Prediction and Analysis of Vitamin D Deficiency Using Machine Learning Algorithms

Vitamin D is an important nutrient that has a wide range of effects on the human body. It is more common in those who do not get enough sunlight and do not get enough vitamin D in their diet. Vitamin D deficiency has been linked to a number of auto-immune diseases, including cardiovascular disease, diabetes, and breast cancer. In the current method, only statistical models were employed to estimate the severity of insufficiency in vitamin D datasets. Smaller vitamin datasets are used to test the statistical models. When the methods are applied to larger datasets, there is a risk of performance degradation. The goal of the proposed research is to compare and evaluate various machine learning models for predicting the severity of vitamin D deficiency (VDD). The work focuses on using several machine learning algorithms to make predictions and evaluating the results using various performance measures such as accuracy, mean absolute error, and mean squared error. To predict the severity of VDD, strong machine learning classifiers such as decision tree (DT) and random forest (RF) are used. The main goal is to find the most accurate machine learning classifier for predicting the severity of VDD.