Early Identification of Nutritional Gaps in Pregnant Women Using Nail Images for Healthcare Analysis

During pregnancy, the mother needs to care for her nutritional deficiencies as it may cause severe health issues for both the mother and her baby. The two most important nutrients are calcium and iron, and their deficiencies can prevalently cause anaemia, premature birth, depression, neurological disorders, weakened bones, slow growth, and osteoporosis which compromises the overall well-being of the mother and her baby. Traditional methods to diagnose these deficiencies are through blood tests done in laboratories. These tests are invasive, costly, and sometimes inaccessible. This paper proposes a novel approach to detect calcium and iron deficiencies in pregnant women using deep learning-based nail analysis and a comprehensive questionnaire, in pregnant women, ultimately contributing to improved maternal and fetal health outcomes. An appropriate deep-learning model was selected for the given problem statement. The model architecture consisted of convolutional layers, pooling layers, and dense layers. The model was trained on the prepared dataset to accurately classify nail images into healthy, calcium-deficient, and iron-deficient categories.