0
Article ? AI-assigned paper type based on the abstract. Classification may not be perfect — flag errors using the feedback button. Tier 2 ? Original research — experimental, observational, or case-control study. Direct primary evidence. Sign in to save

Ensuring reliable feature importance in food chemistry AI

Food Chemistry 2026 Score: 50 ? 0–100 AI score estimating relevance to the microplastics field. Papers below 30 are filtered from public browse.
Yoshiyasu Takefuji

Summary

Researchers demonstrated that standard machine learning models applied to a microplastic-cancer dataset can produce misleading feature importance scores because they optimize prediction rather than causal inference, and proposed a validated pipeline combining nonparametric association tests and stability audits to improve the reliability of AI-driven risk assessment in food chemistry.

Food chemistry's rapid AI adoption (2060 AI articles; 415 in 2025) spans machine learning, logistic regression, random forests, and XGBoost. Yet a skills gap in supervised learning fuels misinterpretation: Models optimize prediction, not true associations, and feature importances lack ground-truth validation. High accuracy does not ensure reliable attributions; importances are model- and data-biased. Using a microplastic-cancer case, we show parametric logistic regression on nonlinear data distorts inference. We propose a standards-based pipeline: Unsupervised structure discovery (e.g., feature agglomeration, highly variable feature selection), nonparametric association tests (spearman with p-values), and explicit stability audits of rankings. This multifaceted approach mitigates label-driven bias, improves robustness, and aligns AI insights with mechanistic understanding, supporting credible risk assessment and safer application of AI in food chemistry.

Share this paper