- Shopping Bag ( 0 items )
Other sellers (Hardcover)
-
All (8) from $112.40
-
New (5) from $127.95
-
Used (3) from $112.4
More About This Textbook
Overview
With the healthcare industry becoming increasingly more competitive, there exists a need for medical institutions to improve both the efficiency and the quality of their services. In order to do so, it is important to investigate how statistical models can be used to study health outcomes.
Cases on Health Outcomes and Clinical Data Mining: Studies and Frameworks provides several case studies developed by faculty and graduates of the University of Louisville's PhD program in Applied and Industrial Mathematics. The studies in this book use non-traditional, exploratory data analysis and data mining tools to examine health outcomes, finding patterns and trends in observational data. This book is ideal for the next generation of data mining practitioners.
Editorial Reviews
Doody's Review Service
Reviewer: Daniela Claudia Moga, MD (University of Iowa College of Public Health)Description: This book presents a series of research topics using data mining techniques and depicts their applicability in health-related research. It is not a comprehensive textbook on data mining or outcomes/health-services research, but it does provide a nice overview of both, which could help those interested in outcomes/health-services research who have less experience in data mining, and vice versa.
Purpose: Although not clearly stated, it appears that the intent was to present the health-related applications of different data mining techniques. According to the editor, the purpose of using data mining is to help patient treatment decision making. She considers that data mining can lead to decision making even in the absence of an a priori hypothesis testing. Today, as secondary data analysis becomes extremely important, data mining represents a useful approach in understanding and describing data. I acknowledge the importance of data mining whose usefulness resides in understanding and exploring large datasets, like those represented by clinical or administrative databases. However, I consider data mining similar to any descriptive study; this approach helps understanding health care in a specific population and can lead to important hypotheses, but the next step (i.e. hypothesis testing) would be necessary before decision making. The authors succeed in showing a variety of applications of data mining in health-services research, but are not as effective in presenting its possible impact on the decision making process.
Audience: Although not specified, the book could be useful for two audiences, at least. First, it could help students/professionals in applied and industrial mathematics (i.e. those using data mining routinely) in understanding some aspects of heath-services research; they could benefit from the medical overview in each chapter. Second, it provides those conducting healthcare/outcomes research with an overview of data mining procedures that can help explore and understand patterns in large databases.
Features: Following an introductory chapter that provides a brief overview of data mining methodology, the book is structured in three main parts, which are basically a collection of research projects conducted at University of Louisville by faculty and graduates from the PhD program in applied and industrial mathematics. The first part presents 10 different applications of data mining techniques in health outcomes research. The second part focuses on healthcare delivery studies, and the third one provides an example of data mining use in modeling EEG images for analysis. Each chapter introduces a health topic and a specific method from data mining, provides background on a specific medical problem, and continues with the methodological approach. The book outlines practical issues and possible solutions to problems that can arise in the process of exploring large datasets for research projects. Graphs throughout the book help readers understand data interpretation. Unfortunately, these illustrations lack color, which makes them difficult to read. However, the narrative flows logically and provides interesting information on healthcare research.
Assessment: This book is successful in emphasizing the role data mining can play in any research conducted from large databases, but seems to overstate its importance in the decision making process. It could be considered useful as a first step in understanding data mining and its applicability in healthcare research by providing a nice overview of different methods. However, those conducting health-service/outcomes research and interested in data mining would need a more in-depth book to be able to understand this approach. The same applies to those with a strong mathematical/statistical background entering the healthcare research field; they would need more information than provided in this book to get a good grasp of the unique characteristics of health-related research.
From The Critics
Reviewer:Daniela Claudia Moga, MD(University of Iowa College of Public Health)Description:This book presents a series of research topics using data mining techniques and depicts their applicability in health-related research. It is not a comprehensive textbook on data mining or outcomes/health-services research, but it does provide a nice overview of both, which could help those interested in outcomes/health-services research who have less experience in data mining, and vice versa.
Purpose:Although not clearly stated, it appears that the intent was to present the health-related applications of different data mining techniques. According to the editor, the purpose of using data mining is to help patient treatment decision making. She considers that data mining can lead to decision making even in the absence of an a priori hypothesis testing. Today, as secondary data analysis becomes extremely important, data mining represents a useful approach in understanding and describing data. I acknowledge the importance of data mining whose usefulness resides in understanding and exploring large datasets, like those represented by clinical or administrative databases. However, I consider data mining similar to any descriptive study; this approach helps understanding health care in a specific population and can lead to important hypotheses, but the next step (i.e. hypothesis testing) would be necessary before decision making. The authors succeed in showing a variety of applications of data mining in health-services research, but are not as effective in presenting its possible impact on the decision making process.
