Machine learning prediction models for nutrient profiles in food after processing
NARAVANE, T.; Tagkopoulos, I.
Show abstract
The future of personalized health relies on knowledge of dietary composition. The current analytical methods are impractical to scale up, and the computational methods are inadequate. We propose machine learning models to predict the nutritional profiles of cooked foods given the raw food composition and cooking method, for a variety of plant and animal-based foods. Our models (trained on USDAs SR dataset) were on average 31% better than baselines, based on RMSE metric, and particularly good for leafy green vegetables and various cuts of beef. We also identified and remedied a bias in the data caused by representation of composition per 100grams. The scaling methods are based on a process-invariant nutrient, and the scaled data improves prediction performance. Finally, we advocate for an integrated approach of data analysis and modeling when generating future composition data to make the task more efficient, less costly and apply for development of reliable models.
Matching journals
The top 8 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- A methodological framework for deriving the German food-based dietary guidelines 2024: food groups, nutrient goals, and objective functions 95%
- Nutritional analysis of commercially available, complete plant- and meat-based dry dog foods in the UK 93%
- Monitoring sodium content in packaged foods sold in the Americas and compliance with the Updated Regional Sodium Reduction Targets 92%
Similar papers in this journal
- Healthier decisions in the cued-attribute food choice paradigm have high test-retest reliability across five task repetitions over 14 days 92%
- Exploring Food Contents in Scientific Literature with FoodMine 92%
- Chemical and Sensory Analyses of Cultivated Pork Fat Tissue as a Flavor Enhancer for Meat Alternatives 90%
Similar papers in this journal
- The impact of the soluble protein fraction and kernel hardness on wheat flour starch digestibility 91%
- Effect of gastrointestinal alterations mimicking elderly conditions on in vitro digestion of meat and soy proteins 90%
- B vitamin quantification in lentil seed tissues using ultra-performance liquid chromatography-selected reaction monitoring mass spectrometry 90%
Similar papers in this journal
- Multi-Dimensional Machine Learning Approaches for Fruit Shape Recognition and Phenotyping in Strawberry 90%
- The FIP 1.0 Data Set: Highly Resolved Annotated Image Time Series of 4,000 Wheat Plots Grown in Six Years 89%
- MLcps: Machine Learning Cumulative Performance Score for classification problems 89%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.