The Study
Using machine learning models to predict the quality of plant-based foods
This study is like teaching a computer to guess a food's health score based on its ingredients — it learned patterns from a list of foods, but didn't test if those foods actually made people healthier. So we can say it's good at predicting scores, but not that it makes food better or changes how people eat.
Analysis score
Maximum 0 for a computational/algorithm study.
Where the score came from
Scientists taught computers to read the nutrition info on plant-based foods and guess their health score (Nutri-Score) using just the numbers for fats, vitamins, and other nutrients.
Where does this study sit?
Reviews of RCTs (Meta-analyses)
Max 100Randomized Trials
Max 90Reviews of Cohort Studies
Max 85Cohort Studies
Max 72Reviews of Case-Control Studies
Max 63Case-Control Studies
Max 58Cross-Sectional & Case Series
Max 50Expert Opinion
Max 50 / 100
Quality score
Based on clinical experience or non-systematic literature reviews. The lowest level of evidence as they are most susceptible to bias and personal perspective.
Key takeaways
Summary
Based on the study abstract and findings.
- 1Yes — this means a phone app could quickly tell you if your plant-based snack is truly healthy, even if the label is confusing.
- 2The computer got the health score right 88% of the time, and predicted the exact Nutri-Score number with 96% accuracy.
- 3Two-thirds of plant-based foods in the study got the best scores (A or B).
Score breakdown, methodology, conflicts of interest, evidence analysis & raw study data
Publication
Journal
Current Research in Food Science
Year
2023
Authors
Christabel Y E Tachie, N. A. Tawiah, Alberta N. A. Aryee
Related Content
Claims (6)
Nutrient scoring systems assign higher health scores to plant-based foods than to animal-based foods.
Plant-based foods with higher total fat content receive lower Nutri-Score ratings (D–E), because the Nutri-Score system assigns negative points for saturated fat.
Adding micronutrient information to the Nutri-Score algorithm improves its ability to predict food healthiness without reducing its accuracy compared to using only macronutrient data.
Machine learning models using nutrient data from U.S. dietary surveys accurately predict Nutri-Score grades and numerical values for plant-based foods.
In U.S. dietary surveys, about two-thirds of plant-based foods received the top two Nutri-Score ratings, indicating they are classified as nutritionally favorable.
Machine learning models using only nutrient data from plant-based foods can accurately calculate Nutri-Score values, explaining 96% of the variation in those scores.
Not medical advice. For informational purposes only. Always consult a qualified healthcare professional before making health decisions.