A scoping review of artificial intelligence-tailored inner beauty solution for obesity: focusing on oolong tea

Introduction

Obesity is a major global problem. Obesity is associated with several diseases, including metabolic syndrome, type 2 diabetes, cardiovascular disease (CVD), and hypertension. Studies have also shown that obesity is associated with an increased risk of several types of cancer (1). The number of people suffering from severe obesity continues to increase, and clinical data show that severely obese patients are at an increased risk for all diseases (1). The prevalence of obesity and pre-obesity continues to increase worldwide. In addition, obesity has been identified as a serious disease that not only affects physical and mental health, but also causes economic burden (1). Abdominal obesity and metabolic syndrome have been reported to be associated with CVD, which is known to be the leading cause of death among American women (2). Obesity is the most important factor contributing to CVD. The incidence and severity of cardiovascular events tend to increase with age (3). Tea polyphenol (TP) is a general term for polyhydroxy compounds contained in tea leaves. The main components of tea include catechin, flavonoids, flavonols, anthocyanins, phenolic acids, condensed phenolic acids, and polymerized phenols. Among them, catechin is the main component of TP (4). Tea, one of the most consumed beverages worldwide, is known to have antioxidant and immunomodulatory effects. It also has powerful biological activities such as cardiovascular protection and anticancer effects (5). It contains various phytochemicals with health-promoting effects. Tea and its components are considered as the most important potential anti-obesity candidates. Recent epidemiological studies have reported that regular consumption of tea is effective in reducing body fat (6). Experimental studies have also confirmed the potential anti-obesity mechanisms of tea (7). It mainly increases energy expenditure and lipid decomposition. It also decreases nutrient digestion and absorption and lipid synthesis. It is reported to be involved in regulating adipocytes, neuroendocrine system, and intestinal microflora (8). Most clinical studies have reported that tea consumption can reduce body weight and alleviate obesity (9-11).

Oolong tea is a traditional Chinese tea and one of the most popular tea drinks. It is a semi-fermented tea that is fermented to a degree between green tea and black tea. It is mainly produced in Fujian and Guangdong provinces in southern China. Oolong tea is famous for its unique aroma and taste, and it is widely consumed because it has various health benefits (12). Oolong tea has antioxidant effects, stress relief, and immune system reduction benefits. Among them, it is shown to have the most excellent effect in reducing body fat (13). Kuo et al. reported in a study on comparative studies on the hypolipidemic and growth suppressive effects of oolong, black, pu-erh, and green tea leaves in rats that the weight loss in the group fed tea leaves was in the order of oolong tea > pu-erh tea > black tea > green tea. This result showed that oolong tea could lower neutral fat levels more significantly than green tea and black tea (14).

The scope of application of artificial intelligence (AI) is expanding worldwide. It will be deeply involved in our lives and will be of great help. As the scope of application of AI is expanding, research has been conducted on the possibility of utilizing the existence of Senior Connection, a digitally excluded group. This aimed to investigate the possibility of utilizing AI for the welfare of the elderly. It was concluded that AI can be used to enable a healthy, sustainable, and beautiful life. It was confirmed through research that consumers will try to solve various health problems for healthy skin and hair for sustainable safety and welfare of the elderly. This confirms the strong need for the convenience of AI (15). A study was conducted to find out the possibility of personalized cosmetic devices using AI and solutions to skin problems that can occur through AI. Considering the sustainability and safety of personalized cosmetic devices in the AI era, it investigated human skin care and alleviating skin damage caused by ultraviolet rays. This was an additional study to evaluate the impact on beauty and health, and it was said that it should reflect the needs of consumers. Therefore, it was said that further research on skin inner beauty materials and personalized cosmetics centered on continuous human security will be necessary. Accordingly, the research results showed that AI is expected to increase further in the scientific community, nutrition, inner beauty, and cosmetics industries. It was expected to be utilized in AI-based personalized skin health strategies and nutritional approaches for human security (16,17).

Therefore, in this study, Obesity is emerging as a major problem worldwide and is associated with various diseases. It is known to increase the risk of metabolic syndrome, type 2 diabetes, CVD, hypertension, and various types of cancer. As the prevalence of obesity and pre-obesity increases worldwide, the risk of all diseases in patients with severe obesity is also increasing. Against this backdrop, obesity is recognized as a serious disease that causes not only physical and mental health but also economic burden. Therefore, this study aims to identify consumer needs for customized inner beauty products to solve the obesity problem that is spreading worldwide. Considering the effects of oolong tea such as antioxidants, stress relief, and immune system enhancement, and the potential benefits of reducing body fat, we explore the possibility of utilizing AI for customized health care and obesity management. Through this, we aim to examine the effectiveness of AI-based customized health care and obesity management using a car automation device. We present this article in accordance with the PRISMA-ScR reporting checklist (available at https://jmai.amegroups.com/article/view/10.21037/jmai-24-371/rc).

Materials and methods

This study was conducted using a narrative review approach and included a critical scoping review. The PRISMA flow chart was used in major academic journal search sites such as ResearchGate, PubMed, Scopus, and Google Scholar. The following search terms were used: obesity, artificial intelligence, customized inner beauty, oolong tea, tea polyphenols, tea and obesity, AI and obesity. Figure 1 is a graphic flow chart for exploring the studies to include in this scoping review.

Figure 1 PRISMA flow diagram.

