Machine Learning for the Analysis of Healthy Lifestyle Data: Scoping Review and Guidelines

This review highlights methodological gaps in the application of supervised ML to healthy lifestyle data. The ML workflow should span from data acquisition to explainability, using iterative steps to improve methodological rigor. Although multidomain data collection enhances the understanding of health issues related to lifestyle, representativeness remains limited due to methodological shortcomings in data acquisition. While random forest was the most commonly used algorithm, a multimodel approach is recommended for a comprehensive comparison. Lifestyle components consistently ranked among the top features in studies integrating XAI. Incorporating XAI methods into the ML pipeline can support personalized interventions, provided data collection is accurate. The R metapackage (tidymodels; Max Kuhn and Hadley Wickham) facilitates process evaluation through unified syntax, improving replicability. Methodological and reporting guidelines and a checklist are provided to enhance transparency and replicability in multidisciplinary ML research.