This project aims to develop a comprehensive AI-powered medical diagnosis system structured into three distinct modules. Initially, the system will focus on analyzing current symptoms and medical history to suggest potential diagnoses for prevalent conditions such as the common cold, fever, and asthma. Building upon this foundation, the second module will introduce X-ray analysis capabilities to enhance diagnostic accuracy. Finally, the third module will integrate findings from both symptom-based and X-ray-based analyses, providing more nuanced and accurate diagnoses. Machine learning algorithms will drive each module, leveraging anonymized and ethically sourced public datasets for model training. The ultimate goal is to create an integrated application that assists healthcare professionals in improving diagnostic efficiency and accuracy. This user-friendly application will streamline the diagnostic process, offering quick access to comprehensive diagnostic insights derived from both symptom-based and radiological assessments. Furthermore, the symptom models, employing Logistic Regression and SVM algorithms, achieved notable accuracies ranging from 92 to 99%. Additionally, the results from the image module demonstrated promising performance, with a train accuracy of 99.02% and a test accuracy of 88.58%. These outcomes underscore the effectiveness and potential of the developed AI-powered diagnostic system.