Effectiveness of AI-Based Diet Plans in Developing

Health Awareness Among University Athletes

AProject Report
Submitted to the National University of Modern Languages
in partialfulfillment of requirements for the award of degree

Bachelor of Science
in
Health and Physical Education
by

Hamza Khalid
Enrollment: 21122

DEPARTMENT OF Health and Physical Education

26 December, 2025
 DECLARATION

I do hereby certify that the preliminary research report, which was made in part
submission of the requirements for awarding the degree. This assignment is a
reflection of my thoughts, and in cases where someone else has had ideas or words of
their own, I have correctly and sufficiently cited and referenced them. I also state
that I have stuck to the ethics of academic honesty and integrity, and I have not
misrepresented or fabricated any data or idea or fact, or source in my submission.

Hamza Khalid
Abstract

Application of artificial intelligence (AI) in health and fitness has exploded in recent
years, particularly when it comes to the production of tailored diets. This research
paper will look at the efficacy of AI-based diet plans in raising health awareness
among university athletes. Young athletes in university usually encounter the problems
of having balanced diets because of their tight schedules, insufficient education, and
knowledge of nutrition. Diet plans that are AI-driven will provide personalized
meal plans, depending on individual requirements, intensity of training, and health
objectives, which should help raise awareness regarding healthy eating habits.

This study examines the impact of AI-based diet apps on athletes and their
nutrition knowledge, food preferences, and theirresponsibility in terms of health. The
data were gathered by using surveys and observation based on the dietary
awareness change, meal planning behavior change, and motivation towards healthy
lifestyles. According to the findings, AI-driven nutritional plans have a good
role to play in raising health awareness by offering user-friendly, high-quality,
and customized nutritional information. Athletes were found to have a higher level
of understanding of nutrient consumption, portion size, and balanced diets.

The study concludes that AI-based diet planning systems could become an
effective method of promoting health awareness among university athletes. These
technologies can help achieve improved athletic performance and long-term health by
helping make informed dietary choices.

Keywords Artificial Intelligence (AI), AI-Based Diet Plans, Health Awareness,

University Athletes, Nutrition Management, Personalized Diet Planning

i
Acknowledgement

I take this opportunity to express my deepest sense of gratitude and sincere thanks to
everyone who helped me to complete this work successfully. I express my sincere
thanks to, Head of Department for providing me with all the necessary facilities and
support.

I would like to express my sincere gratitude to the Professors of my department

as well for their support and cooperation. Finally, Ithank my family and friends who
contributed to the successful fulfillment of this project’s preliminary work.

ii
Contents

Abstract i

Acknowledgement ii

List of Figures v

List of Tables vi

1 Introduction 1
1.1 Background and Rationale of the Study .............................................. 1
1.2 Research Problem .................................................................................... 2
1.3 Objectives and Hypotheses .................................................................... 2
1.3.1 Objectives of the Study .............................................................. 2
1.3.2 Hypotheses ................................................................................. 2
1.4 Significance of the Study ....................................................................... 2

2 Literature Review 4
2.1 Summary and Critique of Existing Research ........................................ 4
2.1.1 AI and Personalized Nutrition .................................................. 4
2.1.2 AI Diet Systems and Technology Innovations ......................... 5
2.1.3 Nutrition Apps and Digital Interventions ............................... 5
2.1.4 Limitations in AI Diet Research ............................................... 5
2.2 Research Gaps Identified ....................................................................... 6

3 Methodology 8
3.1 Research Design .................................................................................... 8

iii
 3.2 Population of the Study .......................................................................... 9
3.3 Sample and Sampling Technique ........................................................... 10
3.4 Data Collection Methods ....................................................................... 10
3.5 Research Tools ....................................................................................... 11
3.6 Research Procedure ................................................................................ 11
3.7 Data Analysis Methods .......................................................................... 11
3.8 Methodology Supported by Case Studies and Previous Research ...... 12
3.9 Ethical Considerations .......................................................................... 12

