面向医疗系统的隐私保护疾病预测研究

Research on Privacy Protection and Disease Prediction for Medical System

摘要:

为了提高医疗数据的隐私性并有效对疾病进行预测,针对从物联网(IoT)设备收集的患者医疗数据,构建了面向医疗系统的隐私保护疾病预测系统框架,通过加密组合文本建立密钥提高了系统认证阶段的隐私性,加强系统和信息传输的安全性。利用基于对数循环值的椭圆曲线密码体制(LR-ECC)提高了数据传输阶段的安全性,从而授权的医护人员可以在医院侧安全地下载患者数据。运用基于象群遗传算法的的深度学习神经网络(EHGA-DLNN)分类技术在疾病预测系统(DPS)阶段实现了疾病数据的有效分类预测。实验结果表明,LR-ECC方法在加密时间和解密时间效率方面高于其他加密方法,并且能够达到98.87%的安全级别,EHGA-DLNN方法在疾病预测分类准确率达到98.35%。

Abstract:

In order to improve the privacy of medical data and effectively predict diseases, for patient medical data collected from Internet of things (IoT) devices, this paper constructs a privacy protection and disease prediction system framework for medical systems. By encrypting the combined text to establish a key, it improves the privacy of the system authentication stage and strengthens the security of the system and information transmission. The Log of Round value-based Elliptic Curve Cryptography (LR-ECC) improves the security of the data transmission stage, so that authorized medical staff can download patient data safely on the hospital side. The classification technology of deep learning neural network (EHGA-DLNN) based on image Swarm Genetic algorithm is used to achieve effective classification and prediction of disease data in the stage of disease prediction system (DPS). The experimental results show that lr-ecc method is higher than other encryption methods in encryption time and decryption time efficiency, and can achieve a security level of 98.87%. Ehga-dlnn method has a classification accuracy of 98.35% in disease prediction.