Eligibility criteria

This study was conducted according to the following eligibility criteria: (I) the increase and severity of obesity worldwide; (II) types and values of tea for obesity solutions; (III) Health, obesity management and aesthetic perspectives of oolong tea; (IV) potential applications of AI healthcare and tea dispensing were considered for inclusion. In the AI usability study, the following additional criteria were used: the link between obesity management and AI.

Screening and data extraction

The selection criteria were as follows. First, research papers, second, review papers, third, papers published in Google Research, fourth, brief reports, and fifth, materials on the topic of the paper. In addition, to obtain various information, the papers were reviewed comprehensively without restrictions on the publication date or language. However, materials that did not meet the following criteria were excluded. First, materials without an abstract in the original text or unclear materials, second, materials that did not match the topic of the paper, third, materials that did not match the type of university or other papers, and fourth, materials that were irrelevant to the focus of the review were excluded from the papers and proceeded.

Study selection and data extraction

The search algorithm was as follows: [(‘obesity’ OR ‘artificial intelligence’ OR ‘customized inner beauty OR oolong tea’ OR obesity OR Device OR Healthy obesity OR obesity tea OR tea artificial intelligence OR tea inner beauty) AND (obesity due to artificial intelligence)]. The search was performed using these terms to ensure the relevance of the study. Here is a description of the elements depicted in the research model diagram for Figure 2: first, the global obesity problem: this section highlights the increasing rate and severity of obesity worldwide, highlighting the growing public health problem. Second, the types and value of tea as a solution to obesity: This section explores the different types of tea, such as green tea, black tea, and oolong tea, and their benefits in managing obesity. They may contain unique properties that are suitable for weight management. Third, the health and beauty perspective of oolong tea: This section focuses on the specific health and beauty benefits of oolong tea. These include its antioxidant properties, ability to aid in weight loss, and potential to improve skin health. Fourth, the potential for AI in health management and tea distribution: This section explores how AI technologies can be integrated into health management systems to help utilize tea as part of a weight management program. Also, the link between obesity management and AI: this section highlights the need to combine AI technologies with obesity management. It explores how AI can improve the effectiveness of weight management strategies and personalization treatment. Hence, the need for AI distribution in obesity management using oolong tea: this final section confirms the need for integrating AI into distributing oolong tea for obesity management. The practical applications of this approach and the benefits of oolong tea are highlighted. Figure 3 also emphasizes the health and beauty aspects of oolong tea, saying that it will help with dieting for a healthy and beautiful body. Figure 4 shows the importance of AI technology in healthcare, mentioning an AI-based tea distribution system and visualizing the system.

Figure 2 Literature review model. AI, artificial intelligence.

Figure 3 Health and beauty aspects of oolong tea.

Figure 4 AI-based tea dispensing system. AI, artificial intelligence.

Results

This study included a scoping review. A total of 2,616 references were selected using the PRISMA results from representative journal search sites such as ResearchGate, PubMed, Scopus, and Google Scholar. Accordingly, a total of 65 articles from 1996 to 2024 were finally selected. The PRISMA results are shown in Figure 1. The detailed data of records identified from: Databases (n=1,890) of Figure 1 are as follows: obesity (n=908), artificial intelligence (n=600), customized inner beauty (n=64), and oolong tea (n=318). The detailed data of Registers (n=726) are as follows: obesity (n=312), artificial intelligence (n=207), customized inner beauty (n=38), and oolong tea (n=169). The exclusion criteria were as follows: first, full text without raw data. Second, full text without accessibility. Third, topics that were inappropriate for this paper. Fourth, those that were not related to the focus of this review were excluded. In addition, the Research model diagram is summarized in Figure 2. In addition, Figure 3 shows the health and beauty aspects of oolong tea, and the implementation of the AI-based tea dispensing system is shown in Figure 4. Additionally, 980 studies that matched the keywords of this study but did not match the topic of the study were deleted. Therefore, the main references of the 65 studies included in this study were organized and the characteristics of the included studies were presented in Table 1. They were published in 15 countries, most of which were published in China (N=19), followed by the United States (N=16). Figure 5 shows the country/region distribution of included studies (N=65). There were 27 studies included in the review and 38 study reports included. In addition, comparing the benefits of oolong tea, green tea, and black tea is shown in Table 2. This shows the health benefits of tea and the advantages of oolong tea in managing obesity.

Figure 5 Country/region distribution of included studies (N=65).

The increase and severity of obesity worldwide

Obesity is a constant problem worldwide. Its serious condition affects more than 2 billion people worldwide (18). The global increase in obesity has led to discussions about classifying obesity as a disease. It is not a medical condition or a risk factor for other diseases. Obesity is a complex disease with multifaceted etiology. It has its own potential for disability. It is also reported to have pathophysiology and complications. Environmental factors have been considered as major variables in recent years. It is also considered as a physiological dysfunction of the human organism with genetic and endocrine etiology. This is why obesity meets the medical definition of a disease (19).

In the United States, overweight and obesity have also been identified as a major threat to public health. Their research reported that it affects more than 60% of the adult population. The largest increase was also identified among African American women, who are disproportionately represented as overweight and obese. They are identified as having poorer health and at greater risk for obesity-related disorders (20). Obesity has been identified as being associated with reduced fertility. It has also been reported that there may be a problem in epidemiology linking excessive weight and reduced fertility. Obese women have a lower chance of pregnancy per cycle than women with abdominal obesity. These obese women may have a disturbance in the hypothalamic-pituitary-ovarian axis. This causes a disturbance in the menstrual cycle. Accordingly, it has been reported that they are up to three times more likely to experience oligo- and anovulation. The delicate hormonal balance caused by this regulates follicular development and maturation of eggs (21). In addition, obesity is associated with reduced fertility, but the epidemiology and mechanisms linking overweight and reduced fertility are not yet fully understood. When looking at the comprehensive impact of obesity on female fertility, women with central obesity have a lower probability of pregnancy per cycle, are more likely to experience hypothalamic-pituitary-ovarian axis changes, menstrual cycle disorders, and infrequent or no ovulation (22). Therefore, it has been observed that obesity can change the hormonal environment. The severity of this obesity is expected to have serious implications for recent population problems and health (23).

