Transparent Nutrition: An Explainable AI-based Diet Tracking System for Preventing Nutrition-Related Disorders
Bibliographic record
Abstract
The growing incidence of nutrition-related diseases, including obesity, diabetes mellitus, iron-deficiency anemia, and cardiovascular disease, calls for an accurate, personalized, and transparent dietary monitoring tool. Where past diet tracking apps are the product of user input or general food data, they often fall short of providing the requisite intelligence or explainability to accurately assess nutrient content and health high-risk status. Herein we present an Explainable AI (XAI) based diet tracking system that uses deep learning for automated food recognition, and machine learning for and nutrient estimation and interpretable models to assess the health risks of potential dietary imbalances. Given a food image, the system identifies consumed food items, measures key nutrients (such as calories, sugar, and iron) and identifies an imbalance in nutrient consumption that may cause or worsen nutrition-related disease. To enhance trust and transparency, we use SHapley Additive Explanations (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME) to showcase how much each piece of dietary information contributed to nutrient limits and health predictions. Results from experiments on the Food-101 dataset and nutrition databases demonstrate our system’s ability to deliver reliable, real-time, and explainable dietary feedback, leveraging XAI for meaningful preventive health taking into consideration user and clinician health implications.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.006 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".