- Shopping Bag ( 0 items )
Other sellers (Hardcover)
-
All (7) from $127.95
-
New (5) from $127.95
-
Used (2) from $354.72
More About This Textbook
Overview
The investigation of healthcare databases can be used to examine physician decisions and develop evidence-based treatment guidelines that optimize patient outcomes.
Clinical Data Mining for Physician Decision Making and Investigating Health Outcomes: Methods for Prediction and Analysis demonstrates how concern for detail in datasets and the use of data mining techniques can extract important and meaningful knowledge from healthcare databases. Basic information on processing data with step-by-step instructions is provided, allowing readers to use their own data and follow the instructions to find meaningful results.
Editorial Reviews
Doody Reviews
Reviewer: Ryan M Carnahan, Pharm.D., M.S. (University of Iowa College of Public Health)Description: This is an overview of the knowledge necessary for working with large administrative healthcare databases to examine health outcomes and their relationship to practice patterns.
Purpose: The authors intend to "show how the investigation of healthcare databases can be used to examine physician decisions to develop evidence-based treatment guidelines that optimize patient outcomes." This is not a simple or straightforward goal, but it is an important one. The authors have done an admirable job of trying to cover the many topics that need to be considered in conducting such work, and also predicting the future of this work by exploring the potential of various data mining techniques that aren't yet common in today's healthcare database research. To my knowledge, few books have given such detailed examples and practical instruction on the nuts and bolts of conducting research using large healthcare databases.
Audience: The book is intended for healthcare researchers who want to use available health outcomes databases but don't know how to get started. The authors have a great deal of experience in this area and are well qualified. The book begins with some valuable introductory commentary on various aspects of healthcare database research that need to be considered, and also provides very useful code for preprocessing of some databases available to researchers. That said, it should not be mistaken as an introductory book for novice researchers. It sometimes skips from an introductory discussion of a topic to fairly sophisticated SAS code that requires baseline SAS expertise to be translated. The statistical topics are also discussed at a fairly high level. The authors focus primarily on time series and time-to-event analyses, and discuss some of the basics and pitfalls of these analyses. However, the book is likely most useful for readers with a strong analytical background who haven't yet applied these skills to large healthcare databases.
Features: The authors pay a great deal of attention to the preprocessing of data, a vital step in the use of these databases that is not often discussed in the research. This is an important contribution. The book also covers topics on compressing and merging claims databases to create analytic datasets, considerations in working with diagnosis codes, comorbidity indices including specific diagnostic code sets and variants of the indices, compliance, and decision trees. It provides a number of examples of studies that have been done with various data sets available to researchers, such as CMS data. The real-world examples are among the great strengths of the book. Theoretical discussions of these topics simply can't illustrate key considerations in the same way that these examples can. The SAS code and pictures of SAS interfaces and output are also very useful. One challenge lies in the methods for processing data in SAS - this can be a matter of taste. For example, the authors show methods for merging, filtering, and recoding data using the Windows-style interfaces within SAS instead of using code. They also use methods for processing prescription data that are different than anything I've ever encountered, such as placing all claims and dates into a single row rather than summarizing multiple claims prior to completing this compression. These challenges should not be terribly difficult to overcome for experienced SAS users, but they must be prepared to translate these methods to their own preferred methods or those that apply to their specific needs.
Assessment: This book is a valuable contribution, which will help researchers understand issues related to research using large healthcare databases. I'm not aware of other books that cover these important topics and provide such detailed analytic examples. One of the reasons I reviewed the book was to see if it would be suitable as a primary textbook for a course on analyzing large administrative healthcare databases. Though there are sections of the book that are clearly useful for that purpose and accessible to less experienced researchers, I've yet to decide if it's the right book for such a course. Given the baseline SAS knowledge needed to use the book to its full potential, it may depend on the level of SAS expertise of the students. More precisely annotated SAS code might have made it more accessible to less experienced programmers. As far as the book's usefulness to researchers with SAS experience who are working with administrative healthcare databases, it is an excellent resource, and I plan to add it to my library.
Doody's Review Service
Reviewer: Ryan M. Carnahan, PharmD, MS (University of Iowa College of Public Health)Description: This is an overview of the knowledge necessary for working with large administrative healthcare databases to examine health outcomes and their relationship to practice patterns.
Purpose: The authors intend to "show how the investigation of healthcare databases can be used to examine physician decisions to develop evidence-based treatment guidelines that optimize patient outcomes." This is not a simple or straightforward goal, but it is an important one. The authors have done an admirable job of trying to cover the many topics that need to be considered in conducting such work, and also predicting the future of this work by exploring the potential of various data mining techniques that aren't yet common in today's healthcare database research. To my knowledge, few books have given such detailed examples and practical instruction on the nuts and bolts of conducting research using large healthcare databases.
Audience: The book is intended for healthcare researchers who want to use available health outcomes databases but don't know how to get started. The authors have a great deal of experience in this area and are well qualified. The book begins with some valuable introductory commentary on various aspects of healthcare database research that need to be considered, and also provides very useful code for preprocessing of some databases available to researchers. That said, it should not be mistaken as an introductory book for novice researchers. It sometimes skips from an introductory discussion of a topic to fairly sophisticated SAS code that requires baseline SAS expertise to be translated. The statistical topics are also discussed at a fairly high level. The authors focus primarily on time series and time-to-event analyses, and discuss some of the basics and pitfalls of these analyses. However, the book is likely most useful for readers with a strong analytical background who haven't yet applied these skills to large healthcare databases.
Features: The authors pay a great deal of attention to the preprocessing of data, a vital step in the use of these databases that is not often discussed in the research. This is an important contribution. The book also covers topics on compressing and merging claims databases to create analytic datasets, considerations in working with diagnosis codes, comorbidity indices including specific diagnostic code sets and variants of the indices, compliance, and decision trees. It provides a number of examples of studies that have been done with various data sets available to researchers, such as CMS data. The real-world examples are among the great strengths of the book. Theoretical discussions of these topics simply can't illustrate key considerations in the same way that these examples can. The SAS code and pictures of SAS interfaces and output are also very useful. One challenge lies in the methods for processing data in SAS - this can be a matter of taste. For example, the authors show methods for merging, filtering, and recoding data using the Windows-style interfaces within SAS instead of using code. They also use methods for processing prescription data that are different than anything I've ever encountered, such as placing all claims and dates into a single row rather than summarizing multiple claims prior to completing this compression. These challenges should not be terribly difficult to overcome for experienced SAS users, but they must be prepared to translate these methods to their own preferred methods or those that apply to their specific needs.
Assessment: This book is a valuable contribution, which will help researchers understand issues related to research using large healthcare databases. I'm not aware of other books that cover these important topics and provide such detailed analytic examples. One of the reasons I reviewed the book was to see if it would be suitable as a primary textbook for a course on analyzing large administrative healthcare databases. Though there are sections of the book that are clearly useful for that purpose and accessible to less experienced researchers, I've yet to decide if it's the right book for such a course. Given the baseline SAS knowledge needed to use the book to its full potential, it may depend on the level of SAS expertise of the students. More precisely annotated SAS code might have made it more accessible to less experienced programmers. As far as the book's usefulness to researchers with SAS experience who are working with administrative healthcare databases, it is an excellent resource, and I plan to add it to my library.
Product Details