This work presents an AI-based healthcare support system designed to assist users in identifying the appropriate medical specialist based on their symptoms. The system uses machine learning techniques with TF-IDF feature extraction and multiple classification algorithms, including Naïve Bayes, Support Vector Machine, and Random Forest. Among the evaluated models, the Random Forest classifier achieved the highest accuracy of approximately 90%, making it suitable for reliable prediction. In addition to specialist recommendation, the system incorporates a severity assessment module that evaluates the urgency of a patient’s condition using a weighted symptom scoring approach. A smart scheduling mechanism is also implemented to automatically allocate the next available appointment slot in case of conflicts, improving user experience and system efficiency. The application is developed using a React frontend, Flask backend, and a lightweight JSON-based data storage approach. This work demonstrates the potential of integrating machine learning with healthcare systems to improve decision-making, reduce manual effort, and enhance accessibility to medical services.
Teja Ravi Hulse (Sun,) studied this question.