Title :
Using Published Medical Results and Non-homogenous Data in Rule Learning
Author :
Wojtusiak, Janusz ; Irvin, Katherine ; Birerdinc, Aybike ; Baranova, Ancha V.
Author_Institution :
George Mason Univ., Fairfax, VA, USA
Abstract :
Many factors limit researchers from accessing studies´ original data sets. As a result, much medical and healthcare research is based off of systematic reviews and meta-analysis of published results. However, when research involves the use of aggregated data from multiple studies, traditional machine learning-based means of analysis cannot be used. This paper describes diversity of data and results available in published man-uscripts, and relates them to a rule learning method that can be applied to build classification and predictive models from such input. The method can be used to support meta-analysis and systematic reviews. Two ap-plication areas are used to illustrate the discussed issues: diagnosis of liver diseases in patients with metabolic syndrome, and detection of polycystic ovary syndrome.
Keywords :
data analysis; diseases; health care; learning (artificial intelligence); medical information systems; pattern classification; publishing; classification model; data diversity; healthcare research; liver disease diagnosis; medical research; metabolic syndrome; nonhomogenous data; polycystic ovary syndrome detection; predictive model; published medical results; rule learning method; Correlation; Data models; Insulin; Learning systems; Machine learning; Predictive models; Systematics; Aggregated data; Meta-analysis; Published result; Rule learning; Systematic reviews;
Conference_Titel :
Machine Learning and Applications and Workshops (ICMLA), 2011 10th International Conference on
Conference_Location :
Honolulu, HI
Print_ISBN :
978-1-4577-2134-2
DOI :
10.1109/ICMLA.2011.154