4 Results 13
4.1 Demographic Characteristics of Participants ........................................ 13
4.2 Health Awareness Before Using AI-Based Diet Plans ......................... 14
4.3 Perceived Benefits and Challenges of AI-Based Diet Plans ................ 15

5 Discussion 16
5.1 Future Directions .................................................................................... 17
5.2 Conclusion ............................................................................................. 18

References 19
5.3 Questioner ................................................................................................ 22

Health and Physical Education iv NUML

List of Figures

3.1 Research Design . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9

v
List of Tables

2.1 Comparison of Existing Research, Identified Gaps, and Contributions

of Current Study .................................................................................... 7

4.1 Demographic Characteristics of Participants ........................................ 13

4.2 Self-Reported Health Awareness Before AI Use by Gender ............... 14
4.3 Perceived Benefits and Challenges of AI-Based Diet Plans (n = 10) . . 15

vi
Chapter 1

Introduction

1.1 Background and Rationale of the Study

Artificial intelligence (AI) is another term used in recent years to refer to a significant
tool in health and fitness. Applications based on AI are very popular for offering
personalized diet, fitness, and health monitoring. They are used to analyze personal
information, including age, body composition, level of activity, and objectives to
provide personalized dietary plans (Ribeiro et al., 2020). Therefore, the AI-based
diet planning is becoming a promising approach to healthier lifestyle promotion.

The nutritional needs of university athletes are special because they train so
much, and they need their performance to be good. However, not all athletes
are knowledgeable enough about proper nutrition, the amount of food they eat, and
the timing of meals (Thomas, Erdman, and Burke, 2016). Poor dietary awareness is
also induced by the lack of professional dietitians and time. The gap can be
addressed through AI-based diet plans, which will provide accessible and
personalized nutrition advice at all times and locations.
The logic of this research is to investigate the effectiveness of AI-based diet plans
in building health awareness among university sportspeople. This relationship is
relevant to comprehend, as better health awareness will result in better food
choices, higher athletic performance, and long-term health. Although AI is
increasingly used in nutrition, the current studies on the topic have not paid much
attention to examining the effects of AI in health awareness in athletes at the
university level.
1
1.2 Research Problem
Even though AI-based diet planning systems are gaining momentum in popularity, the
evidence on their effectiveness in enhancing the health awareness of university
athletes is limited. A lot of athletes continue having issues with the knowledge of
nutritional needs and healthy eating patterns.

1.3 Objectives and Hypotheses

1.3.1 Objectives of the Study

The primary goals of the research are:

• To analyze the extent of health awareness of the university athletes on AI-based

diet plans.

• To examine how AI-based diet plans can enhance nutritional knowledge and
eating behavior.

• To assess the perception of athletes towards AI-based diet planning tools.

• To establish whether AI-generated diet plans can help in the healthier diet
choices of individuals.

1.3.2 Hypotheses

• H1: AI-based diets positively influence health awareness in athletes at the

university to a large extent.

• H0: There is no significant difference in the level of health awareness in AI-

based diet plans among university athletes.

1.4 Significance of the Study

This paper is noteworthy due to a number of reasons. First, it can advance academic
research by offering information on the role of AI to foster health awareness in the

Health and Physical Education 2 NUML

area of sports and nutrition. Second, the results can be used to make university
athletes aware of the benefits of using AI-based diets to enhance their eating habits
and health conditions.

Also, the study could be useful to coaches, sports administrators, and health
practitioners to incorporate AI-based nutrition tools in athletic programs. It can also
inform creators of AI health applications to create more effective and user-friendly
diet planning applications. Finally, the research contributes to a healthier lifestyle
and the enhanced performance of sportspeople in universities.

