AI-Enabled Edge-Based Intraoral Wearable System for Early Detection and Management of Dental Caries

Dental caries remains one of the most prevalent yet preventable non-communicable diseases worldwide, disproportionately affecting populations with limited access to dental care and persistent socioeconomic inequalities. Early-stage lesions frequently remain undetected because of their asymptomatic nature, inadequate screening infrastructure, and the absence of continuous monitoring technologies, resulting in preventable complications and increased healthcare costs. To address these challenges, this study proposes an Internet of Things (IoT)-enabled intraoral wearable sensing device (I-OWSD) for continuous, quantitative, real-time monitoring of biomarkers associated with caries progression. The proposed framework integrates intraoral wearable sensing, cloud-based telemedicine services, and artificial intelligence (AI)-assisted analytics to support preventive oral healthcare and remote clinical decision-making. Two primary contributions are presented. First, a fractional-order delay-type model (FODM) based on the Caputo–Fabrizio derivative is proposed to capture the memory-dependent and nonlocal dynamics of caries progression. Mathematical analysis establishes the model’s non-negativity, boundedness, existence, uniqueness, and stability properties. Second, a biocompatible intraoral sensor interface is designed to enable continuous data acquisition and secure wireless communication with digital health platforms. Simulation results based on the proposed FODM suggest that, under an estimated adoption rate of 67.49%, the I-OWSD framework could reduce caries prevalence by approximately 15% while improving opportunities for early intervention and preventive care. The findings demonstrate the potential of combining fractional-order modelling, wearable sensing, and AI-driven teledentistry to advance continuous oral health monitoring and preventive dental care.