Background: Obesity is a leading cause of preventable death worldwide. Artificial intelligence (AI), characterized by machine learning (ML) and deep learning (DL), has become an indispensable tool in obesity research. Objective: This scoping review aimed to provide researchers and practitioners with an overview of the AI applications to obesity research, familiarize them with popular ML and DL models, and facilitate the adoption of AI applications. Methods: We conducted a scoping review in PubMed and Web of Science on the applications of AI to measure, predict, and treat obesity. We summarized and categorized the AI methodologies used in the hope of identifying synergies, patterns, and trends to inform future investigations. We also provided a high-level, beginner-friendly introduction to the core methodologies to facilitate the dissemination and adoption of various AI techniques. Results: We identified 46 studies that used diverse ML and DL models to assess obesity-related outcomes. The studies found AI models helpful in detecting clinically meaningful patterns of obesity or relationships between specific covariates and weight outcomes. The majority (18/22, 82%) of the studies comparing AI models with conventional statistical approaches found that the AI models achieved higher prediction accuracy on test data. Some (5/46, 11%) of the studies comparing the performances of different AI models revealed mixed results, indicating the high contingency of model performance on the data set and task it was applied to. An accelerating trend of adopting state-of-the-art DL models over standard ML models was observed to address challenging computer vision and natural language processing tasks. We concisely introduced the popular ML and DL models and summarized their specific applications in the studies included in the review. Conclusions: This study reviewed AI-related methodologies adopted in the obesity literature, particularly ML and DL models applied to tabular, image, and text data. The review also discussed emerging trends such as multimodal or multitask AI models, synthetic data generation, and human-in-the-loop that may witness increasing applications in obesity research.

Background: Accurate measurement of food and nutrient intake is crucial for nutrition research, dietary surveillance, and disease management, but traditional methods such as 24-hour dietary recalls, food diaries, and food frequency questionnaires are often prone to recall error and social desirability bias, limiting their reliability. With the advancement of artificial intelligence (AI), there is potential to overcome these limitations through automated, objective, and scalable dietary assessment techniques. However, the effectiveness and challenges of AI applications in this domain remain inadequately explored. Objective: This study aimed to conduct a scoping review to synthesize existing literature on the efficacy, accuracy, and challenges of using AI tools in assessing food and nutrient intakes, offering insights into their current advantages and areas of improvement. Methods: This review followed the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guidelines. A comprehensive literature search was conducted in 4 databases—PubMed, Web of Science, Cochrane Library, and EBSCO—covering publications from the databases’ inception to June 30, 2023. Studies were included if they used modern AI approaches to assess food and nutrient intakes in human subjects. Results: The 25 included studies, published between 2010 and 2023, involved sample sizes ranging from 10 to 38,415 participants. These studies used a variety of input data types, including food images (n=10), sound and jaw motion data from wearable devices (n=9), and text data (n=4), with 2 studies combining multiple input types. AI models applied included deep learning (eg, convolutional neural networks), machine learning (eg, support vector machines), and hybrid approaches. Applications were categorized into dietary intake assessment, food detection, nutrient estimation, and food intake prediction. Food detection accuracies ranged from 74% to 99.85%, and nutrient estimation errors varied between 10% and 15%. For instance, the RGB-D (Red, Green, Blue-Depth) fusion network achieved a mean absolute error of 15% in calorie estimation, and a sound-based classification model reached up to 94% accuracy in detecting food intake based on jaw motion and chewing patterns. In addition, AI-based systems provided real-time monitoring capabilities, improving the precision of dietary assessments and demonstrating the potential to reduce recall bias typically associated with traditional self-report methods. Conclusions: While AI demonstrated significant advantages in improving accuracy, reducing labor, and enabling real-time monitoring, challenges remain in adapting to diverse food types, ensuring algorithmic fairness, and addressing data privacy concerns. The findings suggest that AI has transformative potential for dietary assessment at both individual and population levels, supporting precision nutrition and chronic disease management. Future research should focus on enhancing the robustness of AI models across diverse dietary contexts and integrating biological sensors for a holistic dietary assessment approach.

