The rise of artificial intelligence (AI) has permeated various aspects of our lives, and the field of nutrition and dietetics is no exception. Nowadays, virtually everyone uses the internet to search for information, and AI is increasingly being utilized in nutrition-related tools and applications. This article aims to explore the benefits and risks associated with using AI-powered diet plan generators.
Understanding AI in Nutrition
AI is an umbrella term encompassing various technologies that enable computers to perform cognitive tasks related to the human brain, specifically in learning and problem-solving. Machine learning (ML) and deep learning (DL) are subcategories of AI. ML involves algorithms that learn from data without explicit programming, while DL uses advanced methods through neural networks. AI is already influencing various aspects of our lives, from social media and online search engines to navigation and banking services.
Applications of AI in Nutrition and Dietetics
AI is being utilized in several ways in the field of nutrition and dietetics:
Nutrition Assessment
The first step in creating a nutrition care plan is a comprehensive nutrition assessment. AI-powered devices can assist in gathering dietary information, allowing for earlier treatment for patients in hospitals, rather than waiting long hours to be assessed by a dietitian. These devices can examine and distinguish results that need close observation, highlighting specific information and reminding patients to visit their practitioners for necessary treatment.
Nutrition Planning
AI can assist patients in need of a quick and easy nutrition plan tailored to their individual needs.
Read also: The Hoxsey Diet
Benefits of AI Diet Plan Generators
AI-based tools offer several advantages in the realm of nutrition and dietetics:
Accuracy in Dietary Assessments
AI-based tools can provide greater accuracy in dietary assessments, provided that the appropriate information is inputted into the system. Humans are prone to errors, and AI's ability to conduct dietary assessments rapidly and accurately can lead to more effective nutritional interventions in a shorter time.
Time Efficiency
AI can significantly reduce the time individuals spend browsing through numerous webpages to find answers. Chatbots, like ChatGPT, can generate succinct and easily understandable responses based on user input, providing quick answers to nutrition-related questions.
Accessibility
AI tools can be accessed anywhere, and many are available free of charge. Web browsers also utilize AI to enhance online information searches, offering a cost-effective way to access nutrition information.
Data Collection and Trend Identification
AI is a powerful tool for collecting data and identifying trends, which can be valuable for research and public health initiatives.
Read also: Walnut Keto Guide
Risks and Limitations of AI Diet Plan Generators
Despite the potential benefits, there are also risks and limitations associated with relying on AI for nutrition advice:
Lack of Patient-Centered Communication
AI systems cannot replicate the patient-centered communication methods employed by dietitians, such as motivational interviewing. They cannot determine what patients are feeling, which is crucial for developing effective and personalized nutrition plans.
Potential for Bias and Misinformation
AI-based tools can be susceptible to bias and misinformation due to gaps in data, outdated information, and social inequalities in data collection. Some AI systems integrated with other platforms may also introduce bias in the output of data.
Evolving Field of Nutrition
The field of nutrition and dietetics is constantly evolving, and AI systems may not always be up-to-date with the latest scientific findings. Individuals need individualized nutrition plans based on their dietary assessments and should consult with a dietitian who is currently updated with the right information.
Lack of Clinical Understanding, Personalization, and Accountability
The key difference between a dietician and AI lies in clinical understanding, personalization, and accountability. Dietitians assess lab reports, medical history, lifestyle habits, and emotional patterns before designing a diet. They track progress, adapt the plan weekly, and provide real-time support because nutrition is more than just calories; it’s connected to hormones, mindset, culture, and health conditions. ChatGPT, while helpful for general suggestions, lacks medical insight, can’t diagnose or adjust based on symptoms, and doesn’t take responsibility for your health outcomes.
Read also: Weight Loss with Low-FODMAP
Inability to Access Private Proprietary Lab Data
Organizations like Monash University and FODMAP Friendly Labs have private lab data databases on different foods’ FODMAP content. This is not accessible by AI, so AI-generated information about the FODMAP content of food may be inaccurate or outdated.
