Muutke küpsiste eelistusi

Big Data Analytics for Healthcare: Datasets, Techniques, Life Cycles, Management, and Applications [Pehme köide]

Edited by (Senior Lecturer, School of Computer Sciences, Universiti Sains Malaysia, Minden, Penang, Malaysia)
  • Formaat: Paperback / softback, 354 pages, kõrgus x laius: 276x216 mm, kaal: 970 g, 120 illustrations (80 in full color); Illustrations
  • Ilmumisaeg: 24-May-2022
  • Kirjastus: Academic Press Inc
  • ISBN-10: 0323919073
  • ISBN-13: 9780323919074
Teised raamatud teemal:
Big Data Analytics for Healthcare: Datasets, Techniques, Life Cycles, Management, and ApplicationsSuurem pilt
  • Formaat: Paperback / softback, 354 pages, kõrgus x laius: 276x216 mm, kaal: 970 g, 120 illustrations (80 in full color); Illustrations
  • Ilmumisaeg: 24-May-2022
  • Kirjastus: Academic Press Inc
  • ISBN-10: 0323919073
  • ISBN-13: 9780323919074
Teised raamatud teemal:
Püsilink: https://www.kriso.ee/db/9780323919074.html
Märksõnad:
Big Data Analytics and Medical Information Systems presents the valuable use of artificial intelligence and big data analytics in healthcare and medical sciences. It focuses on theories, methods and approaches in which data analytic techniques can be used to examine medical data to provide a meaningful pattern for classification, diagnosis, treatment, and prediction of diseases. The book discusses topics such as theories and concepts of the field, and how big medical data mining techniques and applications can be applied to classification, diagnosis, treatment, and prediction of diseases. In addition, it covers social, behavioral, and medical fake news analytics to prevent medical misinformation and myths. It is a valuable resource for graduate students, researchers and members of biomedical field who are interested in learning more about analytic tools to support their work.
  • Presents theories, methods and approaches in which data analytic techniques are used for medical data
  • Brings practical information on how to use big data for classification, diagnosis, treatment, and prediction of diseases
  • Discusses social, behavioral, and medical fake news analytics for medical information systems
Contributors xiii
Preface xvii
Section I Theories and concepts of big data analytics in healthcare
1 Big data analytics in healthcare: theory, tools, techniques and its applications
C. Manikandan
S. Abirami
K. Gokul
G. Deepalakshmi
1 Introduction
3(2)
1.1 Volume
3(1)
1.2 Velocity
4(1)
1.3 Variety
4(1)
1.4 Other factors influencing in big data
4(1)
2 Challenges in big data analytics
5(1)
2.1 Management of big data
5(1)
2.2 Security and privacy concerns
5(1)
2.3 Scalability
6(1)
3 Data analytics life cycle
6(1)
3.1 Data generation
6(1)
3.2 Big data acquisition in healthcare
7(1)
4 Data analytics during the Covid-19 pandemic
7(2)
5 Big data tools in healthcare
9(1)
5.1 Big data management and analysis
9(1)
6 Summary
10(3)
References
10(1)
Further reading
11(2)
2 Driving impact through big data utilization and analytics in the context of a Learning Health System
Cameron Graydon
Helena Teede
Clair Sullivan
Kushan De Silva
Joanne Enticott
1 Introduction
13(1)
2 What matters for healthcare?
13(1)
3 Global strategies for impact on health
14(1)
4 What is big data?
14(1)
5 Applying big data--precision medicine
15(1)
