Precision-Driven AI Smartphone-Based Sensor System for Fingernail-Based Noninvasive Disease Detection

Liver disease and nail psoriasis can manifest through secondary nail changes, yet conventional diagnostic methods such as blood tests and biopsies remain invasive, costly, and painful for patients, highlighting the need for more accessible, non-invasive alternatives. This research introduces a novel deep learning (DL) based approach for the non-invasive detection of these diseases using fingernail image analysis. Various DL models, including Convolutional Neural Networks (CNN), VGG16, MobileNet, MobileNetV2, and InceptionV3, were evaluated, and accuracy of 82.66%, 91.33%, 90.00%, 90.67%, and 95.71% respectively for each model was achieved. The models were trained on a dataset of fingernail images, and their performance was assessed based on classification accuracy. The accuracy of InceptionV3 achieved was the highest. Building upon this model's success, a mobile application integrated with sensor-based functionality was developed allowing users to upload fingernail images and receive instant diagnostic feedback conveniently enabling early detection. This research demonstrates the transformative potential of DL and sensor technology in healthcare by providing a fast, reliable, and non-invasive diagnostic tool for early diagnosing liver and nail psoriasis disease in clinical and remote applications.