Atnaujinkite slapukų nuostatas

Big Data in Psychiatry and Neurology [Minkštas viršelis]

Edited by (School of Psychology, Bond University, Robina, Queensland, Australia)
  • Formatas: Paperback / softback, 384 pages, aukštis x plotis: 229x152 mm, weight: 570 g
  • Išleidimo metai: 16-Jun-2021
  • Leidėjas: Academic Press Inc
  • ISBN-10: 0128228849
  • ISBN-13: 9780128228845
Kitos knygos pagal šią temą:
Big Data in Psychiatry and NeurologyDidesnis paveikslėlis
  • Formatas: Paperback / softback, 384 pages, aukštis x plotis: 229x152 mm, weight: 570 g
  • Išleidimo metai: 16-Jun-2021
  • Leidėjas: Academic Press Inc
  • ISBN-10: 0128228849
  • ISBN-13: 9780128228845
Kitos knygos pagal šią temą:
Pastovi nuoroda: https://www.kriso.lt/db/9780128228845.html
Raktažodžiai:

Big Data in Psychiatry and Neurology provides an up-to-date overview of achievements in the field of big data in Psychiatry and Medicine, including applications of big data methods to aging disorders (e.g., Alzheimer’s disease and Parkinson’s disease), mood disorders (e.g., major depressive disorder), and drug addiction. This book will help researchers, students and clinicians implement new methods for collecting big datasets from various patient populations. Further, it will demonstrate how to use several algorithms and machine learning methods to analyze big datasets, thus providing individualized treatment for psychiatric and neurological patients.

As big data analytics is gaining traction in psychiatric research, it is an essential component in providing predictive models for both clinical practice and public health systems. As compared with traditional statistical methods that provide primarily average group-level results, big data analytics allows predictions and stratification of clinical outcomes at an individual subject level.

