Files in this item



application/pdfthesis.pdf (1MB)
Thesis PDF


Title:A Framework for Knowledge Discovery from Sparse, High-Dimensional Medical Datasets
Author(s):Ramachandran, Chandrasekar
Subject(s):data mining, knowledge discovery, association rule mining
Abstract:In this work, we describe a comprehensive framework for knowledge discovery from medical records called SDM-Miner. The records are created before, during and after pancreatic islet cell transplantation1 on a group of diabetic patients. The knowledge discovery focuses on selecting the most relevant variables for predicting the outcome of islet cell transplants temporally, and supporting the medical understanding of the variable relationships that would lead to insulin-free outcome of a transplant with machine learning models. The challenges of knowledge discovery lie in the temporally sparse nature of medical records and the large number of variables which make the traditional statistical analysis ineffective. Our approach to overcome the challenges is to combine data-driven computationally intensive modeling with statistical modeling. The framework incorporates this approach during three phases of knowledge discovery including (1) statistical data-preprocessing, (2) pattern search based dimensionality reduction, and (3) association rule based and conditional probability based data-driven modeling. We evaluate the framework by cross validating the models (of machine learning) using prediction errors and uncertainty of rule discovery. In order to demonstrate the novelty of the framework and the improved performance in knowledge discovery, we report results using real and synthetic datasets. Experimental results on synthetic data act as a sanity check in order to verify the effectiveness of our models in the absence of standard test results. The evaluation results show that our framework led to smaller mean error with the decreasing number of variable samples, higher robustness to Gaussian noise, and higher confidence and support of association rules than the previous methods. Furthermore, we evaluate our proposed technique using existing machine learning algorithms such using the Weka toolkit and show the improved performance of our work as compared to previous approaches.
Issue Date:2009
Genre:Dissertation / Thesis
Publication Status:unpublished
Peer Reviewed:not peer reviewed
Rights Information:Copyright Chandrasekar Ramachandran
Date Available in IDEALS:2009-12-16

This item appears in the following Collection(s)

Item Statistics