A Time Series Based Method for Analyzing and Predicting Personalized Medical Data

摘要

In this paper, we propose a time series based method for analyzing and predicting personal medical data. First, we introduce an auto-regressive integrated moving average model which is good for all time series processes. Second, we describe how to identify a personalized time series model based on the patient's history information, followed by estimating the parameters in the model. Furthermore, a case study is presented to show how the proposed method works. In addition, we forecast the laboratory tests for the next twelve months in the future, with giving the corresponding prediction limits. Finally, we draw our contributions as our conclusions.