Health and Physical Education 3 NUML

Chapter 2

Literature Review

The field of nutrition and personalized health is changing with the assistance of
artificial intelligence (AI). Recent research indicates that AI-based diet and nutrition
systems can provide personalized recommendations, more precise dietary analysis,
and engagement in health management practices for users. Nevertheless, the majority
of studies have been conducted on the general populations or clinical settings (e.g.,
diabetes, obesity), rather than on a specifically athletic population or on how health
awareness is constructed in the case of university athletes. The review will provide a
summary of the major literature, critique the research available as well, and define the
gaps that have to be addressed by the current study.

2.1 Summary and Critique of Existing Research

2.1.1 AI and Personalized Nutrition

Studies indicate that AI technologies can be far more useful in the process of dietary
suggestions and personalization than the old ones. As an illustration, systematic
reviews demonstrate that AI-generated diets usually perform better than traditional
diets as they are customized to personal metabolic requirements and lifestyle informa-
tion, and clinical enhancements in most instances (e.g., metabolic outcomes, nutrient
adequacy) favor different population groups. ( Xi Wang, 2025) Nevertheless, as
the research that was analyzed by Panayotova (2025) also reveals the potential of
AI in

4
delivering individualized nutritional advice, it has limitations, including inconsistency
in practice, bias in algorithms, and difficulties in user compliance. The majority of the
research that is available is based on clinical or general health settings as opposed to
athlete-based settings.

2.1.2 AI Diet Systems and Technology Innovations

There are a number of technological advances that have been made recently that
reveal how AI is able to be used in nutrition tracking and recommendation. As an
example, to demonstrate the technical viability of AI-enhanced nutrition monitoring,
the multimodal data (e.g., sensors, mobile inputs) used by DietGlance and
MealMeter are used to estimate nutritional intake and offer personalized
recommendations ( Asiful Arefeen, 2025). These studies primarily point to
accuracy and technological innovation, yet they do not evaluate behavioral results
like modifications in health- related consciousness or long-term participation, in
particular among the athletes.

2.1.3 Nutrition Apps and Digital Interventions

Mobile apps are digital interventions that have been demonstrated to enhance nu trition
knowledge and behaviors in other groups of people, like athletes. MyFitnessPal was
a mobile application program that proved to be more effective than traditional sports
nutrition education (Digital Education, August 2025). Nevertheless, this study does
not directly engage AI algorithms in the planning of specific diets, leaving a gap in the
specific contribution of AI to awareness and behavior change.

2.1.4 Limitations in AI Diet Research

The available literature has identified the following major limitations in research on
artificial intelligence diet applications:

• Study Population - Most of the diet studies are focused on Healthy Lifestyle
and/or Managing Disease; less than 5% of diet studies examine the health or
nutrition of athletes.

Health and Physical Education 5 NUML

 • Outcomes Measured - Of the many artificial intelligence diet studies, less
than 10% examine health awareness as an outcome, with most examining
clinical/biochemical/metabolic endpoints.

• Limited Behavioral Insights - Very few studies integrating behavior change the-
ories, and/or evaluating psychological outcomes (i.e., motivation, and continued
awareness) in AI diet studies.

• Lack of Validating Real World Contexts and Long-Term Impact - Little to

saved data is available that studies the application of AI diet tools in a
longer-term real-world context, especially for university athlete populations.

2.2 Research Gaps Identified

Based on our literature review, it is clear that there are gaps in the current body
of literature. Specifically, this includes:

• Studies on how AI (Artificial Intelligence) programs affect health awareness

and understanding of an athlete’s dietary habits have yet to be conducted on
university-level athletes.

• Although most of the studies so far have provided limited information regarding

the effectiveness of an athlete’s health awareness and behavioral changes as a

result of an AI diet intervention, there are a number that have measured these
outcomes.

• Using AI-assisted diet plans versus using traditional diet guides in relation to
sports nutrition has not yet been thoroughly compared.

• There is inadequate support or analysis of the long-term impact of utilizing

AI-assisted diet plans on continual health, awareness of an athlete’s nutritional
habits, or behavioral changes resulting from following an AI diet.

