Medical ethics privacy protection based on combining distributed randomization with K-anonymity

In the era of big data, the Privacy Preserving Data Mining (PPDM) technology is increasingly important. The aim is to dig out the hidden, previously unknown and potentially useful knowledge or pattern under the premise of protecting sensitive data. In this paper, we summarize the existing PPDM technology as well as its advantages and disadvantages. We combine distributed randomization with the K-anonymity algorithm to reduce the information loss rate in order to increase the data availability and avoid the leakage of privacy data information. This method is applied to clinical data of diabetic nephropathy(DN). The result has proved that the potential relationship between some certain factors and diabetic nephropathy syndromes has no obvious damage compared with the result which is got on the basis of the unprotected status.