AI-Based Nutrition Recommendation Systems
To tackle challenges and encourage healthier eating habits, there has been a growing interest in developing nutrition recommendation systems, applications, and tools designed to offer personalized dietary guidance and recommendations to users. These applications leverage advances in technology, such as Artificial Intelligence (AI) and Machine Learning (ML), to analyze user data and preferences (e.g., dietary choices, cultural considerations) and deliver tailored recommendations for optimal nutrition and wellness.
Food and nutrition recommendation methods and systems can be broadly categorized into traditional food recommendation systems and AI-based nutrition recommendation systems.
Traditional Food Recommendation Systems
Traditional food recommendation systems utilize various techniques, including combinatorial optimization techniques (e.g., knapsack algorithm, integer and linear programming), content-based filtering, collaborative filtering, and hybrid approaches. Combinatorial analysis in meal planning optimizes food selection and meal sequencing by balancing nutritional requirements, cost efficiency, and user preferences. In contrast, content-based, collaborative and hybrid techniques focus on correlating food item attributes and/or user preferences to provide personalized suggestions.
Combinatorial optimization techniques, such as the knapsack algorithm, integer programming and constraint satisfaction problems, are used to generate meal plans by selecting optimal combinations of food items while ensuring dietary diversity, adherence to food group intake rules, and compliance with user preferences and restrictions.
Another combinatorial technique, such as linear programming (LP) in meal planning, formulates meal planning as an optimization problem where the objective is to either minimize cost or maximize nutrient intake while adhering to essential dietary guidelines, caloric requirements, and promoting food diversity.
Other traditional recommendation techniques, include content-based, collaborative-based, and hybrid methods. Content-based filtering focuses on finding food items that match the preferences of a user profile or are similar to items the user has interacted with previously. Collaborative filtering, on the other hand, relies on similarities between user profiles to generate food recommendations. By analyzing user behavior and preferences, collaborative filtering identifies users with similar preferences and recommends items that these similar users have enjoyed. Hybrid methods combine aspects of both content-based and collaborative filtering to produce more accurate and diverse recommendations.
AI-Based Nutrition Recommendation Systems
AI-based nutrition recommendation systems represent a shift towards generating recommendations that prioritize health and wellness considerations, offering personalized suggestions based on users’ preferences and nutritional requirements. These systems can be grouped into knowledge-based and ML-based systems.
In the realm of knowledge-based systems, the traditional recommendation approach can switch, for example, to a many-objective optimization (MaOO) approach, providing a more balanced way of recommending meals incorporating attributes such as user preferences, nutritional values, dietary diversity, and user diet patterns. Another example is the Meal Plan Generator (MPG) mechanism that can synthesize meals from foods. Considering many factors such as caloric intake, food preferences, variety, and compatibility, the MPG mechanism can provide users with meal proposals generated from a given set of foods. As recommendations become more complex, systems like the Protein AI-advisor can generate weekly meal plans according to each user’s profile and preferences, expert-validated rules, and food diversity criteria. Meals, already curated by nutritionists, are synthesized to create daily nutritional plans that closely align with users’ needs combined with rules.
On the other hand, machine learning-based systems leverage advanced algorithms and data analysis techniques to provide personalized recommendations by learning from user behavior, preferences, and contextual information. In one approach, the AI-based diet recommendation engine leverages a deep generative network to deliver daily personalize meal plans tailored to users’ needs.
Most of the existing approaches focus on specific factors such as the user profile and preferences, or caloric and macronutrient consumption. However, to produce even more personalized meal plans, an AI recommender should consider simultaneously various criteria. In particular, the mechanism takes into consideration user information such as allergies, preferences, and local cuisine to retrieve appropriate meals from an expert-validated database, featuring Mediterranean foods. Seasonality is used as an extra filter to select the right meals for the user. Subsequently, synthesis of all possible daily Nutrition Plans (NPs) is performed, and the algorithm sorts them according to the Daily Energy Requirement (DER) of the user and according to appropriate rules provided by expert nutritionists (knowledge base). DER is calculated from the physical characteristics of the user (sex, age, weight, height, Physical Activity Level or PAL).
Study: An AI-Based Nutrition Recommendation System
A study examined the feasibility and efficacy of nutrition recommendation systems. AI is now being leveraged to produce optimal meal plans based on user dietary choices and needs, including allergies, seasonality, cultural factors, and calorie needs.
