Prediction of the intention to use a smartwatch: A comparative approach using machine learning and partial least squares structural equation modeling

This study makes use of a cohesive yet innovative research model to identify the determinants adoption smart watches using constructs from Technology Acceptance Model (TAM) and smartwatches, including effectiveness, content richness, personal innovativeness. The chief objective was encourage smartwatches for medical purposes so that role doctors can be made more effective facilitate access patient records. Our conceptual framework highlights association TAM (i.e., perceived usefulness ease use) with construct user satisfaction, To measure effectiveness smartwatch, an external factor based on flow theory added, which emphasizes control over smartwatch degree involvement. employs data 385 respondents involved in field medicine, such as doctors, patients, nurses. were gathered through survey used evaluation partial least squares structural equation modeling (PLS-SEM) machine learning (ML) models. significance performance factors impacting THE also identified Importance-Performance Map Analysis (IPMA). User satisfaction is most important predictor intention adopt according ML IPMA analyses. fitting sample showed high dependence use. Furthermore, two critical factors, innovativeness are demonstrated enhance usefulness. However, one should consider or behavioral could not determined In general, findings suggest usage become critically mediator allows other users essential information.