Biological Nutrient Deficiency Prediction using Machine Learning

Thirupathi Sundhararajulu1, Yadamuru Rohini2, Sourav Kumar3, K.Chaithanya kumar4 ,
A.Kunal Kumar5, A.M.Sai Krishnan6
1,2,3,4,5,6 Computer Science and Information Technology, Siddharth Institute of Engineering & Technology

Abstract- Deficiencies of nutrients including Iron, Vitamin C, Vitamin B12, and Vitamin D are common all over the world and they usually remain unnoticed until causing serious health complications. The conventional diagnostic procedures are costly clinical tests that restrictthe ability to detect a condition early enough, particularly in under-served regions. This gap is filled in this project through creating a machine learning-based system that can predict nutrient deficiencies using common symptoms. The algorithms used in the system to give accurate predictions include Decision Tree, Random Forest, and XGBoost. The web application, which is developed with Flask, has a convenient interface and allows a person to enter their symptoms and receive the answer concerning possible nutrient deficiencies. Through the system, users have beenenabled to make wise choices by having an affordable and easy way of tracking their nutritional health without necessarily undertaking costly medical tests. This preventive instrument of early detection increases health awareness, and promotes preventive health, which can lead to improved health outcomes of a population. The system is simple and easy to use by incorporating advanced machine learning methods that allow a high level of accuracy in prediction. The proposed solution will provide scalability to individual and healthcare provider users with an opportunity to intervene early and make an informed decision on nutritional health.Keywords: Keywords Machine learning, nutrition, decision tree, XGBoost, random forest, nutrient deficiency, machine learning, tool (flask), machine learning, diagnosis of symptoms, machine learning, healthcare, early detection, nutrition, health care technology.