An evaluation of transport mode shift policies on transport-related physical activity through simulations based on random forests

Abstract

BackgroundPhysical inactivity is widely recognized as one of the leading causes of mortality, and transport accounts for a large part of people’s daily physical activity. This study develops a simulation approach to evaluate the impact of the Ile-de-France Urban Mobility Plan (2010–2020) on physical activity, under the hypothesis that the intended transport mode shifts are realized.MethodsBased on the Global Transport Survey (2010, n = 21,332) and on the RECORD GPS Study (2012–2013, n = 229) from the French capital region of Paris (Ile-de-France), a simulation method was designed and tested. The simulation method used accelerometer data and random forest models to predict the impact of the transport mode shifts anticipated in the Mobility Plan on transport-related moderate-to-vigorous physical activity (T-MVPA). The transport mode shifts include less private motorized trips in favor of more public transport, walking, and biking trips.ResultsThe simulation model indicated a mean predicted increase of 2 min per day of T-MVPA, in case the intended transport mode shifts in the Ile-de-France Urban Mobility Plan were realized. The positive effect of the transport mode shifts on T-MVPA would, however, be larger for people with a higher level of education. This heterogeneity in the positive effect would further increase the existing inequality in transport-related physical activity by educational level.ConclusionsThe method presented in this paper showed a significant increase in transport-related physical activity in case the intended mode shifts in the Ile-de-France Urban Mobility Plan were realized. This simulation method could be applied on other important health outcomes, such as exposure to noise or air pollution, making it a useful tool to anticipate the health impact of transport interventions or policies.Electronic supplementary materialThe online version of this article (doi: 10.1186/s12966-017-0600-1) contains supplementary material, which is available to authorized users.

Combining sensor tracking with a GPS-based mobility survey to better measure physical activity in trips: public transport generates walking

“…First, as illustrated in this paper, our reliance on a mobility survey in addition to the sensor-based data collection allowed us to provide accurate figures on the transport behavior and transport-related physical activity of participants that other methodologies such as the sole processing of sensor data by algorithms could not provide. Such accurate figures are needed for the correct information of policymakers and, as illustrated in previous articles [3, 9, 10], as input data for modeling the impact of various scenarios of interventions using simulation work. In this previous work, we modelled physical activity in trips in function of trip characteristics with random forests techniques in our small sensor-based sample, and then we applied this random forest algorithm to predict physical activity in each trip of participants from a large representative transport survey, and finally used this large transport survey sample to assess through simulations the impact of scenarios of shift in transport modes (public policies) on population physical activity [9, 10].…”

“…Finally, some studies automatically detected trips and travel modes with algorithms, but did not confirm the travel mode information with participants, so the resulting information might be unreliable and lack details on travel modes (e.g., two-wheel vs. four-wheel vehicle, or private vs. public transport vehicle). However, it is crucial to derive accurate data on the physical activity in trips with different travel modes, for example to provide policymakers with accurate quantitative evidence on the physical activity benefits of public transport use or as input data for subsequent modeling of the population-level impacts on physical activity of scenarios of mode shift and transport policies [3, 9, 10].…”

Identification of the potential prognostic genes of human melanoma

“…For example, Sarica, Cerasa, and Quattrone (2017) reported that using the random forest algorithm, they performed to classification for neuroimaging data about Alzheimer's disease. Brondeel, Kestens, and Chaix (2017) showed that based on random forests analysis, they evaluated the impact of transport mode shift policies on transport-related physical activity. Therefore, the differentially expressed genes we screened out were verified by the random forest analysis, which made our result more reliable and the accuracy of the top 20 genes was assured.…”

A scoping review of simulation modeling in built environment and physical activity research: Current status, gaps, and future directions for improving translation

“…Agent based models are a form of microsimulation, but generally involve more detail about how the individual 'agents' (e.g., people) interact with each other and their environment over time. 34 One other study 35 used random forest prediction models, a form of machine learning that uses random subsets of data features to build a predictive model of an outcome. 36 Of the 16 studies included, seven were real-world applications (models used mostly realworld data and answered questions that were applied to a specific population) 35,[37][38][39][40][41][42] and nine were proof-of-concept (models used mostly hypothetical populations and parameters to answer conceptual questions).…”