Health and Physical Education 6 NUML

Table 2.1: Comparison of Existing Research, Identified Gaps, and Contributions of
Current Study

Author / Study Gaps Identified Current Study Con-

tribution
AI diet quality caloric accuracy across Examines the impact
chatbots (Kac¸ar et al., on health awareness,
2025). Focus on diet specifically among ath-
quality, but no athlete letes.
health awareness out-
comes.
Intelligent Diet Technology-focused, Adds behavioral and
Recommendation limited behavioural awareness measures in
System (2025) outcomes. the athletic context.
MyFitnessPal sports Not AI-based, and not Uses AI diet planning
nutrition study (2025) tailored diet planning. tools and compares
with traditional
education.
Systematic AI nutrition General nutrition con- Targets the university
review (Panayotova, text; lacks athlete fo- athlete population
2025) cus. specifically.
DietGlance and Meal- Technical innovation Measures health aware-
Meter (2025) with multimodal data; ness effects and dietary
no focus on health behavior changes.
awareness outcomes.

To briefly summarize, current studies have demonstrated that there are many
possibilities for using AI in developing personalized diet plans and enhancing the
dietary quality for individuals. However, the current literature does not contain any
studies specifically targeting athletes and addressing the issues of health awareness
and behavior modification. Therefore, an important aim of this research is to examine
how AI-based diet plans impact the health awareness of college/University athletes,
producing additional information about the educational and behavioral impacts of AI-
based diet plans, the type of studies missing from previously published literature.

Health and Physical Education 7 NUML

Chapter 3

Methodology

This chapter provides details on the study’s research design, including the research
population and sample, as well as information about the data collection methods,
instruments used to gather data as well and the procedures followed to collect and
analyze the data to meet the research goals. In addition, this chapter explains how
the methodology for conducting this type of study will provide trustworthy, authentic
results that are directly applicable to the study’s research objectives.

3.1 Research Design

In this research, the researchers used a qualitative research design. I
conducted semi-structured interviews to collect data. Qualitative research is
appropriate here, as it enables the researchers to gain deeper insight into the
athletes, including their experience with and perspectives on AI-assisted dietary
systems. Unlike quantitative studies that provide numeric data about an entire
population, qualitative data captures subjective perceptions, attitudes, and
behaviors, which form the basis of health awareness studies (Creswell, 2014). As
little prior research exists on health awareness and AI-assisted diets among
university athletes, this study utilizes an exploratory research design.

8
 Figure 3.1: Research Design

3.2 Population of the Study

Out of the participants included in this research project, they are all university athletic
participants who are current undergraduate or graduate students enrolled at a university
who compete in university collegiate athletic competition and who either currently

Health and Physical Education 9 NUML

use an AI diet/nutrition application or previously used an AI diet/nutrition application
before competing at a university.

3.3 Sample and Sampling Technique

Participants will be selected using the purposive sampling method to ensure that only
those athletes who can speak to the research topic will be recruited into the study. A
sample size of roughly 10-15 collegiate student-athletes will be included in this study.
The following criteria will be used when determining participant eligibility:

• Currently participating in collegiate athletics

• Have experience using an AI-based diet or nutrition app

• Be willing to engage in an interview

According to Etikan et al., purposive sampling is the best way to get specific
information from targeted participants in qualitative research.

3.4 Data Collection Methods

Through semi-structured interviews, primary data will be gathered, which allows for a
degree of flexibility for participants and ensures all relevant topics will be addressed.
Interviews will cover the following topics:

• How often do you follow the recommendations given by the AI-based diet plan?

• Before using an AI-based diet plan, how would you describe your knowledge of
healthy eating?

• After using the AI-based diet plan, do you feel your awareness about health and
nutrition has changed? Please explain.

• Do you now pay more attention to meal timing, portion size, or food quality?

• Do you feel more conscious or responsible about your food choices after using

the AI diet?

Health and Physical Education 10 NUML

Each interview will last approximately 2 0 – 3 0 minutes and will be conducted face- to-
face and online.

