Data Mining in Biomedicine

by Panos M. Pardalos (Editor), Vladimir L. Boginski (Editor), Alkis Vazacopoulos (Editor)

Overview

This volume presents an extensive collection of contributions covering aspects of the exciting and important research field of data mining techniques in biomedicine. Coverage includes new approaches for the analysis of biomedical data; applications of data mining techniques to real-life problems in medical practice; comprehensive reviews of recent trends in the field. The book addresses incorporation of data mining in fundamental areas of biomedical research: genomics, proteomics, protein characterization, and neuroscience.

Product Details

ISBN-13:	9781441943439
Publisher:	Springer US
Publication date:	11/19/2010
Series:	Springer Optimization and Its Applications , #7
Edition description:	Softcover reprint of hardcover 1st ed. 2007
Pages:	582
Product dimensions:	6.10(w) x 9.25(h) x 0.05(d)

Table of Contents

Recent Methodological Developments for Data Mining Problems in Biomedicine.- Pattern-Based Discriminants in the Logical Analysis of Data.- Exploring Microarray Data with Correspondence Analysis.- An Ensemble Method of Discovering Sample Classes Using Gene Expression Profiling.- CpG Island Identification with Higher Order and Variable Order Markov Models.- Data Mining Algorithms for Virtual Screening of Bioactive Compounds.- Sparse Component Analysis: a New Tool for Data Mining.- Data Mining Via Entropy and Graph Clustering.- Molecular Biology and Pooling Design.- An Optimization Approach to Identify the Relationship between Features and Output of a Multi-label Classifier.- Classifying Noisy and Incomplete Medical Data by a Differential Latent Semantic Indexing Approach.- Ontology Search and Text Mining of MEDLINE Database.- Data Mining Techniques in Disease Diagnosis.- Logical Analysis of Computed Tomography Data to Differentiate Entities of Idiopathic Interstitial Pneumonias.- Diagnosis of Alport Syndrome by Pattern Recognition Techniques.- Clinical Analysis of the Diagnostic Classification of Geriatric Disorders.- Data Mining Studies in Genomics and Proteomics.- A Hybrid Knowledge Based-Clustering Multi-Class SVM Approach for Genes Expression Analysis.- Mathematical Programming Formulations for Problems in Genomics and Proteomics.- Inferring the Origin of the Genetic Code.- Deciphering the Structures of Genomic DNA Sequences Using Recurrence Time Statistics.- Clustering Proteomics Data Using Bayesian Principal Component Analysis.- Bioinformatics for Traumatic Brain Injury: Proteomic Data Mining.- Characterization and Prediction of Protein Structure.- Computational Methods for Protein Fold Prediction: an Ab-initio Topological Approach.- A Topological Characterization of Protein Structure.- Applications of Data Mining Techniques to Brain Dynamics Studies.- Data Mining in EEG: Application to Epileptic Brain Disorders.- Information Flow in Coupled Nonlinear Systems: Application to the Epileptic Human Brain.- Reconstruction of Epileptic Brain Dynamics Using Data Mining Techniques.- Automated Seizure Prediction Algorithm and its Statistical Assessment: A Report from Ten Patients.- Seizure Predictability in an Experimental Model of Epilepsy.- Network-Based Techniques in EEG Data Analysis and Epileptic Brain Modeling.

Editorial Reviews

Reviewer: Nicole Mitchell, MA, MLIS (University of Alabama at Birmingham)
Description: Volume 7 of the Springer Optimization and Its Applications series, this book is an in-depth look at "the development of appropriate methods for extracting useful information" from data in biomedicine. As the editors state in the preface, "data mining techniques play an essential role in analyzing and integrating" datasets such as drug discovery, understanding human genomes or the human brain, disease diagnosis, and the biological processes that bring about these concepts.
Purpose: The chapters discuss varying facets of data mining in the field of biomedicine. Subjects include new approaches in analyzing biomedical data and applying data mining techniques to other areas in medical practice as well as reviews of recent trends in biomedical data mining.
Audience: According to the editors, experts in industrial and systems engineering (Pardolos and Boginski) and modeling and optimization software (Vazacopoulos), this book is aimed at scientists and practitioners in the fields of biomedicine, engineering, mathematics, and computer science as well as graduate students and is appropriate for a variety of readers.
Features: The book is divided into five parts covering new developments, techniques in diagnosing diseases, studies in genomics and proteomics, using data mining to characterize and predict protein structure, and applying data mining techniques to studies in brain dynamics. Some of the recent developments featured in part I are gene expression profiling, sparse component analysis, and entropy and graph clustering. Part III explores such topics as mathematical programming formulas and bioinformatics for traumatic brain injury. In perhaps the most interesting section, part V delves into the role of data mining techniques, like EEG analysis and brain models, to help understand the epileptic brain. One shortcoming of this book is that parts I and V are significantly longer than the others. Part I, for instance, has 11 chapters while part IV has only two. While recent developments in data mining certainly deserve attention, the other topics may have been shortchanged. Filled with various diagrams, charts, and equations, the book features a list of contributing authors, with their respective contact information, as well as an index. Each chapter includes a list of references.
Assessment: A well compiled volume on the application of data mining to biomedicine, this book will be a welcome addition to the literature. Librarians will be particularly interested in the chapter on "Ontology Search and Text Mining of MEDLINE Database" which offers methods for "building concept hierarchies" in MEDLINE.

Doody's Review Service

From the reviews:

"This book is an in-depth look at ‘the development of appropriate methods for extracting useful information’ from data in biomedicine. … is aimed at scientists and practitioners in the fields of biomedicine, engineering, mathematics, and computer science as well as graduate students and is appropriate for a variety of readers. … A well compiled volume on the application of data mining to biomedicine, this book will be a welcome addition to the literature." (Nicole Mitchell, Doody’s Review Service, August, 2008)

From the Publisher