Reducing bias and enhancing equity in AI-enabled precision nutrition: addressing measurement error across wearables, multiomics, and dietary data.

Artificial intelligence (AI) can offer individualized dietary guidance based on multimodal data collected from various sources, including wearable sensors, high-dimensional multiomics and biomarker analyses, behavioral tracking, and self-reported dietary intake, enabling the emergence of precision nutrition. However, the predictive power and fairness of these models rely on the quality of the data inputs, and measurement errors in any of these underlying data streams can introduce systematic bias, degrade model performance, and disproportionately affect underserved populations. In this review, we examine the central role played by measurement error in AI-driven nutrition tools and evaluate statistical and machine learning approaches for mitigating the impacts of measurement error. We provide structured comparisons exploring both classical methods (e.g., regression calibration, Bayesian models) and emerging AI strategies (e.g., denoising autoencoders, multitask learning, uncertainty-aware deep learning) for correcting biased inputs. We also explore how uncorrected measurement error can perpetuate demographic biases, compromise efforts toward personalized medicine, and exacerbate equity gaps when models are deployed in real-world settings. Our review draws upon evidence across nutrition science, digital health, and algorithmic fairness. We propose a framework and offer actionable strategies for overcoming measurement error that can be implemented by researchers, developers, and regulators working at the intersection of data science and dietary health and seeking to build calibration-aware, inclusive precision nutrition systems.