The growing integration of Artificial Intelligence (AI) in healthcare enables the development of intelligent diagnostic support systems. Our project IA-Med is a disease prediction system that, based on symptoms entered by the user, provides a likely diagnosis along with personalized recommendations (treatments, precautions, nutritional advice). The system was developed using synthetic data to ensure privacy during the initial development phase. To achieve this, several machine learning models were trained on a structured dataset. The models Random Forest and Support Vector Machine (SVM) were selected for their superior performance, with Random Forest achieving 99.49% accuracy on the test set. The system predicts possible diseases along with their probabilities and includes a AI Chatbot that delivers these results interactively. IA-Med’s novelty lies in its integrated approach combining high-accuracy prediction with conversational AI and personalized recommendations in a single platform. These results demonstrate the potential of machine learning to create reliable, interpretable, and user-friendly health tools, while highlighting the need for future validation with clinical data.