Version 2 2025-10-05, 08:57Version 2 2025-10-05, 08:57
Version 1 2025-10-05, 08:55Version 1 2025-10-05, 08:55
dataset
posted on 2025-10-05, 08:57authored byLEI ZHAOLEI ZHAO, Ling Kang
<p dir="ltr">The increasing prevalence of diet-related chronic diseases worldwide highlights the need for a shift from generalized nutrition advice to personalized nutrition guidance. However, a significant challenge is the absence of large-scale, practical resources that can translate individual nutrient requirements into varied and realistic daily meal plans. To address this issue, we present a data descriptor for a database containing 215,135 daily meal plans tailored to diverse individual health profiles. This database was constructed using 23,152 adult individuals from the National Health and Nutrition Examination Survey (NHANES). For each individual, we derived personalized daily nutrient requirements based on their specific health status, accounting for nine prevalent health conditions. A multi-tiered computational pipeline incorporating direct matching, tensor-based querying, and a genetic algorithm was developed to generate meal plans that meet these nutrient requirements while adhering to dietary patterns. Validation confirms the meal plans are nutritionally adequate, health-oriented, and practically feasible. The complete database archived on Figshare (DOI:10.6084/m9.figshare.30153778), with generating code on GitHub, an interactive website, and APIs provided for broad access.</p><p dir="ltr">NHANES original data is uploaded to NHANES_raw_data folder for replay the data generation process only so it is not mandatory for usage.</p><p dir="ltr">For data regeneration, and web-based recommendation system, refer to GitHub: https://github.com/tyrone1979/DMP4P</p>