  • Discusses longitudinal big data and risk factors surrounding the development of psychiatric disorders
  • Analyzes methods in using big data to treat psychiatric and neurological disorders
  • Describes the role machine learning can play in the analysis of big data
  • Demonstrates the various methods of gathering big data in medicine
  • Reviews how to apply big data to genetics
Contributors xv
Editor's biography xix
Preface xxi
Acknowledgment xxiii
1 Best practices for supervised machine learning when examining biomarkers in clinical populations
Benjamin G. Schultz
Zaher Joukhadar
Usha Nattala
Maria del Mar Quiroga
Francesca Bolk
Adam P. Vogel
1 Introduction
1(1)
2 Data formatting
2(3)
3 Statistical assumptions
5(3)
4 Sample size estimation
8(1)
5 Choosing parsimonious models
9(2)
6 Reduction of data dimensionality
11(4)
6.1 Scaling
12(1)
6.2 Variable selection
12(1)
6.3 Principal component analysis
13(1)
6.4 Linear discriminant analysis
14(1)
7 Performance metrics
15(4)
8 Resampling methods
19(4)
9 Data leakage
23(1)
9.1 Partitioning
23(1)
9.2 Data reduction and scaling
23(1)
9.3 Variable selection
23(1)
9.4 Balancing datasets
24(1)
10 Supervised machine learning classifiers
24(2)
11 Deep learning and artificial intelligence
26(2)
12 Limitations and future directions
28(1)
13 Conclusions
28(1)
References
29(6)
2 Big data in personalized healthcare
Lidong Wang
Cheryl Alexander
1 Introduction
35(1)
2 Characteristics, methods, and software platforms of big data
36(3)
3 Big data in the healthcare area
39(3)
4 Big data and big data analytics in personalized healthcare
42(4)
5 Conclusion
46(1)
Acknowledgment
46(1)
References
46(5)
3 Longitudinal data analysis: The multiple indicators growth curve model approach
Thierno M.O. Diallo
Ahmed A. Moustafa
1 Introduction
51(2)
2 Multivariate dimension reduction techniques: Principal component analysis and factor analysis
53(5)
2.1 Principal component analysis
54(1)
2.2 Factor analysis
55(2)
2.3 Factor analysis and principal component analysis for multiple indicator growth curve models
57(1)
3 Longitudinal measurement invariance
58(2)
4 Multiple indicators growth curve model
60(4)
4.1 The MILCM equations
61(2)
4.2 Specification details
63(1)
5 Steps in fitting an MILCM
64(2)
References
66(3)
4 Challenges and solutions for big data in personalized healthcare
Tim Hulsen
1 Introduction
69(2)
2 Standardization
71(6)
2.1 Interoperability and reusability
71(1)
2.2 Standards for clinical data
72(2)
2.3 Standards for -omics data
74(1)
2.4 Standards for imaging data
75(1)
2.5 Standards for biosample data
76(1)
3 Data sharing and integration
77(7)
3.1 Data ownership
77(1)
3.2 Support for data sharing
78(1)
3.3 Data sharing initiatives
79(2)
3.4 Data integration
81(3)
4 Privacy and ethics
84(3)
4.1 Stricter regulations
84(1)
4.2 Explicit consent
85(1)
4.3 Privacy and ethics in industry
85(2)
5 Teaching data science
87(1)
5.1 Need for more training
87(1)
5.2 Training data science to medical students
87(1)
5.3 Available courses in Clinical Data Science
88(1)
6 Discussion
88(1)
Competing interest statement
89(1)
References
90(5)
5 Data linkages in epidemiology
Sinead Moylett
1 Introduction
95(1)
2 Linking local and national routinely-collected data
96(3)
2.1 Development of diagnostic algorithms: Structured data
98(1)
3 Linking routinely- and non-routinely-collected data
99(1)
4 Linking structured and unstructured routinely-collected data
100(9)
4.1 CRIS and CRATE databases
101(5)
4.2 Development of diagnostic algorithms: Unstructured data
106(3)
5 Conclusion
109(2)
References
111(8)
6 Neutrosophic rule-based classification system and its medical applications
Sameh H. Basha
Areeg Abdalla
Aboul Ella Hassanien
1 Introduction
119(3)
2 Theoretical background
122(4)
2.1 Neutrosophic logic and neutrosophic set
122(1)
2.2 Neutrosophic rule-based classification system
123(3)
3 NRCS medical applications
126(7)
3.1 Neutrosophic rule-based prediction system for toxicity effects assessment of biotransformed hepatic drugs
126(3)
3.2 A predictive model for diabetics using NRCS
129(1)
3.3 A predictive model for seminal quality using NRCS
130(3)
4 Conclusions and future work
133(1)
References
133(4)
7 From complex to neural networks
Nicola Amoroso
Loredana Bellantuono
1 Big data and MRI analyses
137(4)
2 Modeling purposes: Complex networks
141(4)
3 Learning from data
145(5)
4 A multiplex model to diagnose neurodegenerative diseases and anomalous aging
150(2)
References
152(3)
8 The use of Big Data in Psychiatry-The role of administrative databases
Manuel Goncalves-Pinho
Alberto Freitas
1 Introduction
155(1)
2 Big Data, administrative databases, and mental health
156(1)
3 Pros and cons of administrative databases research in mental health
157(5)
4 Conclusions
162(1)
References
163(4)
9 Predicting the emergence of novel psychoactive substances with big data
Robert Todd Perdue
James Hawdon
1 Introduction
167(2)
2 Internet search queries as data
169(2)
3 Methods
171(1)
4 Results
172(2)
5 Discussion and conclusion
174(3)
References
177(4)
10 Hippocampus segmentation in MR images: Multiatlas methods and deep learning methods
Hancan Zhu
Shuai Wang
Liangqiong Qu
Dinggang Shen
1 Introduction
181(3)
2 Patch-based multiatlas labeling for Hippocampus segmentation
184(10)
2.1 Weighted voting label fusion
185(2)
2.2 Local learning-based label fusion
187(1)
2.3 Supervised metric learning for label fusion
188(2)
2.4 An evaluation of different patch-based multiatlas labeling methods
190(4)
