Delta Division


Nutrimenta was inspired by the need for an accessible and informative nutrition-focused health application in the wake of the U.S. nutrition crisis. Proper nutrition plays a profound role in maintaining a healthy body and preventing diet-based disease. Poor nutrition and unhealthy eating patterns can lead to higher risks for micronutrient deficiencies and diet-based illnesses, including cardiovascular disease, osteoporosis, hypertension, cancer, and diabetes. The U.S. faces an alarming nutrition crisis that is impacting the health of millions of Americans. According to a study performed at the NIH, “nearly one third of the US population aged over 9 years is at risk of a deficiency in at least one vitamin, or has anemia”. According to the Centers for Disease Control and Prevention, “Heart disease remains the leading cause of death among men and women in the United States and accounts for 1 in 4 deaths nationwide”. Looking through the complex nutrition facts and ingredients to see if a meal is nutritious and right for a person can be inconvenient and confusing. The Nutrimenta website application performs this analysis and allows the user to make the best eating decisions, enabling better nutrition and better health.

What it does

Nutrimenta is a website application that empowers its users to create healthy meals and improve their lifestyle through nutrition.

Nutrimenta allows the user to log in and collects all their diet-related info (allergies, food intolerances, dietary restrictions, etc) to store on their personal profile. From there, the user can search for a portion of food and view its full nutritional information. The personalized log-in system allows for a machine-learning algorithm to be implemented in order to predict the user’s eating patterns over time and model long-term health effects using the user’s data, such as age, gender, and macronutrient and micronutrient values. This enables the user to better understand their nutrition patterns and to ingest all-inclusive meals that will maintain good health and decrease risks for diet-based diseases.

Nutrimenta also contains a Plate Guide, which visualizes the United States MyPlate guidelines for the core food groups: fruit, vegetables, grains, protein, and dairy. The user may select a food group and then click on the “Generate Serving Suggestion” button to receive a randomly generated serving recommendation. This enables the user to gain insight into what essential food groups they should include and also examples for these food group portions.

How we built it

We produced our UI design in Figma. For the front-end, we utilized the Bootstrap network, along with HTML/CSS/Javascript. For the pie charts, we used the ApexCharts package. For the back-end, we utilized Nutritionix API for external data, Firebase for the sign-in authorization and user data, and planned to use Pytorch to create a deep learning model with the goal of predicting whether the food is healthy for the user to eat and what the long-term effects can be based on their age, gender, pre-existing conditions, nutritional content, and prior eating patterns.

Challenges we ran into

We faced some challenges connecting data from the Nutritionix API and implementing the ApexChart Javascript/React.js package. We were able to overcome these and successfully implement them into our website application.

Accomplishments that we're proud of

We are most proud of our web application’s UI design and back-end development (implementing the Nutritionix API). We were able to work together in an efficient manner and complete nearly the entirety of our project plan.

What we learned

We were able to experience the design process from beginning to end. We learned how to utilize front-end and back-end tools for our project, including Bootstrap, React.js, Firebase, etc.

What's next for Nutrimenta

Our next steps are to implement our prospective Machine Learning model as described above. Individuals will vary in their nutritional needs depending on a variety of factors, including age, gender, pre-existing conditions, level of activity, and more. Thus, we hope to create a Machine Learning model to create a user-tailored experience for all. We also plan on incorporating the randomized algorithm and user-tailored generator for generating serving examples for the core food groups. We will improve the navigation of the website and extract the ingredient, macronutrient, and micronutrient data from Nutritionix API onto our pages.

Share this project: