Making nutrition and dietary choices are among the most critical aspects of daily life, and as such are subject to conflicting influences from research and media. Past research projects have focused on making recommendations for foods based on nutrient content, but the ability to apply these findings are limited by the lack of tools to visualize and interpret this information for the general public. For this reason, our group worked to tackle this issue at the Summer Intern Program Codeathon hosted by the National Institutes of Health (NIH). Our team developed an interactive dashboard using nutrition and Dietary Reference Intake information that was obtained from the United States Department of Agriculture. Using Streamlit, we produced a nutrition data visualization tool including three unique views. The Individual Foods view offers users the ability to see the nutrition content for a single food item, including macronutrients and 20 different micronutrients. The Comparison view allows for the selection of various foods and reports nutrient content of each item with color-coded charts for direct comparison. The Diet with Recommendations view allows users to select multiple foods common to their own diet and pick micronutrients of interest to create a personalized visualization of the data. Additionally, in this view users will receive three recommendations for foods that will improve the nutrient content of their diet. This initial model for interactive nutrient data visualization offers customizable views and individualized dietary recommendations. We hope to further refine our dashboard in the future to improve functionality and customization options including to 1) increase the number of foods and nutrients our dashboard can reference, 2) automate updating of data from USDA FDC, 3) include macronutrients within the Diet with Recommendations view, 4) include all age bracket options for dietary reference intakes, 5) include activity level and dietary limitation specific customizations 6) allow for custom serving sizes, and 7) pursue user testing and elicit feedback.

{"references": ["https://doi.org/10.22004/ag.econ.169648", "https://doi.org/10.1016/j.chb.2015.11.044", "http://dx.doi.org/10.1016/j.chb.2015.11.044", "http://dx.doi.org/10.1093/cdn/nzab044_027", "http://dx.doi.org/10.1371/journal.pone.0118697", "FoodData Central. https://fdc.nal.usda.gov/. Accessed August 12, 2021.", "Dietary reference intakes (DRIs): Estimated average requirements. https://www.nal.usda.gov/sites/default/files/fnic_uploads/recommended_intakes_individuals.pdf. Accessed August 12, 2021.", "Uncovering-the-Nutritional-Landscape-of-Food. Github https://github.com/STRIDES-Codes/Uncovering-the-Nutritional-Landscape-of-Food/releases/tag/v0.1. Accessed Sept 13, 2021.", "Streamlit: The fastest way to build and share data apps. https://streamlit.io/. Accessed August 12, 2021.", "Understanding the Landscape of Nutrition Dashboard. https://share.streamlit.io/tantar/uncovering-the-nutritional-landscape-of-food/main/UNLF.py. Accessed August 12, 2021."]}