A time series based method for analyzing and predicting personalized medical data

Authors:
Qinwin Vivian Hu;Xiangji Jimmy Huang;William Melek;C. Joseph Kurian
Affiliations:
Information Retrieval and Knowledge Management Research Lab, York University, Toronto, Canada;Information Retrieval and Knowledge Management Research Lab, York University, Toronto, Canada;Alpha Global IT, Toronto, Canada;Alpha Global IT, Toronto, Canada
Venue:
BI'10 Proceedings of the 2010 international conference on Brain informatics
Year:
2010

Citing 0
Cited 1

Sequential event prediction

Machine Learning

Quantified Score

Hi-index	0.00

Visualization

Abstract

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.