AI-Driven Non-Invasive Diagnosis of Diverse Medical Conditions Through Nail Image Analysis with High-Performance Ensemble Classifier

In this research, the application of deep learning methods for the classification of human nail diseases using image analysis is investigated. The aim was to establish a non-invasive, automatic diagnosis tool for different nail conditions, utilizing deep convolutional neural networks (CNNs) for feature extraction. A total of 500 images of nails, divided into seven classes of diseases, were employed for training and testing. Feature extraction was performed using VGG16, ResNet50, and EfficientNetB0, and three machine learning classifiers, AdaBoost, LightGBM, and a Meta Classifier, were applied. The multi-classifier data classifier, the Meta Classifier, did better with 98.0% accuracy, 98.2% precision, 97.9% recall, and 98.0% F1 score when used in conjunction with EfficientNetB0. The study validates the efficacy of AI image diagnostics in non-invasive disease diagnosis, delivering a cost-effective and trustworthy method for early diagnosis, particularly in low-resource areas. The study verifies the accuracy of deep learning models, especially EfficientNetB0, for medical image examination, but extensive clinical validation and dataset acquisition are essential