6 Learning Health System--a paradigm for the future?
15(2)
7 Driving big data utilization in an LHS
17(2)
8 Challenges
19(1)
9 Conclusion
19(4)
Funding statement
20(1)
References
20(3)
3 Classification of medical big data: a review of systematic analysis of medical big data in real-time setup
Ajaypradeep Natarajsivam
R. Sasikala
Katpadi Varadarajan Arulalan
1 Introduction
23(1)
2 Types of data
24(3)
2.1 Attributes of big data
25(1)
2.2 Core big data analysis strategies
25(2)
3 Accountancy of big data analytics in health care domains
27(1)
3.1 Hospital and health hubs
27(1)
3.2 Malignancy detection using big data analytics
27(1)
3.3 Medical intelligence
28(1)
3.4 E-health records
28(1)
3.5 E-medicine
28(1)
3.6 Evolution of new medicines and practices in healthcare
28(1)
4 Machine learning based on big data analytics in real time: autism disease diagnosis
28(2)
5 Open source tools: cloud resources for health care management
30(1)
5.1 Apache "Hadoop"
30(1)
6 Conclusion
31(2)
References
32(1)
4 Towards big data framework in government public open data (GPOD) for health
Najhan Muhamad Ibrahim
Nur Hidayah Ilham Ahmad Azri
Norbik Bashah Idris
1 Introduction
33(1)
2 Related works
34(2)
3 Methodology
36(1)
4 THE finding
37(6)
5 Contribution, limitation, and discussion
43(1)
6 Conclusion
44(5)
References
44(1)
Further reading
45(4)
Section II Big medical data: Techniques, managements, and applications
5 Big data analytics techniques for healthcare
Md. Ashrafuzzaman
Md. Mahmudul Haque Milu
Anika Anjum
Farzana Khanam
Md. Asadur Rahman
1 Introduction
49(1)
2 Big data in healthcare
50(2)
2.1 Structured data
50(1)
2.2 Unstructured data
50(1)
2.3 Semistructured data
51(1)
2.4 Genomic data
51(1)
2.5 Sentiment data
52(1)
2.6 Clinical data
52(1)
3 Characteristics of big data in healthcare
52(1)
3.1 Volume
52(1)
3.2 Velocity
52(1)
3.3 Variety
53(1)
3.4 Value
53(1)
3.5 Variability
53(1)
3.6 Veracity
53(1)
4 Key elements of big data analysis
53(3)
4.1 Data inputs
54(1)
4.2 Functional elements
54(2)
4.3 Human element
56(1)
4.4 Security element
56(1)
5 Big data analytical tools used in healthcare
56(5)
5.1 Hadoop distribution file system
56(1)
5.2 MapReduce
57(1)
5.3 Hive
58(1)
5.4 Pig and PigLatin
59(1)
5.5 ZooKeeper
59(1)
5.6 HBase
60(1)
6 Conclusions
61(2)
References
61(2)
6 Big data analytics in precision medicine
Saurabh Biswas
Yasha Hasija
1 Introduction
63(1)
2 Biomedical big data
63(1)
2.1 Omics data
64(1)
2.2 Electronic health record data
64(1)
3 Challenges associated with big data
64(1)
3.1 Heterogeneous data
64(1)
3.2 High dimensionality
65(1)
3.3 Data quality problems
65(1)
3.4 Frequency of collecting diverse data
65(1)
4 Machine learning techniques for big data analytics
65(1)
5 Methodology
66(3)
5.1 Big data analytics in omics data
66(2)
5.2 Big data analytics in EHR data
68(1)
5.3 Enablers for big medical data analytics
69(1)
6 Applications
69(2)
6.1 Disease subtyping and biomarker discovery
69(1)
6.2 Drug repurposing
70(1)
6.3 Integrating omics data into EHR
71(1)
7 Conclusion
71(2)
References
72(1)
7 Recent advances in processing, interpreting, and managing biological data for therapeutic intervention of human infectious disease
Pritha Chakraborty
Parth Sarthi Sen Gupta
Shankar Dey
Nabarun Chandra Das
Ritwik Patra
Suprabhat Mukherjee
Abbreviations
73(1)
1 Introduction
74(1)
1.1 Need of big data in therapeutic intervention
75(1)
2 Biological data capturing and processing
75(2)
2.1 Architectural framework
75(1)
2.2 Data modeling
76(1)
2.3 Maintenance of threshold quality of data
76(1)
3 Interpretation of processed clinical data
77(1)
3.1 Qualitative approach
77(1)
3.2 Quantitative approach
78(1)
4 Patients' data management for digital therapeutics
78(1)
5 Advantages and limitations
79(1)
6 Conclusion and future direction
80(3)
Acknowledgments
80(1)
References
80(3)
8 Big data analytics for health: a comprehensive review of techniques and applications
Rehab A. Rayan
Christos Tsagkaris
Imran Zafar
Dimitrios V. Moysidis
Andreas S. Papazoglou
1 Introduction
83(1)
2 Literature review
84(4)
2.1 Methodology
84(1)
2.2 Dimensions of big data in health
84(1)
2.3 Big data--based research in health
85(1)
2.4 Big data analytics applications for health
85(3)
3 Discussion
88(1)
3.1 Opportunities and challenges
88(1)
4 Conclusions
89(6)
Acknowledgments
90(1)
References
90(5)
Section III Diagnosis and treatment: Big data analytical techniques, datasets, life cycles, managements, and applications for diagnosis and treatment