3.5 Research Tools

The main research tool would be an interview guide with open-ended questions. Other
tools include a smartphone on which interview audio is recorded.

3.6 Research Procedure

• Identify and recruit suitable participants

• Explain the purpose of the study and obtain informed consent

• Conduct semi-structured interviews

• Record and transcribe interviews

• Analyze data using thematic analysis

• Interpret results and link findings to research objectives

3.7 Data Analysis Methods

Data analysis will entail the use of thematic analysis. The process entails:

• Knowledge of the data

• Coding the key. responses

• Reading for Meaning - Identifying Themes and Patterns

• Applying Theme Analysis for Health Awareness and Usage of AI

Thematic analysis is a popular methodological approach that is applied extensively

in qualitative health-related research. This is because it is possible to systematically
uncover important patterns from the data given by the participants (Braun & Clarke,
2006).

Health and Physical Education 11 NUML

3.8 Methodology Supported by Case Studies and Pre-
vious Research

Previous research has employed a qualitative interview design to study nutrition

knowl- edge and technology adoption. For example, studies concerned with
digital health technology and nutrition education involve semi-structured interviews
(Dennison et al., 2013). Additionally, research in sports nutrition stresses the
importance of qualitative research to understand the experiences of athletes in
terms of their knowledge and development (Heaney et al., 2011). Through the
use of a similar methodology, the research presented here maintains a degree of
consistency with existing research methods, as it analyzes a special subject matter
and a new technology.

3.9 Ethical Considerations

Ethical considerations will be strictly followed: Participants will be informed about
the purpose of the study; confidentiality will be maintained, and participation will be
voluntary. No personal identifiers will be disclosed, and participants may withdraw at
any stage.

Health and Physical Education 12 NUML

Chapter 4

Results

The results of a study that looked at how well AI-based diet plans helped
college athletes become more health-conscious are presented in this section.
Descriptive numerical summaries from participant responses are used to support
the findings, which are based on qualitative interview data. Fifteen university athletes
from various sports disciplines took part in the study. To find trends in their
dietary habits, perceptions of AI-based diet systems, and nutritional awareness,
their answers were transcribed and examined.

4.1 Demographic Characteristics of Participants

Accurately interpreting the results requires an understanding of participant

demograph- ics. Male and female athletes from a range of age groups and athletic
backgrounds were among the participants. The majority of responders, who are
typical of university athletes, were between the ages of 18 and 30.

Table 4.1: Demographic Characteristics of Participants

Variable Category Frequency Percentage

Gender Male 5 50%
Female 5 50%
Age Group 18–20 years 3 30%
21–23 years 4 40%
24–26 years 3 30%
Sport Type Team sports 6 60%
Individual sports 4 40%

13
 The results are more credible due to the diversity in gender, age, and sport type,
which allows for the inclusion of perspectives from athletes with varying training
regimens and nutritional needs.

4.2 Health Awareness Before Using AI-Based Diet Plans

The research team conducted interviews with participants to ask them how aware they
were about their nutrition level and Health awareness before starting to use an AI-
Diet Plan. The analysis of the results revealed that most respondents had little to no
formal nutritional knowledge. Most of the athletes stated that they had some idea
of how their diet impacted their performance, but they were not clear on many of
the specifics regarding Nutrient balance, Caloric intake, or meal timing. The health

Table 4.2: Self-Reported Health Awareness Before AI Use by Gender

Health Awareness Level Male (n=5) Female (n=5) Total (n=10)

