The Community for Technology Leaders
Computer Science and Information Engineering, World Congress on (2009)
Los Angeles, California USA
Mar. 31, 2009 to Apr. 2, 2009
ISBN: 978-0-7695-3507-4
pp: 552-556
In a longitudinal medical study, various types of data and biomaterial samples are collected in frequent intervals, and are used to analyze factors and pathways leading to a defined disease or a group of diseases. Large volume of complex data consisting of medical history and biochemical analysis results are typically collected in such studies.Our research shows that if the appropriate data model is co-designed with the research goals, it is possible to create a generalized model which allows integrating six tasks of the study: collecting, storing, managing, and analyzing data and samples, and introducing machine learning tools to create predictive models, which in turn assist in the previous tasks. We have implemented this model as a system, which integrates individual processes, minimizes human error, and conforms to changes in the study. This clearly improves the quality, interpretability, reliability and efficiency in understanding the development of the disease.
Disease prediction, Expert system

B. Simell, M. Laaksonen, T. Salakoski and O. Simell, "Integrated Data Management and Analysis Environment for Medical Longitudinal Research with Machine Learning Based Prediction Models," 2009 WRI World Congress on Computer Science and Information Engineering, CSIE(CSIE), Los Angeles, CA, 2009, pp. 552-556.
87 ms
(Ver 3.3 (11022016))