Published Paper Details:

AI Doctor 2.0 is an AI-based diagnostic framework that integrates both voice and vision inputs to simulate intelligent real-time doctor-like consultations. The system uses OpenAI's GPT and Vision models for understanding natural language and interpreting medical images like Xrays or skin rashes. ElevenLabs API is used to generate human-like speech for voice-based diagnosis feedback. The platform allows patients to describe symptoms through speech or upload an image, which is then analyzed using pretrained AI models. Voice input is processed via speech-to-text conversion, and images are encoded and analyzed using a multimodal large language model. The AI returns a diagnosis, which is both displayed and read out to the user, increasing accessibility. The system is implemented using Python, Flask/FastAPI, and Gradio, allowing real-time interaction and easy deployment. Testing included real-world inputs to evaluate system accuracy, performance, and output quality. The results demonstrate the effectiveness of combining NLP and vision analysis in healthcare applications. This framework can be extended to include multilingual support, medical report generation, and IoT health device integration in future versions. AI Doctor 2.0 serves as a promising step towards accessible, intelligent, and scalable AI-powered digital healthcare platforms for remote diagnosis and primary consultation support