Low 2 (40%) 3 (60%) 5 (50%)
Moderate 2 (40%) 1 (20%) 3 (30%)
High 1 (20%) 1 (20%) 2 (20%)
Total 5 (100%) 5 (100%) 10 (100%)

awareness levels of university athletes were evaluated through a self-reported survey,

which compared male and female athletes before utilizing artificial intelligence-based
diet plans (AI). The data collected from 50% of the total survey sample indicated a low
level of health awareness due to a lack of knowledge concerning their understanding
of nutrition and maintaining a balanced diet, along with health-related decision-
making processes. Female athletes experienced this gap in health awareness more
than male athletes; 60% of females indicated they possessed low health awareness
compared to only 4 0 % of males. The overall sample also indicated that 3 0 % of
all athletes had a moderate health awareness; the males exhibited a higher
percentage of moderately aware (40%) versus that of females with a moderate health
awareness (20%). Twenty percent of athletes participating in the survey exhibited
strong health awareness before accessing AI-based diet plans; both males and females
exhibited this level at an equal rate (20% for each). From this data, we conclude
that, before implementing AI-based diet plans,the majority of university athletes had

Health and Physical Education 14 NUML

limited health awareness; this issue

Health and Physical Education 14 NUML

is particularly prevalent among female athletes; thus, there is a need for personalized
and structured nutritional guidance or support tools for the university sports industry.

4.3 Perceived Benefits and Challenges of AI-Based Diet

Plans
The participants cited multiple advantages of AI-based diets, especially personalized
recommendations and accessibility of the application. Athletes valued the specific
diet recommendations designed for them as part of an overall plan, which
incorporated their own individual goals and training schedules. Participants shared
some negative experiences, including no access to local produce; cost
limitations for premium

features. The following table provides a concise summary on how University Athletes

Table 4.3: Perceived Benefits and Challenges of AI-Based Diet Plans (n = 10)

Aspect Frequency Percentage

Personalized diet guidance 9 90%
Improved nutrition knowledge 8 80%
Better meal planning 7 70%
Lack of local food options 4 40%
Cost of premium features 3 30%

viewed both the positive aspects and the negative aspects of using an AI-Based Diet
Plan as a result of interviews conducted with five male and five female participants.
The overall response to AI-Based Diet Plans was a very positive one, but there are
some notable differences between the two groups’ views. In general, the vast majority
of the participants were able to identify at least one benefit associated with AI-based
diet Plans. Similarly, more than a few athletes indicated that AI-based diet Plans
helped them gain a better understanding of healthy eating options and a well-balanced
meal.

Health and Physical Education 15 NUML

Chapter 5

Discussion

The outcomes of this research indicate that utilizing Artificial Intelligence (AI)-based
diet plans assists university athletes in gaining an understanding and awareness of
healthy eating practices. An increase in Nutrition Knowledge and Dietary Behavior
was cited as being an important factor in the development of these new habits, and saw
the greatest amount of growth in relation to the research question. The results suggest
that AI tools function not only as a method of developing an eating plan, but also as a
method for improving the way in which one develops a knowledge of what it means to
eat well.

The increase in health awareness is consistent with other studies that have shown
that personalized diet plans based on artificial intelligence improve user experience
and education. Ribeiro et al (2020) suggested that a user who receives personalized
AI-generated meal recommendations is more likely to participate in their dietary
management than a user who does not. Panayotova ( 2 0 2 5 ) supports these findings
by showing the ways in which consumers can be encouraged to be proactive in the
management of their diet and how their experiences with AI-based systems can have
a significant impact on the way they have developed their eating habits. However, this
research focused on a particular population of users, as university athletes are often
a neglected area in the current literature regarding AI-based personalized nutrition.
The research findings support the need for still more customized technology-based
solutions to digitized health products. Through customized recommendation models,
athletes can utilize nutritional information to accomplish their goals by transforming

16
what seems to be an overwhelming amount of information into something simple,
attractive, and useful. This greatly increased motivation to adhere to nutritional plans.

Conceptually, this supports behavioral change theories that stress tailored feedback
and self-powered measures as the main mechanisms for increasing individual aware-
ness and behavior modification.

As positive as the results were, there were limitations to the study. For example, the
limited sample size limits the extent to which results can be generalized to the broader
population; and although the data was collected via self-reported measures, it is also
subject to potential bias (e.g., people over-reporting food consumed, under-reporting
food consumed)/. Also, because the study focused on the short-term experience of
using artificial intelligence to provide a diet plan, it will not help determine how long
these changes may remain in effect. Thus, further studies utilizing larger sample sizes
and longer-term study designs are warranted.

