Thesis subject

Prediction of the degree of food processing using Artificial Intelligence (MSc)

Despite the accumulating evidence that increased consumption of ultra-processed food has adverse health implications, it remains difficult to decide what constitutes processed food. In this project, we will develop a machine-learning classifier that takes as input nutritional measures to predict the degree of processing of any food.

Short description

Unhealthy eating habits pose a significant risk for various diseases such as obesity, type 2 diabetes, coronary heart disease (CHD), and cancer. These conditions account for 70% of global mortality. Traditionally, individuals have relied on food category-based dietary recommendations such as the Food Pyramid or MyPlate, which outline the recommended proportions of fruits, vegetables, grains, dairy, and protein-based foods for a healthy diet. However, in recent years, an increasing number of research studies and dietary guidelines have emphasized the crucial role and distinct health effects of food processing. Observational studies, meta-analyses, and controlled metabolic studies suggest that dietary patterns centered around unprocessed foods offer greater protection against disease risks.
This topic focuses on leveraging the power of artificial intelligence (AI) to analyze and understand the relationship between dietary patterns, food processing, and the prevalence of non-communicable diseases. The study would involve utilizing AI techniques such as machine learning, natural language processing, and data mining to analyze a vast amount of existing research studies, clinical data, and dietary records. By employing AI algorithms, patterns and correlations can be identified between specific dietary patterns, the degree of food processing, and the occurrence of non-communicable diseases.

Objectives

To conduct a comprehensive literature review and data collection on existing studies related to dietary patterns, food processing, and non-communicable diseases.
To develop AI models that incorporates machine learning, natural language processing, and data mining techniques to analyze and extract relevant information from large datasets.
To identify patterns and correlations between dietary patterns, food processing levels, and the occurrence of non-communicable diseases using AI-based analysis.
To investigate the impact of dietary patterns and food processing on specific health outcomes such as obesity, type 2 diabetes, coronary heart disease, and cancer.

Tasks

The work in this master thesis entails:

Literature review: Conduct a review of existing research studies, meta-analyses, and dietary guidelines related to dietary patterns, food processing, and non-communicable diseases. This will provide a foundation of knowledge and identify research gaps.
Data collection and preparation: Gather relevant data, including dietary records, clinical data, and studies investigating the association between dietary patterns, food processing, and non-communicable diseases. Organize and preprocess the data for analysis.
AI models development: Design and develop an AI models that incorporates appropriate machine learning algorithms, natural language processing techniques, and data mining methods.
Results reporting and documentation: Prepare a comprehensive report summarizing the research methodology, results, and conclusions.

Literature

Menichetti, G., Ravandi, B., Mozaffarian, D. et al. Machine learning prediction of the degree of food processing. Nat Commun 14, 2312 (2023). https://doi.org/10.1038/s41467-023-37457-1

Requirements

Courses: Programming in Python (INF-22306), Data Science Concepts (INF-34306) or Machine Learning (FTE-35306)
Required skills/knowledge: Nutrition and health, Machine Learning

Key words: Artificial Intelligence, food and nutrition, nutrition and health

Contact person(s)

Dr. Yamine Bouzembrak (yamine.bouzembrak@wur.nl)
Prof. Bedir Tekinerdogan (bedir.tekinerdogan@wur.nl)