CP-BayesNE: Uncertainty-Aware Personalized Nutrient-Density Estimation from Food Images Using Conformal Prediction and Prior-Corrected Dietary Adaptation
4 affiliations
- 1Graduate School of Engineering, Kobe University, 1-1 Rokkodai-cho, Nada-ku, Kobe 657-8501, Japan
- 2Graduate School of Medicine, Kobe University, 7-10-2 Tomogaoka, Suma-ku, Kobe 654-0142, Japan
- 3School of Gerontology and Long-Term Care, Taipei Medical University, No. 250, Wuxing St., Taipei 11031, Taiwan
- 4Center for Mathematical and Data Sciences, Kobe University, 1-1 Rokkodai-cho, Nada-ku, Kobe 657-8501, Japan
Abstract
Background/Objectives: Reliable longitudinal dietary assessment is a prerequisite for precision nutrition, important for studying nutrition-related changes in health and physical function, but conventional dietary recording can impose substantial user burden. AI-driven, food-image-based assessment can reduce this burden, although uncertainty in food recognition and inter-individual dietary differences may propagate to nutrient estimation. Methods:We developed CP-BayesNE, an uncertainty-aware framework that combines temperature-scaled food classification, conformal candidate sets, training-prior-corrected dietary-history personalization, and posterior-weighted nutrient estimation to support AI-driven personalized nutrition. Results: EfficientNetV2-S achieved 78.01% Top-1 and 93.67% Top-5 accuracy, while temperature scaling reduced expected calibration error from 0.11238 to 0.04345. At α=0.10, regularized adaptive prediction sets reduced the average candidate-set size from 80.78 to 5.77 while maintaining 94.32% empirical category coverage. In FoodLogAthl-218, prior-corrected personalization reduced nutrient density mean absolute error (MAE) by 4.0–6.6% across energy and macronutrients over 51 users. A single-participant 92-meal personal dataset provided preliminary end-to-end feasibility evidence, while also revealing limitations, including slightly worse fat MAE and conservative nutrient intervals. Conclusions: These findings support uncertainty-aware personalized dietary assessment while emphasizing that category-level conformal validity does not directly imply accurate true dietary intake.
Related
- High performance white blood cell classification using ensemble CNNs with Monte Carlo dropout and conformal prediction for clinical uncertainty quantification
- Uncertainty-Aware Multiscale Treatment Response Forecasting in Advanced Non-Small Cell Lung Cancer Using Residual-Variance Conformal Prediction
- Uncertainty-aware estimation of compressive strength for fly ash concrete with enhanced probabilistic prediction performance by incorporating the associated mortar strength
- Cardiovascular disease prediction using variational recurrent autoencoders with uncertainty estimation
- Personalized prediction of sequential therapeutic responses in HR+/HER2-low breast cancer using patient-derived organoids
BibTeX
@article{tong2026cpbayesne,
title = {{CP-BayesNE: Uncertainty-Aware Personalized Nutrient-Density Estimation from Food Images Using Conformal Prediction and Prior-Corrected Dietary Adaptation}},
author = {Zhaozhen Tong and Kumiko Ono and Shu-Chun Lee and Hsin-Yen Yen and Masahide Nakamura and Sinan Chen},
journal = {Nutrients},
year = {2026},
month = oct,
doi = {10.3390/nu18213567},
url = {https://www.mdpi.com/2072-6643/18/21/3567},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - CP-BayesNE: Uncertainty-Aware Personalized Nutrient-Density Estimation from Food Images Using Conformal Prediction and Prior-Corrected Dietary Adaptation
AU - Zhaozhen Tong
AU - Kumiko Ono
AU - Shu-Chun Lee
AU - Hsin-Yen Yen
AU - Masahide Nakamura
AU - Sinan Chen
PY - 2026
DA - 2026/10/28
JO - Nutrients
DO - 10.3390/nu18213567
UR - https://www.mdpi.com/2072-6643/18/21/3567
AB - Background/Objectives: Reliable longitudinal dietary assessment is a prerequisite for precision nutrition, important for studying nutrition-related changes in health and physical function, but conventional dietary recording can impose substantial user burden. AI-driven, food-image-based assessment can reduce this burden, although uncertainty in food recognition and inter-individual dietary differences may propagate to nutrient estimation. Methods:We developed CP-BayesNE, an uncertainty-aware framework that combines temperature-scaled food classification, conformal candidate sets, training-prior-corrected dietary-history personalization, and posterior-weighted nutrient estimation to support AI-driven personalized nutrition. Results: EfficientNetV2-S achieved 78.01% Top-1 and 93.67% Top-5 accuracy, while temperature scaling reduced expected calibration error from 0.11238 to 0.04345. At α=0.10, regularized adaptive prediction sets reduced the average candidate-set size from 80.78 to 5.77 while maintaining 94.32% empirical category coverage. In FoodLogAthl-218, prior-corrected personalization reduced nutrient density mean absolute error (MAE) by 4.0–6.6% across energy and macronutrients over 51 users. A single-participant 92-meal personal dataset provided preliminary end-to-end feasibility evidence, while also revealing limitations, including slightly worse fat MAE and conservative nutrient intervals. Conclusions: These findings support uncertainty-aware personalized dietary assessment while emphasizing that category-level conformal validity does not directly imply accurate true dietary intake.
SN - 2072-6643
ER -