Types and values of tea for obesity solutions

Tea can be divided into three types: unfermented green tea, fully fermented black tea, and semi-fermented oolong tea. All of these are made from the leaves of the Camellia sinensis plant (11). Organic acids account for about 3% of the dry tea leaves. Their composition and content vary slightly depending on the type of tea. Organic acids participate in the metabolism of tea trees. They regulate nutrient absorption and growth. They also contribute to the quality of tea aroma and taste. They play a major role in human antioxidants. They also promote digestion and absorption, which are important for health. This is because they accelerate gastrointestinal transit. They also include health benefits related to immunity, such as regulating intestinal flora (24). Likewise, tea has also been proven to have effects on CVDs. Also, tea’s antioxidant and antimutagenic potential against cancer and obesity has been studied for a long time. It is reported that these therapeutic and nutritional benefits of tea may be due to the presence of flavonoids (25). In a study of obesity using black tea, women who consumed it were reported to have changes in the production of reactive oxygen species. A relative decrease in request for proposals was shown. This was greater after 5 months than after 1 month of treatment. The decrease in robot operating system (ROS) production after black tea consumption can be confirmed by the response to the tested compounds in normal cells. Therefore, it appeared together with the decrease in ROS. It was confirmed that black tea epigallocatechin gallate and task force showed similar efficacy in antioxidant activity (26). The protective effect of tea on CVDs has also been proven. This is related to the effect of inhibiting lipid oxidation and scavenging oxygen and hydroxyl free radicals. Tea pigments inhibit the oxidation of low-density lipoprotein cholesterol and the adhesion of vascular endothelial cells. In addition, they lower endothelin levels. This is known to increase glutathione peroxidase activity. This prevents blood clotting and platelet aggregation. It also shows an effect in preventing atherosclerosis of coronary arteries by promoting fibrinogen dissolution (27). Comparing the benefits of oolong tea, green tea, and black tea is shown in Table 2.

Health, obesity management and aesthetic perspectives of oolong tea

Oolong tea has attracted considerable attention for its beneficial effects on obesity. This has been clearly demonstrated in a study comparing the anti-obesity effects of oolong tea over several years on mice fed a high-fat diet. As a result of the study, oolong tea in 2001, oolong tea in 2011, and oolong tea in 2020 were administered extracts (400 mg/day per kg) for 8 weeks. It was confirmed that the mice fed a high-fat diet lost weight. It was confirmed that the mice fed a high-fat diet showed an alleviation of obesity (28). In addition, mice that consumed oolong tea were confirmed to have decreased adipocyte size, sterol regulatory element binding protein 1 (SREBP1), and fatty acid synthase (FASN) protein expression, which are fat-producing proteins. In addition, it was confirmed that the expression of superoxide dismutase-activated receptor gamma coactivator 1-alpha (PGC1α), a thermogenic protein, and uncoupling protein 1 (UCP1) protein in epididymal adipose tissue was increased compared to the full high-definition group (29). This confirms that oolong tea regulates lipid metabolism. It can be understood that it reduces lipid accumulation in adipose tissue by regulating the distribution of intestinal microflora communities. Therefore, it shows that oolong tea can alleviate weight gain (30).

Potential applications for AI healthcare and tea dispensing

Health Level 7 fast healthcare interoperability resources are widely used. It is being utilized in low- and middle-income environments. Health information systems in low- and middle-income have the advantage of being relatively stable and easy to implement. Electronic medical records are known to be increasing with the deployment of national reporting systems and mHealth applications. Open medical record system open-source electronic medical record has increased the demand for interoperability with another HISs. It has been recently deployed in more than 44 low- and middle-incomes. Therefore, new fast healthcare interoperability resources modules supporting the latest standards have been developed and deployed, and laboratory systems have been improved. It is also being used as a tool to support mHealth applications, interoperability with pharmacy dispensing systems, and advanced user interface design (31). A standardized, domain-independent application programming interface for electronic medical record systems has been developed. It is intended to enable better interoperability and easier adoption of healthcare applications. It leverages the modular architecture of the open medical record system. An add-on module based on fast healthcare interoperability resources has been built that can use fast healthcare interoperability resources and requests made in open medical record system. It supersedes both HL7 versions 2 and 3, thus demonstrating the adoption of the fast healthcare interoperability resources standard. It proposes a progressive integration approach where the fast healthcare interoperability resources API becomes the preferred way to communicate with the open medical record system platform and will be leveraged in a multifaceted manner (32). Healthcare organizations need to explore a variety of ways to improve the quality of care they provide. Therefore, interoperability must be an urgent priority. The demand for personalized healthcare systems is increasing. This requires processing a variety of data types. Interoperability between all healthcare stakeholders must also be increased (33). Telemedicine has broader implications for health care beyond individual patient care, addressing health disparities and enabling professionals to reach underserved areas. Marinelli et al. have highlighted that the introduction of telemedicine services across a range of health care disciplines provides important access to populations that are otherwise difficult to reach due to socioeconomic or geographic barriers (34). The development of an AI-based tea dispensing system can automatically provide tea that matches the user’s taste and health condition (35). AI analyzes the user’s preferences and the patient’s health data. In this way, it can recommend the optimal type and amount of tea. In addition, AI adjusts the temperature and brewing time of the tea. Accordingly, it can provide the user with the best taste. This system can be used not only at home but also in hospitals (36). Recently, the development of smart devices and the network linked to them are popularizing the Internet of Things. Accordingly, it is contributing greatly to prioritizing user convenience. The Internet of Things is not only smart homes, but smart devices are being actively used in all fields recently. The following results were obtained in the study of an innovative and practical intelligent coffee shop management system utilizing smart devices and Internet of Things devices. This allows not only kiosk ordering but also smartphone ordering. It also provides a beacon-based automatic user recognition function. It can also identify user location information using geofences. This means that ordering without waiting is possible. In addition, it can provide big data-based weather, temperature, time, and user-based recommendation services (37). Accordingly, research is being conducted on the potential development of AI in dermatology and U-healthcare, suggesting the limitless potential of AI (38). In addition, the “Sm@rtEven” project presented a way to utilize telemedicine to remotely assess the condition of patients after surgery. This approach allows healthcare providers to communicate with patients for extended periods of time, using mobile applications and continuous monitoring systems, thus allowing timely intervention and ensuring the rehabilitation process. In fact, telemedicine has been shown to facilitate remote consultations, reduce the need for travel, reduce healthcare costs, and prevent delays in the treatment of critically ill patients. In a study of the adoption of the Sm@rtEven application for remote assessment of traumatology patients and possible medical legislation, the Sm@rtEven application proved to be a useful tool for remotely following patients, especially during the pandemic. It was confirmed that telemedicine has the same value as traditional clinical assessment (39).