A study presents an AINR designed to provide weekly meal plans based on the Mediterranean diet, either Spanish or Turkish. The results demonstrated 100% filtering accuracy for country, allergies, preferences, and seasonality. Milk and nut allergies prevented weekly planning, especially for Spanish users, due to limited database options. The AINR system "holds promise in facilitating more balanced dietary habits" but requires database improvements for allergies and Turkish male users.
AI-Powered Meal Planner
One system integrates semantic reasoning, fuzzy logic, heuristic search, and multicriteria analysis to produce flexible, optimized meal plans based on the user’s health concerns, nutrition needs, as well as food restrictions or constraints, along with other personal preferences.
Specifically, an ontology-based knowledge base was constructed to model knowledge about food and nutrition. Semantic rules were defined to represent dietary guidelines for different health concerns, and a fuzzy membership of food nutrition was built based on the experience of experts to handle vague and uncertain nutritional data. A semantic rule-based filtering mechanism was applied to filter out food that violate mandatory health guidelines and constraints, such as allergies and religion. A novel, heuristic search method was designed to identify the best meals among several candidates and evaluates them based on their fuzzy nutritional score. A mobile app prototype system was implemented and evaluated its effectiveness through a use case study and user study. The results showed that the system generated healthy and personalized meal plans that considered the user’s health concerns, optimized nutrition values, respected dietary restrictions and constraints, and met the user’s preferences.
The brain of the planner is a comprehensive food and nutrition knowledge graph. It is a visual representation of information and the relationships between various elements of food and nutrition. This includes information on food groups, nutrients, dietary recommendations, and the relationship between food consumption and health outcomes.
In addition to food and nutrition knowledge, a comprehensive user profile includes users’ biological, socioeconomic, and cultural characteristics and contextual situations that influence peoples’ food choices.
The first step in meal planning is to screen food ingredients that violate the user’s mandatory constraints, such as medical, allergy, cultural, and religious constraints. For example, if a user is allergic to peanuts, peanuts as an ingredient should be eliminated from meal ingredient lists. Alternatively, if a user is a vegetarian, animal products as ingredients must be eliminated.
Subsequently, rule-based food screening uses a set of predefined rules to evaluate the nutritional value of food choices and to make recommendations. For example, rules will be applied to evaluate a food based on its calorie content, fat content, and the presence of certain vitamins and minerals, and then a recommendation will be made based on those evaluations. The system may flag foods that are high in calories, unhealthy fats, or lack certain essential nutrients, and suggest healthier alternatives.
We used semantic rules, which are description logic in nature, to apply these dietary recommendations. We implemented a reasoner that uses forward chaining as the implementation strategy, which can be described logically as repeated applications of modus ponens.
Incorporating fuzzy membership into our planning system allows for more informed decisions regarding food choices and nutrient intake, considering the uncertainties and subjectivity inherent in food preferences, dietary restrictions, and health goals. Fuzzy logic, using linguistic variables such as “low,” “medium,” and “high” provides flexibility compared with strict binary decision rules, effectively capturing uncertainty and improving recommendation accuracy and personalization.
To produce the optimal intake of nutrients in a meal, each nutrient has a fuzzy set in which the membership value should achieve its maximum value (µ=1).
To determine the best combination of meals for a day (breakfast, lunch, and dinner), we proposed a heuristic optimization algorithm that computes the optimal PV value. Many of these factors may conflict with one another. We proposed an MCDM approach to determine the best daily meals that a user likes.
Evaluating Chatbot-Generated Diet Plans
A study evaluated the capabilities of three popular chatbots-Gemini, Microsoft Copilot, and ChatGPT 4.0-in designing weight-loss diet plans across varying caloric levels and genders.
The Diet Quality Index-International (DQI-I) was used to evaluate the plans across dimensions of variety, adequacy, moderation, and balance. Caloric accuracy was analysed by calculating percentage deviations from requested targets and categorising discrepancies into defined ranges.
All chatbots achieved high total DQI-I scores (DQI-I > 70), demonstrating satisfactory overall diet quality. However, balance sub-scores related to macronutrient and fatty acid distributions were consistently the lowest, showing a critical limitation in AI algorithms. ChatGPT 4.0 exhibited the highest precision in caloric adherence, while Gemini showed greater variability, with over 50% of its diet plans deviating from the target by more than 20%.