3 Deep learning-based methods for Hippocampus segmentation
194(16)
3.1 Multiatlas-based deep learning method for hippocampus segmentation
196(9)
3.2 End-to-end dilated residual dense U-net for hippocampus segmentation
205(5)
4 Conclusion
210(1)
Acknowledgments
211(1)
References
212(5)
11 A scalable medication intake monitoring system
Diane Myung-Kyung Woodbridge
Kevin Bengtson Wong
1 Introduction
217(1)
2 Related work
218(2)
3 System architecture
220(3)
3.1 Smartwatch application
221(1)
3.2 Cloud services
222(1)
3.3 Data storage
222(1)
3.4 Distributed data processing
223(1)
4 Algorithms
223(5)
4.1 Distributed preprocessing
224(2)
4.2 Distributed AutoML and machine learning
226(2)
5 Experiment results
228(8)
5.1 Experiment setting
228(3)
5.2 Results
231(5)
6 Conclusion
236(2)
Acknowledgments
238(1)
References
238(3)
12 Evaluating cascade prediction via different embedding techniques for disease mitigation
Abhinav Choudhury
Shubham Shakya
Shruti Kaushik
Varun Dutt
1 Introduction
241(2)
2 Background
243(2)
3 Method
245(8)
3.1 Dataset
245(1)
3.2 Generating graph embeddings
245(4)
3.3 Cascade prediction
249(4)
3.4 Evaluation metrics
253(1)
4 Results
253(2)
4.1 Cascade prediction using MLP
253(1)
4.2 Cascade prediction using LSTM
253(2)
4.3 Model comparison
255(1)
5 Discussion and conclusions
255(4)
Acknowledgment
259(1)
References
259(4)
13 A two-stage classification framework for epileptic seizure prediction using EEG wavelet-based features
Sahar Elgohary
Mahmoud I. Khalil
Seif Eldawlatly
1 Introduction
263(2)
2 Materials and methods
265(7)
2.1 Dataset
265(1)
2.2 Two-stage zero-crossings wavelet-based framework
266(5)
2.3 Comparative analysis methods
271(1)
3 Results
272(11)
3.1 Stage 1: Interictal and preictal binary classification
272(5)
3.2 Stage 2: Preictal classification into early and late stages
277(6)
4 Discussion
283(1)
5 Conclusions
284(1)
Disclosure statement
285(1)
References
285(2)
14 Visual neuroscience in the age of big data and artificial intelligence
Kohitij Kar
1 Confining the problem space
287(1)
2
Chapter roadmap
288(1)
3 Understanding vision-What do we seek to reveal?
288(5)
3.1 The first generation of neural network models
290(1)
3.2 Next generation of neural network models
291(1)
3.3 Experiments to falsify and improve models
292(1)
4 How to evaluate the current models of vision?
293(4)
4.1 Prediction
293(4)
4.2 Control
297(1)
5 The vision community is coming together to combine data and models
297(4)
5.1 Allen brain observatory
299(1)
5.2 Brain-score
299(1)
5.3 The Algonauts project
300(1)
6 Conclusion
301(1)
References
301(4)
15 Application of big data and artificial intelligence approaches in diagnosis and treatment of neuropsychiatric diseases
Qiurong Song
Tianhui Huang
Xinyue Wang
Jingxiao Niu
Wang Zhao
Haiqing Xu
Long Lu
1 Introduction
305(2)
2 Main data sources
307(3)
2.1 Genomics
307(1)
2.2 EEG signals
308(1)
2.3 Eye movement data
308(1)
2.4 Neuroimaging data
309(1)
2.5 Wearable equipment data
309(1)
3 Main algorithms
310(1)
4 Applications
311(6)
4.1 Early warning
311(1)
4.2 Diagnosis
312(4)
4.3 Prognosis
316(1)
5 Challenges and promising solutions
317(3)
5.1 Privacy and security of patient information
317(2)
5.2 Information island
319(1)
5.3 Storage and analysis capabilities
319(1)
5.4 Lack of specialized personnel
320(1)
6 Conclusions
320(1)
References
321(4)
16 Harnessing big data to strengthen evidence-informed precise public health response
C.V. Asokan
Mohammed Yousif Mohammed
1 Public health
325(1)
2 Global burden of disease
326(2)
2.1 Noncommunicable diseases
327(1)
2.2 Infectious diseases
327(1)
3 Health systems and public health system
328(4)
3.1 Public health surveillance system
329(3)
4 Big data in precision public health
332(1)
5 Case studies
333(2)
5.1 Noncommunicable diseases
333(1)
5.2 Infectious disease: COVID-19
334(1)
References
335(4)
17 How big data analytics is changing the face of precision medicine in women's health
Maryam Panahiazar
Maryam Karimzadehgan
Roohallah Alizadehsani
Dexter Hadley
Ramin E. Beygui
1 Introduction
339(2)
2 The role of big data and deep learning in personalized medicine to empower women's health
341(1)
3 Use case studies
342(5)
3.1 Advanced data analytics on skin conditions from genotype to phenotype
342(2)
3.2 Big data platform to use machine learning on EHR data for personalized medicine in heart failure survival analysis and patient similarity
344(2)
3.3 Large-scale labeling of free-text pathology report for deep learning to improve women's health in breast cancer
346(1)
4 Conclusion
347(1)
Acknowledgements
348(1)
Author contribution
348(1)
References
348(3)
Index 351
Dr. Ahmed Moustafa is the Head of School of Psychology and Professor of Psychology and Computational Modeling at Bond University, Australia. He obtained his BSc in Mathematics and Computer Science at Cairo University, Egypt, and his PhD in Cognitive Science at the University of Lafayette, USA. Dr. Moustafa specializes in computational and neuropsychological studies of addiction, schizophrenia, Parkinsons disease, PTSD, depression, and Alzheimers disease. He is the Editor-in-Chief of Discover Psychology (Springer) and has edited ten books, including Elseviers Cognitive, Clinical, and Neural Aspects of Drug Addiction; The Psychology and Neuroscience of Impulsivity; Cognitive and Behavioral Dysfunction in Schizophrenia; Mental Health Effects of COVID-19; Alzheimers Disease; Cybersecurity and Cognitive Science; Big Data in Psychiatry and Neurology; The Nature of Depression; and Social Cognition in Psychosis.