In the field of plant phenotyping, remote sensors and phenotyping platforms are also being utilized due to technological advancements. This has greatly increased in scalability over the past decade. These platforms examine thousands of plants multiple times throughout the day. This generates a huge amount of data. Automated analysis is required to extract meaningful information. Deep learning is a major field of machine learning that has revolutionized many research fields. These deep learning models autonomously extract basic features within a data set. They can provide multi-level representations of this data. In addition, deep neural networks can be trained to segment leaf images and extract pixels associated with diseases (40). In addition, an outbreak of Klebsiella pneumoniae producing metallo-β-lactamase (MBL) was reported in a children’s hospital in Japan. It was confirmed that the outbreak occurred in a tea dispenser in the hospital. K. pneumoniae producing MBL was detected in the tea dispenser. As such, tea dispensers are widely used in hospitals, and differentiated management will be necessary accordingly (41).

Discussion

Main findings

This research study is the first report to highlight the growing demand for and potential use of dermatology U-healthcare as population aging becomes more prominent globally. After the 4th Industrial Revolution, the importance of U-healthcare emerged, and a perception survey on this was conducted. The customized industry will further increase in this topic in the future, and as a result, the interest of academia and the cosmetics industry will increase. Given its importance to future human security, this trend is likely to continue in the future.

Why did you mention the need for AI dispensing in obesity management using oolong tea?

Tea is the most consumed beverage in the world. The fermentation of tea leaves plays an important role in the quality of tea. The olfactory perception of tea tasters is monitored through laboratory analysis equipment. This is done through advanced data processing. First, it can be confirmed from the perspective of an electronic nose equipped with an algorithm, second, an electronic tongue, and third, an electronic eye. The development of an electronic sensing platform has enabled consumer-based sensory quality assessment of tea (35). This can be accelerated accurately. In addition, it will be possible to define a new standard for this biologically active product, thereby meeting the demand for the inner beauty market that can manage health worldwide (42-44). Nutrition has been used to promote youth and beauty around the world. Recently, there has been an increase in interest in the connection between nutrition and skin aging. Accordingly, consumers have come to see beauty and health as closely related, and nutrition plays an important role in skin beauty and aging. For this reason, various inner beauty products are gaining popularity. Oolong tea, green tea, and black tea are known to have excellent antioxidant effects (45). Oolong tea is a traditional Chinese tea Camellia sinensis. The production technology of oolong tea varies by region, but it is mainly produced in Guangdong, Taiwan, and Fujian provinces in China. The climate and topography of each region greatly affect the quality of oolong tea, and traditional processing methods are combined with modern technology to create a variety of aromas and flavors. The oolong tea market size in 2024 was valued at approximately USD 5.57 billion, and is expected to reach approximately USD 7.02 billion by 2030, at a compound annual growth rate of 3.29%. The promotion of oolong tea is mainly focused on its health benefits, with ethical sourcing methods and sustainability also emerging as important factors (46). It is especially popular in southern China. In terms of health benefits, Oolong tea has excellent effects on reducing obesity, as explained by modern pharmacological studies. It is also effective in controlling diabetes. (-)-Epigallocatechin-3-gallate acts in Oolong tea to prevent the occurrence of cancer cells. Oolong tea improves and reduces heart and blood vessel diseases. It also protects teeth and bones (47). Recently, it can be used for its antioxidant effect in relation to beauty. It can also act as an antibacterial agent to prevent infectious diseases (48). Therefore, it is believed that this can be used in obesity and health management by combining it with AI.

What is the connection between obesity management and AI?

