Real-time detection of eating behavior and meal consumption by commercial wrist-worn wearable devices: protocol for a systematic review and meta-analysis

Accurate measurement of dietary consumption and eating behavior is essential to understand nutrition health relationships. Traditional dietary assessment approaches (e.g., food diaries, 24-h recalls, food frequency questionnaires) are subject to recall error, social desirability bias, and participant burden, which can compromise data quality. Commercial wrist-worn wearable devices, including smartwatches and smartbands, represent a promising platform for unobtrusive, real-time monitoring of eating behavior, leveraging embedded sensors to detect hand-to-mouth movements and related intake gestures. However, evidence synthesis specifically focused on wrist-worn commercial wearable devices as standalone tools for real-time detection remains limited. The primary objective is to assess the diagnostic accuracy of commercial wrist-worn wearable devices for the real-time detection of eating behavior and meal consumption in adults. Secondary objectives address device and sensor characteristics, algorithmic approaches, feasibility, and qualitative dimensions of meal consumption. The systematic review will be conducted in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 statement as the general methodological framework. Given that the primary outcome concerns the diagnostic accuracy of commercial wrist-worn wearable devices in detecting eating behavior and meal consumption, the review will additionally follow the Preferred Reporting Items for Systematic Reviews and Meta-Analyses of Diagnostic Test Accuracy Studies (PRISMA-DTA) extension. This protocol is reported according to the Preferred Reporting Items for Systematic Review and Meta-analysis Protocols (PRISMA-P) 2015 statement. The protocol is registered in the Open Science Framework (OSF) registries (registration DOI https://doi.org/10.17605/OSF.IO/NP3GU ) and will be updated in case of amendments. This protocol will guide the first systematic synthesis of diagnostic accuracy, analytical performance, and feasibility of commercial wrist-worn wearable devices for real-time detection of eating behavior and meal consumption. Findings will inform the readiness of commercial wrist-worn wearable device-based approaches for translational use in clinical nutrition, behavioral interventions, and public health monitoring. Open Science Framework (OSF): https://doi.org/10.17605/OSF.IO/NP3GU