An AI-Powered Deep Learning Model for Vitamin Deficiency Diagnosis

Vitamin deficiencies are a major global health concern, leading to severe medical conditions if left undiagnosed. Traditional detection methods are time-consuming, require expert analysis, and often lack accessibility. This paper presents a deep learning-based approach using a Convolutional Neural Network (CNN) to classify vitamin deficiencies from images. A selftrained CNN model processes input images to detect specific deficiencies. The model is integrated with a real-time image capture system using Android Debug Bridge (ADB), enabling image acquisition directly from a mobile device. Performance metrics, including accuracy, Precision, F1 Score and Recall, are analysed to evaluate model efficiency. Experimental results indicate that the proposed system provides fast, automated, and reliable vitamin deficiency detection, making it a cost-effective and scalable solution for healthcare applications.