Integrated AI-Driven Healthcare System: Predictive Diagnosis, Personalized Medical-Report Content Generation, and Physician Recommendation

Accurate medical diagnosis remains elusive due to limitations in symptom analysis and personalized reports. Current systems often rely on keyword matching, leading to misdiagnosis and failing to adapt to nuanced medical narratives. This paper proposes a novel web application that addresses these challenges using state-of-the-art natural language processing techniques. Users input symptoms, triggers, and illness duration using a Likert scale. The proposed system employs a two-step process: initial diagnosis with a BM25 model followed by refinement using a pre-trained BERT model for a more contextual understanding. A comprehensive medical report is then generated, outlining the likely condition, proposing a treatment plan, and categorizing the report based on extracted keywords. Finally, K-means clustering suggests relevant specialist doctors based on the report category. This innovative approach enhances healthcare accessibility by providing tailored and swift recommendations, ultimately empowering users with informed decisions and fostering efficient doctor-patient connections.