Medical health data analysis based on Spark Mllib

In recent years, health and disease prediction has become an important part of medical wisdom, and has attracted more and more attention. At this stage, the prediction of health care mainly relies on the medical health records data. For predicting results, it is only in view of the disease or not. At present, for the lack of adaptability and limitations of the data feature selection, in this paper we use the existing health records data and available life habit data, combined with the current popular Spark machine learning computing platform, and establish a multi-classification model, which can provide a reasonable prediction and evaluation. This design has a certain degree of accuracy and efficiency and it has a certain use value.