pyActigraphy: Open-source python package for actigraphy data visualization and analysis

Hammad, G. H.; Reyt, Mathilde; Beliy, Nikita; Baillet, Marion; Deantoni, Michele; Lesoinne, Alexia; Muto, Vincenzo; Schmidt, Christina

doi:10.1371/journal.pcbi.1009514

Cited by 34 publications

(28 citation statements)

References 55 publications

(58 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the first set of features, we used the pyActigraphy library [ 53 ], a popular open-source Python package designed specifically for processing actigraphy data. The resulting features were computed using the package’s built-in BaseRaw model functions for the preprocessed magnitude of acceleration data generated from the triaxial data from which the gravitational acceleration bias was removed.…”

Section: Methodsmentioning

confidence: 99%

The Actigraphy-Based Identification of Premorbid Latent Liability of Schizophrenia and Bipolar Disorder

Nagy

Dombi

Fülep

et al. 2023

Sensors

View full text Add to dashboard Cite

(1) Background and Goal: Several studies have investigated the association of sleep, diurnal patterns, and circadian rhythms with the presence and with the risk states of mental illnesses such as schizophrenia and bipolar disorder. The goal of our study was to examine actigraphic measures to identify features that can be extracted from them so that a machine learning model can detect premorbid latent liabilities for schizotypy and bipolarity. (2) Methods: Our team developed a small wrist-worn measurement device that collects and identifies actigraphic data based on an accelerometer. The sensors were used by carefully selected healthy participants who were divided into three groups: Control Group (C), Cyclothymia Factor Group (CFG), and Positive Schizotypy Factor Group (PSF). From the data they collected, our team performed data cleaning operations and then used the extracted metrics to generate the feature combinations deemed most effective, along with three machine learning algorithms for categorization. (3) Results: By conducting the training, we were able to identify a set of mildly correlated traits and their order of importance based on the Shapley value that had the greatest impact on the detection of bipolarity and schizotypy according to the logistic regression, Light Gradient Boost, and Random Forest algorithms. (4) Conclusions: These results were successfully compared to the results of other researchers; we had a similar differentiation in features used by others, and successfully developed new ones that might be a good complement for further research. In the future, identifying these traits may help us identify people at risk from mental disorders early in a cost-effective, automated way.

show abstract

Section: Methodsmentioning

confidence: 99%

The Actigraphy-Based Identification of Premorbid Latent Liability of Schizophrenia and Bipolar Disorder

Nagy

Dombi

Fülep

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Participants wore an actigraph (Motionwatch 8; CamNtech) at the nondominant wrist and completed a sleep diary for at least 8 consecutive days, with a maximum duration of 15 days (13.58 ± 1.81 days). Locomotor activity data and light levels were aggregated into 30‐s epochs and processed by the open‐source software pyActigraphy (v1.0) 27 . Periods of actigraph removal were visually identified according to sleep diaries and excluded from the analysis.…”

Section: Methodsmentioning

confidence: 99%

“…Locomotor activity data and light levels were aggregated into 30s epochs and processed by the open-source software pyActigraphy (v1.0). 27 Periods of actigraph removal were F I G U R E 1 (A) Schematic illustration of the study timeline including daytime rest characterisation and rest-activity cycle estimation in the field as well as cognitive and circadian phase assessment. Circadian phase was extracted through a 40-h constant routine.…”

Section: Dtr Characteristics and 24-h Rest Probability Profiles: Acti...mentioning

confidence: 99%

Daytime rest: Association with 24‐h rest–activity cycles, circadian timing and cognition in older adults

Reyt

Deantoni

Baillet

et al. 2022

Journal of Pineal Research

Self Cite

View full text Add to dashboard Cite

Growing epidemiological evidence points toward an association between fragmented 24‐h rest–activity cycles and cognition in the aged. Alterations in the circadian timing system might at least partially account for these observations. Here, we tested whether daytime rest (DTR) is associated with changes in concomitant 24‐h rest probability profiles, circadian timing and neurobehavioural outcomes in healthy older adults. Sixty‐three individuals (59–82 years) underwent field actigraphy monitoring, in‐lab dim light melatonin onset assessment and an extensive cognitive test battery. Actimetry recordings were used to measure DTR frequency, duration and timing and to extract 24‐h rest probability profiles. As expected, increasing DTR frequency was associated not only with higher rest probabilities during the day, but also with lower rest probabilities during the night, suggesting more fragmented night‐time rest. Higher DTR frequency was also associated with lower episodic memory performance. Moreover, later DTR timing went along with an advanced circadian phase as well as with an altered phase angle of entrainment between the rest–activity cycle and circadian phase. Our results suggest that different DTR characteristics, as reflective indices of wake fragmentation, are not only underlined by functional consequences on cognition, but also by circadian alteration in the aged.

show abstract

“…The suite, called pyLight, is part of and extends the previously published pyActigraphy Python package (17), which implements routines for the loading, processing and analysis of actigraphy data. In this tutorial, we will demonstrate the use of the module, with a specific focus on importing data, manipulating data, and calculating metrics from the data.…”

Section: Introductionmentioning

confidence: 99%

Open-source Python module for the analysis of personalized light exposure data

Hammad¹,

Wulff²,

Skene³

et al. 2023

Preprint

View full text Add to dashboard Cite

Light exposure fundamentally influences human physiology and behavior, with light being the most important zeitgeber of the circadian system. Throughout the day, people are exposed to a variety of different scenes differing in light level, spectral composition and spatio-temporal properties. Personalized light exposure can be measured through wearable light loggers and dosimeters, including wrist-worn actimeters containing light sensors, yielding time courses of person-centric light exposure. There is a growing interest in relating light exposure patterns to health outcomes, requiring analytic techniques to summarize light exposure time courses. Building on the previously published pyActigraphy package, we introduce the package pyLight. pyLight allows users to extract light exposure data recordings from a wide range of devices, clean and filter the data, and compute common metrics for quantifying and summarising light exposure extracted from a literature survey. We demonstrate the use of the module in three examples: (1) loading, accessing and visually inspection a dataset, (2) truncation, masking, filtering and binarization of data set, (3) calculation of summary metrics, including time above threshold (TAT) and mean light timing above threshold (MLit). The pyLight package paves the way for the large-scale programmatic analysis of light-exposure data.

show abstract

pyActigraphy: Open-source python package for actigraphy data visualization and analysis

Cited by 34 publications

References 55 publications

The Actigraphy-Based Identification of Premorbid Latent Liability of Schizophrenia and Bipolar Disorder

The Actigraphy-Based Identification of Premorbid Latent Liability of Schizophrenia and Bipolar Disorder

Daytime rest: Association with 24‐h rest–activity cycles, circadian timing and cognition in older adults

Open-source Python module for the analysis of personalized light exposure data

Contact Info

Product

Resources

About