Deep learning algorithms play a crucial practice in the diagnosis and prognosis of any diseases by analysing health data. Vitamins and minerals that the body needs in extremely small amounts are known as micronutrients. However, they have a crucial impact on a body’s health, and a lack of any one of them can result in serious, even life-threatening illnesses. They carry out a variety of tasks, including assisting the body in producing the hormones, enzymes, and other elements necessary for typical growth and development. Machine learning and deep learning algorithms have been proposed in literature to identify the nutrition deficiency. But providing better classification accuracy over nail image dataset is still a challenging task. The deep learning-based convolutional neural network (CNN) model is proposed in this approach for efficient identification of micro nutrient deficiency. The efficiency is measured based on the metrics accuracy, precision, specificity, and F-score. The result analysis of the proposed approach shows that maximum accuracy obtained is 98.40% while the dataset is splitted into training 80% and testing 20%.