Early detection of diseases is a critical factor in improving patient survival rates and reducing healthcare costs. Traditionaldiagnostic processes usually involve multiple laboratory tests, clinical examinations, and specialist consultations, whichmayconsumeconsiderable time and resources. With the rapid development of artificial intelligence and machine learning technologies, automatedmedical diagnosis systems have become increasingly popular in modern healthcare. These systems assist healthcare professionalsbyanalyzing large volumes of medical data and identifying patterns that may indicate the presence of diseases at an earlystage.Machinelearning techniques have demonstrated remarkable potential in predicting diseases using structured medical datasets containingpatientinformation such as blood pressure, glucose level, cholesterol level, body mass index, and other clinical parameters. At thesametime,deep learning algorithms have shown strong performance in analyzing medical images such as X-rays and microscopicbloodsmearimages. These advancements have enabled the development of intelligent diagnostic systems capable of detectingdiseasesmoreefficiently and accurately.This research presents an AI-based multi-disease medical diagnosis system that integrates both machine learning and deep learning techniques within a unified web-based platform. The proposed system is designed to predict several major diseases, including diabetes, heart disease, liver disease, kidney disease, breast cancer, pneumonia, and malaria. Machine learning models are used to analyze tabular clinical data, while deep learning convolutional neural networks are used for detecting diseases from medical images. Keywords: Machine Learning, Deep Learning, Medical Diagnosis, Disease Prediction, Healthcare AI, Artificial Intelligence