Obesity management is an effective way to reduce the risks and complications associated with obesity. It can improve the quality of life of patients. Various obesity management approaches have fewer side effects than medication and surgical treatments. In addition, management methods through this have the advantage of low cost. This customized self-management has been strongly recommended. Scientific guidance is needed to strategically implement it according to everyone’s lifestyle. Recently, with the development of electronic and information technology, customized interventions for everyone’s lifestyle have changed significantly. It is a new concept called Gamified Digital Therapeutics. It refers to a game format with Digital Therapeutics. It is reported that this method can effectively improve patient compliance and accessibility to chronic disease management (49). In addition, the latest technology for predicting type 2 diabetes mellitus was summarized and a study including deep learning was conducted. This is a study comparing the prediction accuracy obtained through existing statistical regression and machine learning methods. As a result, it was confirmed that the machine learning algorithm tends to perform better than logistic regression in technology for predicting type 2 diabetes mellitus prediction accuracy (50). Diabetic retinopathy in patients with type 1 diabetes has a negative impact on the prognosis due to complications such as complications. Such diabetes can lead to greater medical expenses due to complications. Using a predictive model through machine learning, we confirmed whether patients at risk for these microvascular complications can be prevented and identified early. This study may be helpful in the management of type 1 diabetes (51,52). The purpose of this study was to systematically identify published predictive models that assess the risk of diabetic nephropathy in type 1 diabetes patients using Machine learning. It is judged that AI-based management of diseases related to obesity such as diabetes will continue to be necessary (53,54).

What are the caffeine and health benefits of oolong tea in terms of nutrition and obesity management?

Known for its antioxidant properties, oolong tea plays an important role in obesity management. As a rich source of antioxidants, it helps combat oxidative stress and inflammation that are associated with obesity and metabolic disorders. Regular consumption of oolong tea can improve your nutrition by providing essential compounds that support overall health. These antioxidants help break down body fat, improve metabolism, and reduce the risk of obesity-related complications. Caffeine can also help with weight loss by promoting oxidative fat breakdown. Incorporating oolong tea into a balanced diet can help individuals reap the health-promoting benefits, making it a valuable addition to an obesity management strategy. Therefore, the antioxidant properties of oolong tea make it an effective dietary component in managing obesity, emphasizing the importance of nutrition for overall health (55). Tea consumption is becoming increasingly popular, especially due to weight loss claims (56,57). Among them, the benefits of oolong tea for obesity management can be supported by the following research results (58). This means that oolong tea is more effective in obesity management than green tea and black tea. The research results confirmed that oolong tea has the greatest weight-suppressing effect, and oolong tea is excellent in lowering neutral fat levels. However, oolong tea contains caffeine, although less than coffee, so caution is required. People who are sensitive to caffeine are advised to consume it in moderation (59). Accordingly, personalized drinking using AI will be necessary.

Can AI transparency and interpretability enhance personalized medicine with T-automation devices?

Integrating AI into personalized healthcare systems, such as the proposed T-automation device, requires a focus on AI transparency and interpretability. According to the results of bootstrap simulations of machine learning methods, out of 10,000 simulations completed, the gain for angina was 0.225–0.456 with a difference of 0.231. In addition, the gain for cholesterol was 0.148–0.326 with a difference of 0.178. The gain for maximum heart rate was 0.081–0.200 with a difference of 0.119. In addition, the study results showed that the gain for age was 0.059–0.157 with a difference of 0.098. Ensuring that AI systems are transparent and that their decision-making processes are interpretable is important for building trust and ensuring effective health interventions. This transparency makes it easier for users and healthcare providers to understand the basis for AI-generated recommendations, making it easier to adopt and implement these recommendations in their daily lives (60). Also, early taste sensors were designed to achieve a specific goal. The human tongue cannot directly identify individual chemicals, but it can identify groups of chemicals with similar tastes. In this identification process, the human brain interprets and restores the received taste stimuli as individual experiences. Similarly, artificial taste sensors work on the principle that groups of chemicals evoke similar taste responses. For example, sweetness is detected by the presence of sugars, including glucose, sucrose, fructose, or a combination of these, and umami taste is induced by the amino acid glutamate. Thus, artificial taste sensors mimic human taste experiences by detecting similar taste responses caused by various chemicals (61). The AI tea sensor showed a short response time for specific properties, high selectivity and sensitivity, high stability for result measurement, high resistance to different scents to distinguish different scents, and was shown to be insensitive to temperature and humidity. In addition, it was shown to be small, inexpensive, and reusable (62).

What are the possibilities for tea consumption and health management using AI and machine learning?

In the ever-evolving healthcare environment, AI-based technologies are playing an increasingly important role. Integrating AI into healthcare systems through AI-based devices such as tea automation systems holds significant potential to improve overall health outcomes. These AI systems can monitor and suggest health-oriented tea consumption patterns, providing users with personalized recommendations that are aligned with their health goals. This not only promotes better eating habits, but also promotes a holistic approach to wellness (63). Machine learning applications have a particularly significant impact on chronic disease management. By analyzing vast amounts of patient data, Machine learning algorithms can identify patterns and predict disease progression. For example, in the context of obesity management, AI can provide personalized interventions based on an individual’s dietary habits and lifestyle choices. These insights can help healthcare providers tailor more effective and personalized treatment plans for patients, ultimately resulting in better health outcomes (64).

Furthermore, the role of ML extends to chronic disease prediction. Predictive models can assess the likelihood of developing a disease based on a variety of factors, including genetic predisposition and lifestyle choices (35). The proposed AI system can explore the integration of tea consumption as an obesity prevention measure. By analyzing data on tea composition, consumption patterns, and health effects, the AI system can provide valuable recommendations to help manage and prevent obesity (36). This proactive approach to healthcare highlights the transformative potential of AI and Machine learning in creating a more personalized and effective healthcare ecosystem. In summary, the synergy of AI-based devices and Machine learning applications in healthcare can revolutionize chronic disease management and prediction. These technologies have the potential to significantly improve health outcomes and patient well-being by facilitating personalized health interventions and preventive measures (65).

