Identification of physical activity and sedentary behaviour dimensions that predict mortality risk in older adults: Development of a machine learning model in the Whitehall II accelerometer sub-study and external validation in the CoLaus study

Mathilde Chen; Benjamin Landré; Pedro Marques-Vidal; Vincent T van Hees; April C E van Gennip; Mikaela Bloomberg; Manasa S Yerramalla; Mohamed Amine Benadjaoud; Séverine Sabia

doi:10.1016/j.eclinm.2022.101773

Identification of physical activity and sedentary behaviour dimensions that predict mortality risk in older adults: Development of a machine learning model in the Whitehall II accelerometer sub-study and external validation in the CoLaus study

EClinicalMedicine. 2022 Dec 13:55:101773. doi: 10.1016/j.eclinm.2022.101773. eCollection 2023 Jan.

Authors

Affiliations

¹ Université Paris Cité, Inserm U1153, CRESS, Epidemiology of Ageing and Neurodegenerative Diseases, 10 Avenue de Verdun, 75010, Paris, France.
² Department of Medicine, Internal Medicine, Lausanne University Hospital and University of Lausanne, Switzerland.
³ Accelting, Almere, the Netherlands.
⁴ Department of Internal Medicine, Maastricht University Medical Centre, the Netherlands.
⁵ School for Cardiovascular Diseases CARIM, Maastricht University, the Netherlands.
⁶ Department of Epidemiology and Public Health, University College London, UK.
⁷ Institute for Radiological Protection and Nuclear Safety (IRSN), Fontenay-Aux-Roses, France.

Abstract

Background: Identification of new physical activity (PA) and sedentary behaviour (SB) features relevant for health at older age is important to diversify PA targets in guidelines, as older adults rarely adhere to current recommendations focusing on total duration. We aimed to identify accelerometer-derived dimensions of movement behaviours that predict mortality risk in older populations.

Methods: We used data on 21 accelerometer-derived features of daily movement behaviours in 3991 participants of the UK-based Whitehall II accelerometer sub-study (25.8% women, 60-83 years, follow-up: 2012-2013 to 2021, mean = 8.3 years). A machine-learning procedure was used to identify core PA and SB features predicting mortality risk and derive a composite score. We estimated the added predictive value of the score compared to traditional sociodemographic, behavioural, and health-related risk factors. External validation in the Switzerland-based CoLaus study (N = 1329, 56.7% women, 60-86 years, follow-up: 2014-2017 to 2021, mean = 3.8 years) was conducted.

Findings: In total, 11 features related to overall activity level, intensity distribution, bouts duration, frequency, and total duration of PA and SB, were identified as predictors of mortality in older adults and included in a composite score. Both in the derivation and validation cohorts, the score was associated with mortality (hazard ratio = 1.10 (95% confidence interval = 1.05-1.15) and 1.18 (1.10-1.26), respectively) and improved the predictive value of a model including traditional risk factors (increase in C-index = 0.007 (0.002-0.014) and 0.029 (0.002-0.055), respectively).

Interpretation: The identified accelerometer-derived PA and SB features, beyond the currently recommended total duration, might be useful for screening of older adults at higher mortality risk and for diversifying PA and SB targets in older populations whose adherence to current guidelines is low.

Funding: National Institute on Aging; UK Medical Research Council; British Heart Foundation; Wellcome Trust; French National Research Agency; GlaxoSmithKline; Lausanne Faculty of Biology and Medicine; Swiss National Science Foundation.

Keywords: Accelerometer; Mortality; Older adults; Physical activity; Prediction.

Abstract

Grants and funding