Classification and retrieval method of personal health data based on differential privacy

Research on personal health data classification and retrieval methods can improve the accuracy and efficiency of medical decision-making, promoting the development of personalised medicine. To overcome the issues of low accuracy, long retrieval time, and low satisfaction in traditional methods, a classification and retrieval method of personal health data based on differential privacy is proposed. The method involves encrypting personal health data using linear regression model and differential privacy and constructing a classification objective function through integrated manifold learning that classifies the encrypted results of personal health data. Binary hash codes are used to retrieve the classification results, and the decrypted retrieval results are provided to users for personal health data classification and retrieval. The experimental results demonstrate that this method achieves a maximum accuracy of 96.8% in personal health data classification and retrieval, with a minimum retrieval time of 20 ms and an average satisfaction of 97.1% for the retrieval results.