Limitations of this study

The limitation of this study is that, despite numerous studies on obesity and tea being conducted worldwide, AI that ensures sustainable safety and further research on it are needed. Therefore, to expand the scope of this study, future research on customized oolong tea for the obese population and the development of various user-friendly applications are needed. In addition, AI obesity care has great potential to be utilized in the inner beauty field, but research on this is insufficient. In the future, attention should be paid to the safety and protection of personal information for dietary therapy. In addition, collaboration with medical experts is necessary. Therefore, follow-up research seems necessary. The development of AI in the field of obesity healthcare is expected in the future.

Conclusions

The AI-based tea automation device in this study is expected to be effective in personalized health care and obesity management. This study provides important data for the development of hospital and home health care tea automation device products and confirms that oolong tea contributes to reducing the risk of obesity as an important source of dietary antioxidants. In the future, the value of health functional tea will become more important, and research on personalized health care services using AI technology should continue. Such policy improvements will enhance the effectiveness of personalized health care and obesity management. Accordingly, this study identified consumer needs for personalized inner beauty products, and the effectiveness of health care and obesity management using AI-based tea automation devices was confirmed. In addition, research on augmented reality, virtual reality, and AI complex food technology is needed to develop personalized tea products that reflect consumer needs.

Acknowledgments

None.

Footnote

Reporting Checklist: The authors have completed the PRISMA-ScR reporting checklist. Available at https://jmai.amegroups.com/article/view/10.21037/jmai-24-371/rc

Peer Review File: Available at https://jmai.amegroups.com/article/view/10.21037/jmai-24-371/prf

Funding: None.

Conflicts of Interest: Both authors have completed the ICMJE uniform disclosure form (available at https://jmai.amegroups.com/article/view/10.21037/jmai-24-371/coif). The authors have no conflicts of interest to declare.

Ethical Statement: The authors are accountable for all aspects of the work in ensuring that questions related to the accuracy or integrity of any part of the work are appropriately investigated and resolved.

Open Access Statement: This is an Open Access article distributed in accordance with the Creative Commons Attribution-NonCommercial-NoDerivs 4.0 International License (CC BY-NC-ND 4.0), which permits the non-commercial replication and distribution of the article with the strict proviso that no changes or edits are made and the original work is properly cited (including links to both the formal publication through the relevant DOI and the license). See: https://creativecommons.org/licenses/by-nc-nd/4.0/.

