The paper introduces Health-LLM, an innovative framework that combines large-scale feature extraction, medical knowledge scoring, and machine learning techniques to enhance personalized disease prediction in healthcare. The system integrates health reports and medical knowledge into a large model, leveraging retrieval-augmented generation (RAG) for enhanced feature extraction and a semi-automated feature updating framework to improve prediction accuracy. Compared to traditional methods and large language models like GPT-3.5 and GPT-4, Health-LLM demonstrates superior performance, achieving an accuracy of 0.833 and an F1 score of 0.762. The system uses the Llama Index framework for feature scoring, XGBoost for prediction, and in-context learning for symptom feature generation. Extensive experiments on the IMCS-21 dataset validate the system's effectiveness, showing it can accurately predict diseases and provide personalized health advice. Future work includes integrating multimodal data to further enhance disease prediction capabilities.The paper introduces Health-LLM, an innovative framework that combines large-scale feature extraction, medical knowledge scoring, and machine learning techniques to enhance personalized disease prediction in healthcare. The system integrates health reports and medical knowledge into a large model, leveraging retrieval-augmented generation (RAG) for enhanced feature extraction and a semi-automated feature updating framework to improve prediction accuracy. Compared to traditional methods and large language models like GPT-3.5 and GPT-4, Health-LLM demonstrates superior performance, achieving an accuracy of 0.833 and an F1 score of 0.762. The system uses the Llama Index framework for feature scoring, XGBoost for prediction, and in-context learning for symptom feature generation. Extensive experiments on the IMCS-21 dataset validate the system's effectiveness, showing it can accurately predict diseases and provide personalized health advice. Future work includes integrating multimodal data to further enhance disease prediction capabilities.