The study aimed to evaluate the capabilities of various chatbots in generating weight loss diet plans across different calorie levels, focusing on their accuracy in meeting caloric targets and the nutritional quality of the proposed diets, with findings highlighting their overall effectiveness and limitations as assessed using the DQI-I.
Despite achieving relatively high total DQI-I scores across all chatbots, the sub-scores reveal critical areas requiring improvement. The balance subscale, which evaluates macronutrient and fatty acid ratios, consistently received the lowest scores. Notably, while no significant differences were observed among the chatbots for total or subscale DQI-I scores (p > 0.05), distinct trends in meeting specific dietary requirements emerged, with ChatGPT 4.0 demonstrating the highest precision in caloric adherence.
This study is the first to quantitatively assess chatbot-generated diets using the DQI-I, providing a validated and standardised measure of diet quality. Previous research has primarily relied on qualitative assessments, comparing AI-generated diets to those developed by dietitians through subjective evaluations.
The Role of AI in Personalized Nutrition Advice
AI nutrition apps and platforms are designed to give you personalized diet advice based on specific inputs like your age, weight, sex, activity level, and health goals. They use large databases and machine learning algorithms to analyze food choices, calculate nutritional intake, and offer recommendations on what to eat to meet your goals. AI nutrition tools promise personalized, data-driven advice in the palm of your hand.
Two types of AI technology that are becoming increasingly popular in nutrition apps are photo recognition and conversational AI.
Photo recognition enables computers to understand images using advanced algorithms and deep learning. They can automatically tell the difference between foods, estimate portions, and predict which ingredients were used to make the meal.
Conversational AI is a type of AI that simulates human conversations. It uses natural language processing, a field of AI that enables computers to understand and process human language.
Benefits of AI Nutrition Advice
There are several advantages to using AI tools for nutrition guidance:
- Personalization. AI tailors its recommendations to your needs based on your inputs (like age and health goals), making it more relevant than one-size-fits-all dietary advice.
- Convenience. AI nutrition apps are available 24/7 and offer instant feedback to help you make informed decisions in real-time.
- Data-Driven Recommendations. AI can process huge amounts of data to deliver evidence-based recommendations, potentially making it more accurate than general health tips.
- Trackable Progress. Many AI nutrition tools allow you to track your progress over time, offering detailed insights into nutrient intake, macronutrient distribution, and more.
- Accessibility. AI nutrition tools provide a lower-cost and more accessible way to get personalized nutrition recommendations.
Limitations of AI in Nutrition
However, while AI nutrition tools have some benefits, it’s important to be aware of their significant limitations.
- Lack of Human Touch. AI can’t fully understand factors like emotional eating, cultural preferences, or the psychological aspects of food that a human dietitian can. Taking these factors into account is critical for long-term success and behaviour change. AI nutrition tools don’t provide the human touch needed to motivate people and keep them accountable for their goals.
- Generalized Algorithms. Although AI systems use large sets of data, they may not account for specific health conditions, genetic factors, or unique nutritional needs.
- Potential for Misinformation: AI’s accuracy is only as good as the data it uses to provide information. If an app uses outdated or incorrect data, it can offer advice that’s not ideal for your specific needs.
- Oversimplification: Human metabolism is extremely complex, and AI might oversimplify certain dietary recommendations, leading to less-than-ideal results. It often struggles to offer personalized advice for people with chronic health conditions, providing generic guidelines that may not be suitable for specific health conditions like IBS.
- Potential for Misinterpretation. People using AI nutrition tools may misinterpret the advice they’re given due to unclear instructions or lack of context. This can lead to unintended consequences like nutrient deficiencies or overconsumption of certain foods.
- Privacy and Data Security Concerns. Many AI nutrition tools require you to input personal information like weight, health history, and food preferences. This raises concerns about how securely that data is stored and used.
AI Nutrition Advice for Irritable Bowel Syndrome (IBS)
AI nutrition tools often fall short for people with chronic health conditions like IBS. While AI can help with basic nutrition advice, it cannot provide the personalized care that someone with IBS needs. Each person’s IBS triggers are unique, and managing flare-ups often requires more than following general guidelines.