AI-powered scurvy detection : bridging healthcare disparities in rural settings

Scurvy, historically associated with sailors on long voyages without access to fresh fruits and vegetables, is characterized by symptoms like fatigue, swollen gums, and impaired wound healing, highlighting the importance of adequate vitamin C intake. Given the resurgence of scurvy, particularly in developed countries where it was previously considered rare, there is a pressing need for improved diagnostic tools to detect and classify this condition efficiently and accurately. Rural areas often face challenges of limited healthcare infrastructure and skilled medical professionals, leading to delayed diagnosis and management of diseases such as scurvy. This research proposes an innovative solution by developing an artificial intelligence (AI) model using the AlexNetCNN architecture to detect scurvy, thereby overcoming barriers to timely diagnosis in rural settings. Comprehensive datasets are collected from public resources such as Google to train the AI model for accurate scurvy detection. The collected images are cropped and resized to standardize the input format, optimizing the model's efficiency and performance. Initial testing of the AI model reveals a remarkable accuracy rate of 100% in scurvy detection, showcasing the potential of AI technology to address healthcare disparities and improve diagnostic capabilities, particularly in underserved rural areas. The project aims to further develop the AI model into a user-friendly app, empowering individuals in rural areas to self-assess and detect scurvy early, thereby facilitating timely intervention and improving health outcomes in vulnerable populations.