Muutke küpsiste eelistusi

Clinical Research Computing: A Practitioner's Handbook [Pehme köide]

2.00/5 (2 hinnangut Goodreads-ist)
(Research Professor, University of Iowa School of Medicine, Iowa City, IA, USA)
  • Formaat: Paperback / softback, 240 pages, kõrgus x laius: 235x191 mm, kaal: 480 g
  • Ilmumisaeg: 27-Apr-2016
  • Kirjastus: Academic Press Inc
  • ISBN-10: 0128031301
  • ISBN-13: 9780128031308
Teised raamatud teemal:
Clinical Research Computing: A Practitioner's HandbookSuurem pilt
  • Formaat: Paperback / softback, 240 pages, kõrgus x laius: 235x191 mm, kaal: 480 g
  • Ilmumisaeg: 27-Apr-2016
  • Kirjastus: Academic Press Inc
  • ISBN-10: 0128031301
  • ISBN-13: 9780128031308
Teised raamatud teemal:
Püsilink: https://www.kriso.ee/db/9780128031308.html
Märksõnad:

Clinical Research Computing: A Practitioner’s Handbook deals with the nuts-and-bolts of providing informatics and computing support for clinical research. The subjects that the practitioner must be aware of are not only technological and scientific, but also organizational and managerial. Therefore, the author offers case studies based on real life experiences in order to prepare the readers for the challenges they may face during their experiences either supporting clinical research or supporting electronic record systems. Clinical research computing is the application of computational methods to the broad field of clinical research. With the advent of modern digital computing, and the powerful data collection, storage, and analysis that is possible with it, it becomes more relevant to understand the technical details in order to fully seize its opportunities.

  • Offers case studies, based on real-life examples where possible, to engage the readers with more complex examples
  • Provides studies backed by technical details, e.g., schema diagrams, code snippets or algorithms illustrating particular techniques, to give the readers confidence to employ the techniques described in their own settings
  • Offers didactic content organization and an increasing complexity through the chapters

Muu info

Using a case study approach to prepare readers for the challenges of providing informatics and computing support for clinical research, this practical handbook covers the full range of relevant perspectives-technological, scientific, organizational, and managerial-for fully exploiting the opportunities created by clinical research computing
Foreword ix
1 An Introduction to Clinical Research Concepts
1(24)
1.1 Introduction
1(1)
1.2 The level of evidence hierarchy
1(4)
1.3 A bird's-eye view of statistics in clinical research
5(6)
1.4 Clinical studies of investigational therapies
11(5)
1.5 Clinical studies of established therapies
16(1)
1.6 Experimental design of comparative-effectiveness studies
17(4)
1.7 Evaluation of medical software
21(2)
1.8 Further reading
23(2)
Bibliography
24(1)
2 Supporting Clinical Research Computing: Technological and Nontechnological Considerations
25(24)
2.1 Technological aspects: software development
25(4)
2.2 Nontechnical factors: overview
29(1)
2.3 Attitude: service versus research
29(2)
2.4 Technical skills
31(2)
2.5 General skills and breadth of knowledge
33(1)
2.6 Communication skills
34(1)
2.7 Managing people and projects
35(4)
2.8 Personality traits
39(1)
2.9 Negotiation skills
40(1)
2.10 Choosing your collaborators
41(3)
2.11 Topics in clinical research support
44(5)
Bibliography
46(3)
3 Core Informatics Technologies: Data Storage
49(36)
3.1 Types of data elements: databases 101
49(7)
3.2 Transactional databases versus analytical databases
56(7)
3.3 Database indexes
63(12)
3.4 Managing integrated (structured + unstructured) data
75(2)
3.5 Nonrelational approaches to data management: "NoSQL" systems
77(6)
3.6 Final words
83(2)
Bibliography
83(2)
4 Core Technologies: Machine Learning and Natural Language Processing
85(30)
4.1 Introduction to machine learning
85(1)
4.2 The bridge between traditional statistics and machine learning
85(4)
4.3 A basic glossary of machine learning
89(4)
4.4 Regression-based methods
93(1)
4.5 Regression-type methods for categorical outcome variables
94(4)
4.6 Artificial neural networks
98(1)
4.7 Bayes' theorem and Naive Bayes methods
99(2)
4.8 Methods for sequential data
101(7)
4.9 Introduction to natural language processing
108(5)
4.10 Further reading
113(2)
Bibliography
113(2)
5 Software for Patient Care Versus Software for Clinical Research Support: Similarities and Differences
115(14)
5.1 Introduction
115(1)
5.2 Similarities between EHRs and CSDMSs
116(1)
5.3 EHRs are specialized for clinical care and workup
117(1)
5.4 CSDMSs: study participants (subjects) are not necessarily patients
117(1)
5.5 Study protocol: overview
118(1)
5.6 Configuration information
119(1)
5.7 Recruitment and eligibility
120(1)
5.8 Study calendar
121(5)
5.9 Multiinstitutional or multinational research scenarios
126(3)
Bibliography
128(1)
6 Clinical Research Information Systems: Using Electronic Health Records for Research
129(14)
6.1 Biospecimen management systems
130(1)
6.2 Grants management systems
131(1)
6.3 Clinical research workflow support systems
132(2)
6.4 Clinical study data management systems
134(2)
6.5 Using EHRs for research
136(4)
6.6 Effective interoperation between a CSDMS and EHR-related software
140(3)
Bibliography
142(1)
7 Computer Security, Data Protection, and Privacy Issues
143(16)
7.1 Security basics
143(3)
7.2 Special concerns related to personal data
146(1)
7.3 Protecting data
146(2)
7.4 Institutional preparedness
148(1)
7.5 HIPAA matters: calibrating the level of privacy to the level of acceptable risk
149(3)
7.6 A primer on electronic intrusion
152(2)
7.7 State of healthcare systems with respect to intrusion resistance
154(1)
7.8 Role of the US Government
155(4)
Bibliography
157(2)
8 Mobile Technologies and Clinical Computing
159(14)
8.1 Introduction
159(1)
8.2 Uses of mobile devices: historical and recent
160(3)
8.3 Applications in biomedical research
163(2)
8.4 Limitations of mobile devices
165(8)
Bibliography
170(3)
9 Clinical Data Repositories: Warehouses, Registries, and the Use of Standards
173(14)
9.1 Introduction
173(1)
9.2 Operational data store
173(1)
9.3 Data warehouses and data marts
174(6)
9.4 Clinical registries
180(2)
9.5 Encoding data prior to warehousing: standardization challenges
182(2)
9.6 Relationships between healthcare IT and health informatics groups
184(3)
Bibliography
185(2)
10 Core Technologies: Data Mining and "Big Data"
187(18)
10.1 Introduction
187(3)
10.2 An overview of data-mining methodology
190(5)
10.3 Limitations and caveats
195(4)
10.4 The human component
199(1)
10.5 Conclusions
200(1)
10.6 Additional resources for learning
201(4)
Bibliography
203(2)
11 Conclusions: The Learning Health System of the Future
205(12)
11.1 Introduction
205(1)
11.2 Origin and inspiration for the LHS proposal
206(3)
11.3 Challenges of KM/BPR for US healthcare
209(8)
Bibliography
215(2)
Subject Index 217
Dr. Nadkarni has been working in the field of biomedical informatics since 1989, with over 100 peer-reviewed publications in the field. He is the lead developer of TrialDB, an open-source clinical study data management system, which is used at multiple locations nationally and internationally. He is an Associate Editor of the Journal of the American Medical Informatics Association (JAMIA) since 2005, and was elected Fellow of the American College of Medical Informatics (ACMI) in 2002.