Optimizing Erythemato-Squamous Disease Diagnosis with Cutting-Edge Machine Learning Models

This The goal of this project paper is to create a machine learning-enhanced diagnostic system for Erythemato-Squamous diseases (ESD) that uses the Gradient Booster algorithm, K-Nearest Neighbors (KNN), and Logistic Regression (LR) to classify various strains of the disease. of LR, the system used a dataset of clinical, historical, and demographic data to obtain an astounding 98.64% accuracy rate. This demonstrates how the approach may significantly enhance ESD diagnosis and treatment choices. The reliability of the findings was confirmed using an additional dataset, pointing to noteworthy developments in the field of dermatological healthcare and creating new avenues for the application of machine learning in medical diagnostics