NailSight: An Application Utilizing Convolutional Neural Networks for The Early Diagnostic Detection of Diseases through Fingernails

Numerous early-stage cardiovascular, liver, and kidney diseases are undetectable in their early stages, with survival rates decreasing as the disease spreads into their later stages, early diagnostics are vital. These diseases frequently have small or unnoticeable manifestations in the fingernail that allow for the early detection of these conditions, often going ignored or misdiagnosed. Current diagnostic methods for these diseases include a comprehensive patient’s medical history, a thorough clinical review, and an MRI scan, leaving those residing in rural or underserved areas unable to access such diagnoses. The goal of this research project was to (1) develop a more effective and accurate Convolutional Neural Network (CNN) algorithm to validate, identify, and classify a variety of diseases through feature segmentation with pictures of your fingernails and (2) integrate a machine learning model into a mobile app platform for offline and portable, accessibility to the platform. After following the procedures, the algorithms accuracy rates of up to 85%. Following the initial development, the machine learning model was successfully implemented in a mobile application. The application’s efficiency and ease of use will prove it to be a helpful tool for people around the world. With more than 3.8 billion smartphone users worldwide and increasing, the application could potentially provide low-cost universal access to vital diagnostics. The algorithm has the ability to detect Beau’s Lines, Clubbing Nails, Terry’s Nails, Lindsay’s Nails, Melanoma and Healthy Nails, and will soon be further developed to analyze a wider range of diseases and conditions. It has the ability to provide automatic, offline, and accurate medical analysis around the globe, subsequently, profoundly expanding access to vital medical care.


Related Project


Smart DeTech