The outbreak and spread of novel coronavirus disease (COVID-19) in 2019 was a public health emergency of global concern. As an important health behavior, physical activity (PA) and its impact on mental health have been increasingly explored during the epidemic period. The keywords and references were searched on PubMed, Web of Science, Scopus, Cochrane Library, EBSCO, and CNKI since the inception of an electronic bibliographic database until October 2021. A total of 2979 articles were identified, of which 23 were eligible for inclusion to examine the relationship between PA and mental health during the COVID-19 epidemic. Residents with regular PA, high-intensity PA, and PA duration of 30–60 min or more per day were associated with a lower risk of anxiety, depression, and negative emotions. In contrast, residents with no exercise and physical inactivity were more likely to have anxiety, depression, sleep disturbances, and lower subjective well-being. In addition, the dose–response curve between PA and negative emotions indicated a U-shaped relationship, and there were urban–rural differences in the relationship between emotional status and the levels of PA in adolescents. The findings have significant implications for addressing mental health issues during the current pandemic and future pandemics. Future studies adopting an experimental study design, conducting objective PA measures, and focusing on the vulnerable subpopulations are warranted to further explore the association of PA on mental health during the COVID-19 pandemic.

Green space may play an essential role in residents’ physical activity (PA), but evidence remains scattered in China. This study systematically reviewed scientific evidence regarding the influence of green space on PA among residents in China. Keyword and reference searches were conducted in PubMed, Web of Science, Scopus, EBSCO, and CNKI from the inception of an electronic bibliographic database to May 2021. Eligibility criteria included the following: study designs—observational (e.g., longitudinal or cross-sectional studies) and experimental studies; study subjects—people of all ages; exposures—green space (e.g., parks, vegetation areas, open green fields); outcomes—leisure-time and work/school-related PA (e.g., active commuting); and country—China. All but two studies identified at least one measure of green space to be associated with PA. Street greenness was associated with increased odds of active commuting (e.g., cycling) and walking, and a reduced risk of physical inactivity. Access to green space was associated with increased PA levels and green space usage. Distance to green space was inversely associated with the odds of PA. By contrast, evidence linking overall greenness exposure to PA remains limited. Future studies adopting experimental study design are warranted to establish more robust scientific evidence of causality between green space and PA in China. Future studies are also warranted to examine the underlining mechanisms and the differential impacts of green space on population subgroups in China.

The aging global population necessitates innovative strategies to enhance older adults' health and quality of life. Physical activity (PA) is crucial for healthy aging, yet many older adults struggle to exercise regularly. Artificial intelligence (AI)-powered social robots offer an interactive, engaging, and personalized solution to promote PA among this demographic. This systematic review investigated the role of AI-powered social robots in encouraging PA in older adults. We conducted a systematic literature search in databases including PubMed, IEEE Xplore, Scopus, Cochrane Library, and Web of Science, focusing on studies published until February 2024. We included peer-reviewed articles reporting empirical findings on designing, implementing, and evaluating AI-enabled social robots to promote PA among older adults. Studies were conducted in nursing homes, rehabilitation centers, community centers, and home environments. A total of 19 studies were included in the review. Analysis reveals that AI-powered social robots effectively motivate older adults to engage in PAs, leading to increased exercise adherence, higher engagement levels, and extended training durations. Social robots have demonstrated effectiveness across various environments, including nursing homes, rehabilitation centers, community centers, home environments, and elder care facilities. In structured environments like nursing homes and rehabilitation centers, robots help maintain regular exercise routines, improving adherence and recovery outcomes. In community and elder care centers, robots promote PA and social engagement by facilitating group exercises and enhancing participation. In home environments, robots provide personalized support for daily activities, offering reminders and engagement, which fosters long-term activity engagement. User acceptance and satisfaction are high, with participants finding the robots engaging and enjoyable. Additionally, several studies indicate potential health benefits, such as improved medication adherence, better sleep patterns, and enhanced overall well-being. Nevertheless, additional research is imperative to address unresolved issues concerning the technological maintenance costs, design constraints, and adaptability of AI-powered social robots to specific user demographics. AI-powered social robots play a promising role in promoting PA among older adults, enhancing their health, well-being, and independence. This review provides insights for researchers, designers, and healthcare professionals developing AI-enabled social robotic systems for older adults.