Audience:Although not specified, the book could be useful for two audiences, at least. First, it could help students/professionals in applied and industrial mathematics (i.e. those using data mining routinely) in understanding some aspects of heath-services research; they could benefit from the medical overview in each chapter. Second, it provides those conducting healthcare/outcomes research with an overview of data mining procedures that can help explore and understand patterns in large databases.
Features:Following an introductory chapter that provides a brief overview of data mining methodology, the book is structured in three main parts, which are basically a collection of research projects conducted at University of Louisville by faculty and graduates from the PhD program in applied and industrial mathematics. The first part presents 10 different applications of data mining techniques in health outcomes research. The second part focuses on healthcare delivery studies, and the third one provides an example of data mining use in modeling EEG images for analysis. Each chapter introduces a health topic and a specific method from data mining, provides background on a specific medical problem, and continues with the methodological approach. The book outlines practical issues and possible solutions to problems that can arise in the process of exploring large datasets for research projects. Graphs throughout the book help readers understand data interpretation. Unfortunately, these illustrations lack color, which makes them difficult to read. However, the narrative flows logically and provides interesting information on healthcare research.
Assessment:This book is successful in emphasizing the role data mining can play in any research conducted from large databases, but seems to overstate its importance in the decision making process. It could be considered useful as a first step in understanding data mining and its applicability in healthcare research by providing a nice overview of different methods. However, those conducting health-service/outcomes research and interested in data mining would need a more in-depth book to be able to understand this approach. The same applies to those with a strong mathematical/statistical background entering the healthcare research field; they would need more information than provided in this book to get a good grasp of the unique characteristics of health-related research.
From The Critics
Reviewer: Daniela Claudia Moga, MD(University of Iowa College of Public Health)Description: This book presents a series of research topics using data mining techniques and depicts their applicability in health-related research. It is not a comprehensive textbook on data mining or outcomes/health-services research, but it does provide a nice overview of both, which could help those interested in outcomes/health-services research who have less experience in data mining, and vice versa.
Purpose: Although not clearly stated, it appears that the intent was to present the health-related applications of different data mining techniques. According to the editor, the purpose of using data mining is to help patient treatment decision making. She considers that data mining can lead to decision making even in the absence of an a priori hypothesis testing. Today, as secondary data analysis becomes extremely important, data mining represents a useful approach in understanding and describing data. I acknowledge the importance of data mining whose usefulness resides in understanding and exploring large datasets, like those represented by clinical or administrative databases. However, I consider data mining similar to any descriptive study; this approach helps understanding health care in a specific population and can lead to important hypotheses, but the next step (i.e. hypothesis testing) would be necessary before decision making. The authors succeed in showing a variety of applications of data mining in health-services research, but are not as effective in presenting its possible impact on the decision making process.
Audience: Although not specified, the book could be useful for two audiences, at least. First, it could help students/professionals in applied and industrial mathematics (i.e. those using data mining routinely) in understanding some aspects of heath-services research; they could benefit from the medical overview in each chapter. Second, it provides those conducting healthcare/outcomes research with an overview of data mining procedures that can help explore and understand patterns in large databases.
Features: "Following an introductory chapter that provides a brief overview of data mining methodology, the book is structured in three main parts, which are basically a collection of research projects conducted at University of Louisville by faculty and graduates from the PhD program in applied and industrial mathematics. The first part presents 10 different applications of data mining techniques in health outcomes research. The second part focuses on healthcare delivery studies, and the third one provides an example of data mining use in modeling EEG images for analysis. Each chapter introduces a health topic and a specific method from data mining, provides background on a specific medical problem, and continues with the methodological approach. The book outlines practical issues and possible solutions to problems that can arise in the process of exploring large datasets for research projects. Graphs throughout the book help readers understand data interpretation. Unfortunately, these illustrations lack color, which makes them difficult to read. However, the narrative flows logically and provides interesting information on healthcare research."
Assessment: This book is successful in emphasizing the role data mining can play in any research conducted from large databases, but seems to overstate its importance in the decision making process. It could be considered useful as a first step in understanding data mining and its applicability in healthcare research by providing a nice overview of different methods. However, those conducting health-service/outcomes research and interested in data mining would need a more in-depth book to be able to understand this approach. The same applies to those with a strong mathematical/statistical background entering the healthcare research field; they would need more information than provided in this book to get a good grasp of the unique characteristics of health-related research.
Product Details