Machine learning-driven flavoromics: Decoding stage-specific volatile compound dynamics and sensory deterioration in stored infant formula
Clinical Snapshot
PICO Framework
| P — Population | Infant formula products during storage |
| I — Intervention | Flavoromics analysis with machine learning modeling |
| C — Comparator | Different storage stages and formula types |
| O — Outcomes | Sensory deterioration, volatile compound profiles, fatty acid degradation, predictive model accuracy |
Bottom Line
This analytical study demonstrates that machine learning models can accurately predict sensory deterioration in stored infant formula using just six volatile compounds linked to lipid oxidation. The research identifies aldehydes and ketones as key off-flavor markers, with polyunsaturated fatty acid degradation as the primary mechanism. While the strong model performance (R² > 0.85) suggests practical utility for quality control, the study's limitations include unclear sample representativeness and limited methodological details. The findings could enhance infant formula shelf-life optimization and quality assurance, particularly relevant for Australian manufacturers subject to strict TGA regulations. However, validation in diverse storage conditions and formula types would strengthen the evidence base before widespread implementation.
Key Findings
P Value: Not reported in abstract
Effect Size: R² > 0.85 for Random Forest and XGBoost models
Primary Outcome: Stage-specific sensory deterioration prediction using volatile compound profiles
Nnt Or Sensitivity: Six lipid-oxidation-derived volatiles sufficient for accurate prediction
Confidence Interval: Not reported in abstract
Clinical Application
Requires specialized analytical equipment and expertise in volatile compound analysis Relevant to TGA food safety regulations and ACCC consumer protection standards for infant formula quality Infant formula manufacturers, quality control laboratories, regulatory bodies
Abstract
Infant formula (IF) is a vital nutritional source for infants. However, its sensory quality deteriorates during prolonged storage, impacting consumer acceptance. This study investigated the stage-specific sensory deterioration mechanisms and the predictive modeling of IFs during storage by integrating flavoromics, fatty acid dynamics, and machine learning. Quantitative descriptive analysis identified six key attributes driving quality loss, with one-stage IF showing the earliest and most pronounced decline. Volatile compound profiling revealed aldehydes (hexanal, octanal) and ketones as dominant off-flavor markers, correlating with lipid oxidation pathways. Fatty acid analysis showed the degradation of polyunsaturated fatty acids, particularly linoleic and α-linolenic acid, as key drivers of off-flavor generation. Using only six lipid-oxidation-derived volatiles, Random Forest and XGBoost models accurately predicted stage-specific sensory scores (with R2 > 0.85), directly linking fatty acid oxidation to flavor deterioration. This work establishes lipid oxidation as predominant degradation mechanism and provides practical, data-driven tool for shelf-life optimization.
References
- 1.Wang, J., Yang, M., Xi, Y., Wang, W., Zhao, L., Xue, S., Su, Y., Sun, B., & Ai, N. (2026). Machine learning-driven flavoromics: Decoding stage-specific volatile compound dynamics and sensory deterioration in stored infant formula. Food Chemistry, 148532. https://doi.org/10.1016/j.foodchem.2026.148532
This content is for educational purposes for healthcare professionals only and does not constitute clinical advice. Clinical decisions should be based on individual patient assessment, current guidelines, and appropriate specialist consultation. Editorial Standards · Privacy Policy · Terms of Service