Patient re-admission rate prediction method and device based on ciphertext replacement and Gaussian noise

The invention discloses a method and a device for predicting the re-admission rate of a patient based on ciphertext replacement and Gaussian noise, and belongs to the field of medical data analysis of data science and analysis. And selecting a machine learning model for predicting the re-admission rate, training the machine learning model, inputting the data added with the noise into the trained machine learning model, and predicting the re-admission rate. According to the invention, the problem of balancing the privacy of the patient and the accuracy of hospital re-admission rate prediction can be solved. 本发明公开了一种基于密文替换和高斯噪声的患者再入院率预测方法及装置，属于数据科学与分析的医疗数据分析领域，收集目标医院的医疗数据，对医疗数据进行编码，对编码后的数据添加噪声，选择用于预测再入院率的机器学习模型并进行训练，将添加噪声后的数据输入到训练好的机器学习模型中，预测再入院率。本发明能够解决平衡患者隐私与医院再入院率预测的准确性问题。