5.1 Future Directions

The results of this review indicate that there is a growing need and desire for
continued research into the impact of AI diet programs, as well as the impact
of AI diet programs on increasing health awareness and improving the dietary
behavior of athletes. Future research studies should recruit participants across all
sports disciplines, universities, and backgrounds, as well as across genders. These
participants should be representative samples of larger, more diverse groups that will
allow for an overall increase in the generalisability of the results. Longitudinal study
designs will allow researchers to follow participants over time to evaluate the long-
term impact of AI diet programs on health awareness, dietary behavior, and athletic
performance. Researchers should also compare AI diet plans to traditional dietitian-led
diet programs to identify the relative strengths and weaknesses of both. Additionally,
there is an opportunity for researchers to conduct more research to better understand

the integration of AI diet systems with fitness wearables (e.g., smartwatches, activity
trackers) to further personalise nutrition advice and improve health outcomes for
athletes through the use of real-time data.

Health and Physical Education 17 NUML

5.2 Conclusion
This research examined how AI diet methods may positively affect the way university
student athletes become educated about their health. The data that was collected shows
that the use of AI diet methods was proven to increase the diet knowledge of athletes,
create greater awareness of dietary practices for athletes, and have a positive effect on
how many athletes changed their dietary habits. As a result, athletes who used
these methods had greater nutritional knowledge and were more likely to continue
to eat healthier in the future.

In conclusion, AI diet methods may be an important supplemental resource for

positively supporting athletes’ health education on the collegiate level, but should
always be accompanied by professional nutrition education. More re search needs to be
completed regarding the long-term effects of AI diet methods, the ability to
incorporate the methods into a wider range of populations, and the integration of AI
diet methods with wearablesused for fitness. By providing meaningful information
about how AI is being used in the world of sports nutrition, this research sheds light
on how AI can help athletes live healthier lives.

Health and Physical Education 18 NUML

References

[1] Ribeiro, J., Lima, R., Eckhardt, T., & Paiva, S. (2020). Artificial intelligence
and personalized nutrition: A systematic review. Nutrition Reviews, 78(12),
1012–1024. [Link]

[2] Thomas, D. T., Erdman, K. A., & Burke, L. M. (2016). Position of the Academy
of Nutrition and Dietetics, Dietitians of Canada, and the American College of
Sports Medicine: Nutrition and athletic performance. Journal of the Academy
of Nutrition and Dietetics, 116(3), 501–528. [Link] .
jand .2015 . 12 .006

[3] West, D., & Allen,J. (2018). How artificial intelligence is transforming the health
care sector. Brookings Institution Report, 1–12.

[4] Burke, L.M., Hawley, J.A., Wong, S.H.S. and Jeukendrup, A.E. (2011)
‘Carbohydrates for training and competition’, Journal of Sports Sciences, 29(S1),
pp. S17–S27.

[5] Panayotova, G.G. (2025) ‘Artificial intelligence in nutrition and dietetics: A

comprehensive review’, Healthcare, 13(12), pp. 1–18. Available at: https:
//[Link] (Accessed: 20 December 2025).

[6] Ribeiro, J., Lima, R., Eckhardt, T. and Paiva, S. (2020) ‘Artificial intelligence
and personalized nutrition: A systematic review’, Nutrition Reviews, 78(12), pp.

1012–1024.

[7] Thomas, D.T., Erdman, K.A., and Burke, L.M. (2016) ‘Position of the Academy
of Nutrition and Dietetics, Dietitians of Canada, and the American College of

19
 Sports Medicine: Nutrition and athletic performance’, Journal of the Academy
of Nutrition and Dietetics, 116(3), pp. 501–528.