References

1. Alfaris N, Alqahtani AM, Alamuddin N, et al. Global Impact of Obesity. Gastroenterol Clin North Am 2023;52:277-93. [PubMed]
2. Evangelista O, McLaughlin MA. Review of cardiovascular risk factors in women. Gend Med 2009;6:17-36. [PubMed]
3. Budhathoki S, Graham C, Sethu P, et al. Engineered Aging Cardiac Tissue Chip Model for Studying Cardiovascular Disease. Cells Tissues Organs 2022;211:348-59. [PubMed]
4. Guo J, Li K, Lin Y, et al. Protective effects and molecular mechanisms of tea polyphenols on cardiovascular diseases. Front Nutr 2023;10:1202378. [PubMed]
5. Tang GY, Meng X, Gan RY, et al. Health Functions and Related Molecular Mechanisms of Tea Components: An Update Review. Int J Mol Sci 2019;20:6196. [PubMed]
6. Huang S, Li J, Wu Y, et al. Tea Consumption and Longitudinal Change in High-Density Lipoprotein Cholesterol Concentration in Chinese Adults. J Am Heart Assoc 2018;7:e008814. [PubMed]
7. Xu Y, Zhang M, Wu T, et al. The anti-obesity effect of green tea polysaccharides, polyphenols and caffeine in rats fed with a high-fat diet. Food Funct 2015;6:297-304. [PubMed]
8. Wang J, Li P, Liu S, et al. Green tea leaf powder prevents dyslipidemia in high-fat diet-fed mice by modulating gut microbiota. Food Nutr Res 2020; [PubMed]
9. Xu XY, Zhao CN, Li BY, et al. Effects and mechanisms of tea on obesity. Crit Rev Food Sci Nutr 2023;63:3716-33. [PubMed]
10. Huang J, Wang Y, Xie Z, et al. The anti-obesity effects of green tea in human intervention and basic molecular studies. Eur J Clin Nutr 2014;68:1075-87. [Crossref] [PubMed]
11. Hayat K, Iqbal H, Malik U, et al. Tea and its consumption: benefits and risks. Crit Rev Food Sci Nutr 2015;55:939-54. [PubMed]
12. Shao S, Xu M, Liao X, et al. Production regions discrimination of Huangguanyin oolong tea by using the content of chemical components and rare earth elements. Food Res Int 2023;165:112522. [Crossref] [PubMed]
13. Yang Y, Qiao L, Zhang X, et al. Effect of methylated tea catechins from Chinese oolong tea on the proliferation and differentiation of 3T3-L1 preadipocyte. Fitoterapia 2015;104:45-9. [Crossref] [PubMed]
14. Kuo KL, Weng MS, Chiang CT, et al. Comparative studies on the hypolipidemic and growth suppressive effects of oolong, black, pu-erh, and green tea leaves in rats. J Agric Food Chem 2005;53:480-9. [Crossref] [PubMed]
15. Lee J, Kwon KH. Changes and expectations of the digitally underprivileged in artificial intelligence: a systematic review focusing on skin health for the welfare of the elderly. J Med Artif Intell 2024;7:30. [Crossref]
16. Lee J, Kwon KH. Skin health response to climate change weather tailored cosmetics using artificial intelligence. J Med Artif Intell 2024;7:20. [Crossref]
17. Kamel I. Artificial intelligence in medicine. J Med Artif Intell 2024;7:4. [Crossref]
18. Caballero B. Humans against Obesity: Who Will Win? Adv Nutr 2019;10:S4-9. [Crossref] [PubMed]
19. Conway B, Rene A. Obesity as a disease: no lightweight matter. Obes Rev 2004;5:145-51. [Crossref] [PubMed]
20. Stephens EW. Relationship between obesity's adverse health risk and body mass index in African-American women. J Natl Black Nurses Assoc 2008;19:28-34. [PubMed]
21. Marinelli S, Napoletano G, Straccamore M, et al. Female obesity and infertility: outcomes and regulatory guidance. Acta Biomed 2022;93:e2022278. [PubMed]
22. Silvestris E, de Pergola G, Rosania R, et al. Obesity as disruptor of the female fertility. Reprod Biol Endocrinol 2018;16:22. [Crossref] [PubMed]
23. Broughton DE, Moley KH. Obesity and female infertility: potential mediators of obesity's impact. Fertil Steril 2017;107:840-7. [Crossref] [PubMed]
24. Chen H, Yu F, Kang J, et al. Quality Chemistry, Physiological Functions, and Health Benefits of Organic Acids from Tea (Camellia sinensis). Molecules 2023;28:2339. [Crossref] [PubMed]
25. Jain A, Manghani C, Kohli S, et al. Tea and human health: the dark shadows. Toxicol Lett 2013;220:82-7. [Crossref] [PubMed]
26. Zielińska-Przyjemska M, Dobrowolska-Zachwieja A. Effect of tea polyphenols on oxidative metabolism of polymorphonuclear neutrophils in healthy and obese people. Pol Merkur Lekarski 2005;19:41-7. [PubMed]
27. Han C. Studies on the antioxidant properties of tea. Wei Sheng Yan Jiu 2005;34:234-7. [PubMed]
28. Fang WW, Wang KF, Zhou F, et al. Oolong tea of different years protects high-fat diet-fed mice against obesity by regulating lipid metabolism and modulating the gut microbiota. Food Funct 2023;14:2668-83. [Crossref] [PubMed]
29. Tung YC, Liang ZR, Yang MJ, et al. Oolong tea extract alleviates weight gain in high-fat diet-induced obese rats by regulating lipid metabolism and modulating gut microbiota. Food Funct 2022;13:2846-56. [Crossref] [PubMed]
30. Liu C, Guo Y, Sun L, et al. Six types of tea reduce high-fat-diet-induced fat accumulation in mice by increasing lipid metabolism and suppressing inflammation. Food Funct 2019;10:2061-74. [Crossref] [PubMed]
31. Bacher I, Goodrich M, Kimaina A, et al. FHIRing up OpenMRS: Architecture, Implementation and Real-World Use-Cases in Global Health. AMIA Jt Summits Transl Sci Proc 2024;2024:162-71. [PubMed]
32. Kasthurirathne SN, Mamlin B, Kumara H, et al. Enabling Better Interoperability for HealthCare: Lessons in Developing a Standards Based Application Programing Interface for Electronic Medical Record Systems. J Med Syst 2015;39:182. [Crossref] [PubMed]
33. Torab-Miandoab A, Samad-Soltani T, Jodati A, et al. A unified component-based data-driven framework to support interoperability in the healthcare systems. Heliyon 2024;10:e35036. [Crossref] [PubMed]
34. Marinelli S, Basile G, Zaami S. Telemedicine, Telepsychiatry and COVID-19 Pandemic: Future Prospects for Global Health. Healthcare (Basel) 2022;10:2085. [Crossref] [PubMed]
35. Gharibzahedi SMT, Barba FJ, Zhou J, et al. Electronic Sensor Technologies in Monitoring Quality of Tea: A Review. Biosensors (Basel) 2022;12:356. [Crossref] [PubMed]
