AI technologies show potential in enhancing obesity prevention efforts, but research on their integration into real-world settings remains insufficient.
Do artificial intelligence technologies enhance obesity prevention efforts?
This systematic review highlights the growing use of AI in obesity detection but identifies a significant gap in its application for actual obesity prevention and management.
Absolute Event Rate: 0% vs 0%
ABSTRACT This systematic review examines the applications of artificial intelligence (AI) in preventing obesity, addressing a critical public health issue that affects a substantial portion of the population. With obesity rates rising alarmingly, particularly in the United States, this review synthesizes findings from 46 studies published between 2008 and 2024, highlighting the potential of AI technologies to enhance obesity prevention efforts. The review employs PRISMA guidelines to ensure a rigorous methodology, encompassing a comprehensive search of major biomedical databases. The results indicate a notable increase in research activity since 2018, with a predominant focus on AI‐driven methodologies for obesity detection, whereas areas such as prevention, management, and treatment remain underexplored. Various machine learning (ML) and deep learning (DL) algorithms, including support vector machines and long short‐term memory networks, were identified, with performance metrics such as accuracy and sensitivity commonly reported. Despite the promising advancements, the review identifies significant gaps in the literature, including a lack of comprehensive frameworks for integrating AI in real‐world settings and the need for more targeted research on prevention strategies. This review underscores the transformative potential of AI in combating obesity and calls for further investigation to optimize its applications in public health initiatives.
Haghighathoseini et al. (Tue,) reported a other. AI technologies show potential in enhancing obesity prevention efforts, but research on their integration into real-world settings remains insufficient.