[8] West, D.M. and Allen, J.R. (2018). How artificial intelligence is transforming
health care. Washington, DC: Brookings Institution.
¨
[9] Kac¸ar, H.K., Kac¸ar, O.F. and Avery, A. (2025) ‘Diet quality and caloric accuracy
in AI-generated diet plans across chatbots’,Nutrients, 17(2), pp. 206–220.

[10] Gunby, P., Jin,Y. and Reed,W.R. (2017) ‘Did FDI really cause Chinese
economic growth? A meta-analysis’, World Development, 90, pp. 242–255.

[11] Vacaflores, D.E. and Mogab, J.W. (2020) ‘Does foreign direct investment really
affect employment in host countries? Subsidiary-level evidence’, Journal of
International Business Studies, 51(7), pp. 1215–1239.

[12] Braun, V. and Clarke, V. (2006) ‘Using thematic analysis in psychology’,

Qualitative Research in Psychology, 3(2), pp. 77–101.

[13] Creswell, J.W. (2014) Research design: Qualitative, quantitative, and mixed
methods approaches. 4th edn. Thousand Oaks, CA: Sage.

[14] Dennison, L., Morrison, L., Conway, G. and Yardley, L. (2013)

‘Opportunities and challenges for smartphone applications in supporting
health behavior change’, British Journal of Health Psychology, 18(4), pp. 747–
760.

[15] Etikan, I., Musa, S.A. and Alkassim, R.S. (2016) ‘Comparison of
convenience sampling and purposive sampling’, American Journal of Theoretical
and Applied Statistics, 5(1), pp. 1–4.

[16] Heaney, S., O’Connor, H., Michael, S., Gifford, J. and Naughton, G. (2011)
‘Nutrition knowledge in athletes: A systematic review’, International Journal of
Sport Nutrition and Exercise Metabolism, 21(3), pp. 248–261.

[17] Creswell, J.W. (2014) Research design: Qualitative, quantitative, and mixed
methods approaches. 4th edn. Thousand Oaks, CA: Sage.

Health and Physical Education 20 NUML

[18] Dennison, L., Morrison, L., Conway, G. and Yardley, L. (2013)
‘Opportunities and challenges for smartphone applications in supporting
health behavior change’, British Journal of Health Psychology, 18(4), pp. 747–
760.

[19] Heaney, S., O’Connor, H., Michael, S., Gifford, J. and Naughton, G. (2011)
‘Nutrition knowledge in athletes: A systematic review’, International Journal of
Sport Nutrition and Exercise Metabolism, 21(3), pp. 248–261.

[20] Ribeiro, J., Lima, R., Eckhardt, T. and Paiva, S. (2020) ‘Artificial intelligence
and personalized nutrition: A systematic review’, Nutrition Reviews, 78(12), pp.

1012–1024.

Health and Physical Education 21 NUML

Appendix

5.3 Questioner
1. What is your age, gender, and sport at university?

2. How long have you been involved in university-level sports?

3. Have you ever used an AI-based diet plan or nutrition app? If yes, for how long?

4. How often do you follow the recommendations given by the AI-based diet plan?

5. Before using an AI-based diet plan, how would you describe your knowledge
of healthy eating?

6. What did a “healthy diet” mean to you before using AI-based nutrition guidance?

7. After using the AI-based diet plan, do you feel your awareness about health
and nutrition has changed? Please explain.

8. Has the AI-based diet helped you understand nutrients such as protein, carbohy-
drates,fats, or hydration better?

9. Do you now pay more attention to meal timing, portion size, or food quality?

10. Has using an AI-based diet plan changed your daily eating habits?

11. Do you feel more conscious or responsible about your food choices after using
the AI diet?

12. Can you share one example where the AI-based diet influenced a
healthier decision?

22
 13. How does AI-based diet advice differ from guidance given by coaches, trainers,
or family?

14. Which source do you trust more for nutrition awareness: AI-based diet plans
or traditional advice? Why?

15. Overall, do you think AI-based diet plans are effective in improving
health awareness among university athletes? Why or why not?

Health and Physical Education 23 NUML