36. Kim Mi-sook. study of designs for traditional tea maker. Ewha Womans University Graduate School of Design 1996. Available online: https://www.riss.kr/link?id=T934065
37. Ahn Byeong-tae. Study on Intelligent Coffee Shop Management System Based on Internet of Things. Journal of Convergence for Information Technology 2017:165-71. Available online: 10.22156/CS4SMB.2017.7.3.16510.22156/CS4SMB.2017.7.3.165
38. Lee J, Kwon KH. Development potential of dermatological artificial intelligence and U-healthcare: perceptions reported by middle-aged people in the Republic of Korea. J Med Artif Intell 2025;8:17. [Crossref]
39. Basile G, Accetta R, Marinelli S, et al. Traumatology: Adoption of the Sm@rtEven Application for the Remote Evaluation of Patients and Possible Medico-Legal Implications. J Clin Med 2022;11:3644. [Crossref] [PubMed]
40. F Danilevicz M, Bayer PE. Machine Learning for Image Analysis: Leaf Disease Segmentation. Methods Mol Biol 2022;2443:429-49. [Crossref] [PubMed]
41. Ito K, Honda H, Yoshida M, et al. A metallo-beta-lactamase producing Enterobacteriaceae outbreak from a contaminated tea dispenser at a children's hospital in Japan. Infect Control Hosp Epidemiol 2019;40:217-20. [PubMed]
42. Liu J, Nam Y, Choi D, et al. MXene/Hydrogel-based bioelectronic nose for the direct evaluation of food spoilage in both liquid and gas-phase environments. Biosens Bioelectron 2024;256:116260. [Crossref] [PubMed]
43. Zhang X, Wu H, Lin L, et al. The qualitative and quantitative assessment of xiaochaihu granules based on e-eye, e-nose, e-tongue and chemometrics. J Pharm Biomed Anal 2021;205:114298. [Crossref] [PubMed]
44. Calvini R, Pigani L. Toward the Development of Combined Artificial Sensing Systems for Food Quality Evaluation: A Review on the Application of Data Fusion of Electronic Noses, Electronic Tongues and Electronic Eyes. Sensors (Basel) 2022;22:577. [Crossref] [PubMed]
45. Lee J, Kwon KH. Sustainable Countermeasures for Skin Health Improvement for Green Consumers: The Utilization of Hsian-Tsao during Global Warming. Sustainability 2023;15:14619. [Crossref]
46. Global Oolong Tea Market by Type (Guangdong, Fujian), Application (Beverages, Functional Foods), Geographic Scope and Forecast. Verified Market Reports 2024, Available online: https://www.verifiedmarketreports.com/ko/product/oolong-tea-market/
47. Ng KW, Cao ZJ, Chen HB, et al. Oolong tea: A critical review of processing methods, chemical composition, health effects, and risk. Crit Rev Food Sci Nutr 2018;58:2957-80. [Crossref] [PubMed]
48. Wang Y, Li Q, Wang Q, et al. Simultaneous determination of seven bioactive components in Oolong tea Camellia sinensis: quality control by chemical composition and HPLC fingerprints. J Agric Food Chem 2012;60:256-60. [Crossref] [PubMed]
49. Zhu X, Gu S, Li J. How do gamified digital therapeutics work on obesity self-management? Metabol Open 2024;23:100314. [Crossref] [PubMed]
50. Riihimaa P. Impact of machine learning and feature selection on type 2 diabetes risk prediction. J Med Artif Intell 2020;3:10.
51. Xu Q, Wang L, Sansgiry SS, et al. A systematic literature review of predicting diabetic retinopathy, nephropathy and neuropathy in patients with type 1 diabetes using machine learning. J Med Artif Intell 2020;3:6.
52. Nuryunarsih D, Wahyuningsih HP, Rauf S, et al. Utilizing an apriori algorithm to examine attributes associated with hypertension and hypertension cardiovascular patients in Pakistan. J Med Artif Intell 2024;7:34. [Crossref]
53. Alskaf E, Crawley R, Scannell CM, et al. Hybrid artificial intelligence outcome prediction using features extraction from stress perfusion cardiac magnetic resonance images and electronic health records. J Med Artif Intell 2024;7:3. [PubMed]
54. Parsons O, Barlow NE, Baxter J, et al. Enabling scalable clinical interpretation of machine learning (ML)-based phenotypes using real world data. J Med Artif Intell 2023;6:2.
55. Huang AA, Huang SY. Quantification of the Effect of Vitamin E Intake on Depressive Symptoms in United States Adults Using Restricted Cubic Splines. Curr Dev Nutr 2023;7:100038. [PubMed]
56. Muenzner M, Tappenbeck N, Gembardt F, et al. Green tea reduces body fat via upregulation of neprilysin. Int J Obes (Lond) 2016;40:1850-5. [PubMed]
57. Heber D, Zhang Y, Yang J, et al. Green tea, black tea, and oolong tea polyphenols reduce visceral fat and inflammation in mice fed high-fat, high-sucrose obesogenic diets. J Nutr 2014;144:1385-93. [PubMed]
58. Yamashita Y, Wang L, Wang L, et al. Oolong, black and pu-erh tea suppresses adiposity in mice via activation of AMP-activated protein kinase. Food Funct 2014;5:2420-9. [PubMed]
59. Zhang S, Takano J, Murayama N, et al. Subacute Ingestion of Caffeine and Oolong Tea Increases Fat Oxidation without Affecting Energy Expenditure and Sleep Architecture: A Randomized, Placebo-Controlled, Double-Blinded Cross-Over Trial. Nutrients 2020;12:3671. [PubMed]
60. Huang AA, Huang SY. Increasing transparency in machine learning through bootstrap simulation and shapely additive explanations. PLoS One 2023;18:e0281922. [PubMed]
61. Patil AB, Bachute MR, Kotecha K. Artificial Perception of the Beverages: An in Depth Review of the Tea Sample. IEEE Access 2021;7:82761-85.
62. Xu M, Wang J, Zhu L. The qualitative and quantitative assessment of tea quality based on E-nose, E-tongue and E-eye combined with chemometrics. Food Chem 2019;289:482-9. [PubMed]
63. Chen M, Decary M. Artificial intelligence in healthcare: An essential guide for health leaders. Healthc Manage Forum 2020;33:10-8. [PubMed]
64. Eckhardt CM, Madjarova SJ, Williams RJ, et al. Unsupervised machine learning methods and emerging applications in healthcare. Knee Surg Sports Traumatol Arthrosc 2023;31:376-81. [PubMed]
65. Sato H. Yakugaku Zasshi 2022;142:337-40. [Development of Clinical Pharmaceutical Services via Artificial Intelligence Adaptation]. [PubMed]