Adélie penguin (Pygoscelis adeliae) chicks on Inexpressible Island during the polar day between 15 and 21 January 2019. Averaged heart rates were between 186 and 233 beats/min for individual chicks. Both fast Fourier transformation and autocorrelation were employed to assess the daily rhythmicity. Based on fast Fourier transformation, a significant contribution of daily rhythm in heart rate variation was found only in one individual. Small effect size of significant autocorrelation coefficients was found in two individuals, while there was no significant autocorrelation coefficient for 24-h time lag in four other individuals. In summary, no prevailing daily rhythm of heart rate was found in these Adélie penguin chicks. We propose that the lack of daily rhythm in Adélie penguin chicks could be an adaptation to the local environment in the polar regions, but that the adaptive value thereof remains to be investigated.

show abstract

Circadian Rhythm Analysis Using Wearable Device Data: A Novel Penalized Machine Learning Approach

Cited by 3 publications

References 34 publications

Circadian Rhythm Analysis Using Wearable Device Data: Novel Penalized Machine Learning Approach

Circadian Rhythm Analysis Using Wearable Device Data: Novel Penalized Machine Learning Approach

Automated feature extraction from population wearable device data identified novel loci associated with sleep and circadian rhythms

Lack of daily heart rate rhythms in Adélie penguin chicks during the polar day

Contact Info

Product

Resources

About