Examinando por Autor "Montane, Joel"

Mostrando 1 - 2 de 2
  • Miniatura
    Ítem
    Analysis of training behavior in users of a fitness app: cross-sectional study
    (2026-01-08) Fuente Vidal, Andrea ; Prat, Roger; Arribas Marín, Juan Manuel; Bastidas-Jossa, Óscar ; Guerra-Balic, Myriam ; García-Zapirain, Begoña; Montane, Joel ; Jerez-Roig, Javier
    BACKGROUND: Mobile health (mHealth) apps are increasingly being used to promote physical activity (PA) and can support exercise uptake and maintenance. Despite their potential, these tools face high dropout rates and inconsistent adherence, posing a significant challenge. Understanding how users engage with fitness apps is essential for improving user experience and health outcomes. OBJECTIVE: This study aims to analyze user behavior patterns in the Mammoth Hunters (MH) fitness app (Mammoth Hunters SL), focusing on retention (days from registration to user's last recorded training session), average weekly training frequency, and adherence (alignment between planned and actual training). We examined how these outcomes are influenced by sociodemographic, motivational, and other variables. METHODS: This cross-sectional study involved 2771 Mammoth Hunters app users. In a subsample (n=289), training data were complemented by motivational data acquired through online surveying via an ad-hoc scale (internal consistency >0.83) based on the self-determination theory (SDT). Descriptive statistics and nonparametric tests (Kruskal-Wallis, Dunn post-hoc, and Spearman correlation) were used to assess correlation between sociodemographic, motivation, and training behavior variables. RESULTS: Mean retention (days) was significantly higher among males than females (135 vs 109, respectively; P<.01), users in the subscription vs free plan (154 vs 81; P<.001), active or very active individuals vs inactive, midbuilt vs thin body types (132 vs 120; P=.001), and those with slightly lower BMI. Users pursuing antiaging or muscle gain goals showed longer retention than those aiming to lose weight (gain: 132, antiaging: 128, lose weight: 116; P<.001). Average weekly frequency (sessions per week) of training was statistically significantly different by sex (male: 1.9 vs female: 1.8; P=.04), body type (thin: 1.96 vs mid: 1.77; P=.04), activity level (very active: 2.05 vs inactive: 1.83; P=.04), and motivation type (extrinsic introjected motivation correlated positively: r=0.17; P<.05), but did not correlate with perceived difficulty or fitness goals. Adherence, defined as actual vs targeted training frequency, was only significantly different among body types, with thin users showing higher adherence than the midbuilt group (57% vs 52.1%; P=.02). Intrinsic motivation showed a positive correlation with retention (r=0.19; P=.002), as did identified motivation (r=0.12; P<.05). CONCLUSIONS: This study shows that retention is influenced by demographic factors, with males, subscribers, previously active, midbuilds, those aiming to gain muscle, and individuals with autonomous types (ie, intrinsic and identified) of motivation displaying greater long-term participation. These findings provide valuable preliminary insight into the complexities of exercise training behavior in apps. They suggest that training frequency, retention, and adherence do not respond to the same factors. App developers, researchers, and trainers should assess these variables separately and develop strategies accordingly.
  • Miniatura
    Ítem
    Predicting physical exercise adherence in fitness apps using a deep learning approach
    (MDPI, 2021-10-14) Bastidas-Jossa, Óscar; Zahia, Sofia; Fuente Vidal, Andrea; Sánchez Férez, Néstor; Roda Noguera, Oriol; Montane, Joel; García-Zapirain, Begoña
    The use of mobile fitness apps has been on the rise for the last decade and especially during the worldwide SARS-CoV-2 pandemic, which led to the closure of gyms and to reduced outdoor mobility. Fitness apps constitute a promising means for promoting more active lifestyles, although their attrition rates are remarkable and adherence to their training plans remains a challenge for developers. The aim of this project was to design an automatic classification of users into adherent and non-adherent, based on their training behavior in the first three months of app usage, for which purpose we proposed an ensemble of regression models to predict their behaviour (adherence) in the fourth month. The study was conducted using data from a total of 246 Mammoth Hunters Fitness app users. Firstly, pre-processing and clustering steps were taken in order to prepare the data and to categorize users into similar groups, taking into account the first 90 days of workout sessions. Then, an ensemble approach for regression models was used to predict user training behaviour during the fourth month, which were trained with users belonging to the same cluster. This was used to reach a conclusion regarding their adherence status, via an approach that combined affinity propagation (AP) clustering algorithm, followed by the long short-term memory (LSTM), rendering the best results (87% accuracy and 85% F1_score). This study illustrates the suggested the capacity of the system to anticipate future adherence or non-adherence, potentially opening the door to fitness app creators to pursue advanced measures aimed at reducing app attrition.