AUTHOR=Lin Wenyi , Karahanoglu F. Isik , Demanuele Charmaine , Khan Sheraz , Cai Xuemei , Santamaria Mar , Di Junrui , Adamowicz Lukas 

TITLE=SciKit digital health package for accelerometry-measured physical activity: comparisons to existing solutions and investigations of age effects in healthy adults

JOURNAL=Frontiers in Digital Health

VOLUME=5

YEAR=2023

URL=https://www.frontiersin.org/journals/digital-health/articles/10.3389/fdgth.2023.1321086

DOI=10.3389/fdgth.2023.1321086

ISSN=2673-253X

ABSTRACT=<sec><title>Introduction</title><p>Accelerometry has become increasingly prevalent to monitor physical activity due to its low participant burden, quantitative metrics, and ease of deployment. Physical activity metrics are ideal for extracting intuitive, continuous measures of participants’ health from multiple days or weeks of high frequency data due to their fairly straightforward computation. Previously, we released an open-source digital health python processing package, SciKit Digital Health (SKDH), with the goal of providing a unifying device-agnostic framework for multiple digital health algorithms, such as activity, gait, and sleep.</p></sec><sec><title>Methods</title><p>In this paper, we present the open-source SKDH implementation for the derivation of activity endpoints from accelerometer data. In this implementation, we include some non-typical features that have shown promise in providing additional context to activity patterns, and provide comparisons to existing algorithms, namely GGIR and the GENEActiv macros. Following this reference comparison, we investigate the association between age and derived physical activity metrics in a healthy adult cohort collected in the Pfizer Innovation Research Lab, comprising 7–14 days of at-home data collected from younger (18–40 years) and older (65–85 years) healthy volunteers.</p></sec><sec><title>Results</title><p>Results showed that activity metrics derived with SKDH had moderate to excellent ICC values (<inline-formula><mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" id="IM1"><mml:mn>0.550</mml:mn></mml:math></inline-formula> to <inline-formula><mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" id="IM2"><mml:mn>1.0</mml:mn></mml:math></inline-formula> compared to GGIR, <inline-formula><mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" id="IM3"><mml:mn>0.469</mml:mn></mml:math></inline-formula> to <inline-formula><mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" id="IM4"><mml:mn>0.697</mml:mn></mml:math></inline-formula> compared to the GENEActiv macros), with high correlations for almost all compared metrics (&gt;0.733 except vs GGIR sedentary time, <inline-formula><mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" id="IM5"><mml:mn>0.547</mml:mn></mml:math></inline-formula>). Several features show age-group differences, with Cohen’s <inline-formula><mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" id="IM6"><mml:mi>d</mml:mi></mml:math></inline-formula> effect sizes &gt;1.0 and <inline-formula><mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" id="IM7"><mml:mi>p</mml:mi><mml:mtext>-values</mml:mtext></mml:math></inline-formula> &lt; 0.001. These features included non-threshold methods such as intensity gradient, and activity fragmentation features such as between-states transition probabilities.</p></sec><sec><title>Discussion</title><p>These results demonstrate the validity of the implemented SKDH physical activity algorithm, and the potential of the implemented PA metrics in assessing activity changes in free-living conditions.</p></sec>