A survey of mastication evaluation: from traditional approach to artificial intelligence

Abstract

Abstract Mastication, a critical component of human digestion and oral health, plays a vital role in overall well-being, particularly in aging populations. An accurate assessment of chewing efficiency is essential for diagnosing and managing dental and orofacial conditions. Over the years, various methods have been developed to evaluate masticatory performance, ranging from traditional techniques such as sieving and color-changing chewing gums to modern approaches leveraging artificial intelligence (AI), wearable devices, and robotic simulators. This paper provides a comprehensive review of the evolution of masticatory evaluation methods, from conventional to AI-driven approaches. We systematically analyze the strengths and limitations of these methods, their applications in clinical and research settings, and their potential for future innovation. Traditional methods, while effective, often face challenges related to time consumption, practicality, and individual variability. In contrast, AI-based technologies, including computer vision systems, wearable sensors, and machine learning algorithms, offer real-time, non-invasive, and highly precise assessments of chewing efficiency. These advancements not only enhance diagnostic accuracy but also enable personalized and continuous monitoring of masticatory function, particularly beneficial for elderly populations and individuals with oral health impairments. By integrating these innovative tools, the field of masticatory evaluation is poised to improve diagnostics, treatment planning, and personalized care, ultimately enhancing oral health and quality of life. This review highlights the transformative potential of AI and underscores the need for multidisciplinary collaboration to further refine these technologies for clinical and research applications.