APPLICATION OF AI AND MACHINE LEARNING TO ANALYZE PROTEIN CONTENT IN U.S. COMMERCIAL BABY FOODS

Area of Science:

• Pediatric Nutrition
• Nutritional Biochemistry
• Data Science in Health

Background:

• Proteins are vital macronutrients for children's growth, development, and tissue maintenance.
• Nutrient requirements are dynamic, influenced by age, weight, and physiological status, necessitating age-specific dietary planning.
• Diverse protein sources are crucial for meeting nutritional needs and fostering healthy eating habits.

Purpose of the Study:

• To analyze protein content in a dataset of 244 baby foods using artificial intelligence (AI) and machine learning.
• To categorize baby foods into low, moderate, and high protein content groups.
• To compare the protein content of baby foods with age-specific protein requirements for infants and toddlers.

Main Methods:

• Utilized artificial intelligence (AI) and machine learning techniques to analyze a nutritional dataset of 244 baby foods.
• Categorized foods into low (0.0-5.9 g/day), moderate (6.0-10.9 g/day), and high (11.0-15.0 g/day) protein groups.
• Assessed age-specific protein requirements (g/kg body weight) for infants and toddlers aged 0-3 years.

Main Results:

• The majority of analyzed baby foods (n=202) were categorized as low-protein.
• Fewer foods fell into the moderate (n=22) and high (n=20) protein categories.
• A significant portion of foods may not meet the protein needs of infants, especially those with reduced milk intake.

Conclusions:

• Findings highlight a potential gap between the protein content of many complementary baby foods and the recommended age-specific requirements.
• Low-protein foods may be inadequate for supporting optimal growth and cognitive development in infants.
• Emphasizes the critical need to align complementary food protein levels with established nutritional guidelines for early childhood.