Abstract
The incidence of Alzheimer's disease (AD) continues to rise, and predictive models combining artificial intelligence (AI) with wearable devices offer a new approach for its detection and diagnosis. Existing reviews remain focused on traditional biomarkers, making it necessary to supplement the evidence in this field, particularly given the rapid advancements in wearable and AI technologies. The scoping review protocol aims to systematically evaluate AI-based predictive models using wearable devices for AD, with a focus on their measurement outcomes and model development processes. The review will follow the Arksey and O'Malley framework and incorporate PRISMA-ScR guidelines. This study will search multiple databases, including Web of Science, Cochrane Library, and PubMed, covering relevant gray literature. The quality of the included studies will be rigorously assessed using the Prediction Model Risk of Bias Assessment Tool (PROBAST) and Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD) checklists. Two independent reviewers will conduct title and abstract screening, retrieve and assess full-text evidence sources, and extract data. The results will be narratively synthesized and presented in tables and figures. The knowledge gained from this review is expected to provide systematic evidence supporting AI-based predictive models that combine wearable devices for AD, potentially offering insights into model construction details such as data collection and external validation.