9 Recent applications of data mining in medical diagnosis and prediction
Ozge Doguc
Zehra Nur Canbolat
Gokhan Silahtaroglu
1 Introduction
95(1)
2 Big data and the health sector
96(2)
3 A machine learning medical diagnosis model based on patients' complaints
98(1)
4 An early prediction and diagnosis of sepsis in intensive care units
98(2)
5 A machine learning approach to predict creatine kinase test results
100(2)
5.1 Model creation
101(1)
6 Use of artificial intelligence in the prediction of malignant potential of gastric gastrointestinal stromal tumors
102(2)
7 Weekly emotional changes amidst Covid-19: Turkish experience
104(3)
8 Conclusion
107(4)
References
107(4)
10 Big medical data analytics for diagnosis
Omanin Siddiqua Prova
Faiza Ahmed
Jafrin Sultana
Md. Ashrafuzzaman
1 Introduction
111(3)
1.1 Big medical data
111(1)
1.2 Data lifecycle
112(1)
1.3 Impact of big medical data on the healthcare system
112(1)
1.4 Digitized big medical data analytical applications for the health industry
112(2)
2 Big medical data analytics in disease diagnosis
114(6)
2.1 Cardiology
114(1)
2.2 Neurology
115(2)
2.3 Ophthalmology
117(1)
2.4 Respiratory system
118(2)
3 Big medical data analytics tools/algorithms
120(1)
3.1 Machine learning on big medical data analysis for diagnosis
120(1)
3.2 Data mining in big medical data analytics
120(1)
3.3 The Internet of Things and disease prediction
121(1)
4 Challenges
121(1)
5 Future scopes
122(1)
6 Conclusion
122(3)
References
122(3)
11 Big data analytics and radiomics to discover diagnostics on different cancer types
Ebru Aydindag Bayrak
Pinar Kirci
1 Introduction
125(1)
2 Radiomics
125(1)
3 The methodology of radiomics
126(3)
3.1 Image acquisition
127(1)
3.2 Segmentation
127(1)
3.3 Feature extraction
127(1)
3.4 Analysis
127(2)
4 The applications of radiomics on several kinds of cancer types
129(1)
5 Big data
130(2)
5.1 Structured data
130(1)
5.2 Semistructured data
131(1)
5.3 Unstructured data
131(1)
5.4 The components of big data
131(1)
6 Big data analytics
132(2)
7 The similarities and differences of radiomics and big data analytics
134(1)
8 The challenges of radiomics and big data analytics
134(1)
9 The relationship between radiomics and big data analytics
135(1)
10 Discussion
136(1)
11 Conclusion
136(3)
References
136(3)
12 Big medical data, cloud computing, and artificial intelligence for improving diagnosis in healthcare
Mustafa Asim Kazancigil
1 Introduction
139(1)
2 Retrieving patient data from medical apps
140(2)
2.1 Medical apps for cutaneous disorders
140(1)
2.2 Medical apps for cardiovascular diseases
141(1)
2.3 Medical apps for visual and cognitive disorders
142(1)
2.4 New methods in apps for testing blood pressure and blood glucose levels
142(1)
3 Collecting patient data into cloud-based big data repositories
142(2)
3.1 Big data repositories in healthcare
142(1)
3.2 Management and analysis of big data in healthcare
143(1)
3.3 Commercial platforms for healthcare data analytics
144(1)
4 Using artificial intelligence techniques for improving diagnosis
144(3)
4.1 Clinical Information Systems and clinical decision support systems
144(1)
4.2 Al methods used in healthcare
145(2)
5 Conclusions
147(6)
References
148(5)
Section IV Prediction: Big data analytical techniques, datasets, life cycles, managements, and applications for prediction
13 Use of artificial intelligence for predicting infectious disease
Suna Kang
Donghyun Lee
1 Introduction
153(1)
2 Mathematical modeling of infectious diseases and their development
153(5)
2.1 SIR and SEIR
153(3)
2.2 Agent-based model
156(2)
3 Predicting infectious diseases using artificial intelligence
158(3)
3.1 Big data
158(1)
3.2 Al
159(2)
4 Conclusion
161(4)
References
162(3)
14 Hospital data analytics system for tracking and predicting obese patients' lifestyle habits
Liew Set Yee
Pantea Keikhosrokiani
1 Introduction
165(1)
2 Related works
166(1)
2.1 Existing habit-based healthcare systems with analytical features
166(1)
2.2 Big data and predictive analytics in healthcare
166(1)
2.3 Big data and Clinical Decision Support Systems
166(1)
3 Development methodology
167(1)
4 System design and implementation
168(3)
4.1 System modules and use case diagram
168(2)
4.2 System architecture design and predictive analytics
170(1)
4.3 Implementation strategy
171(1)
4.4 Testing strategy
171(1)
5 Data analytics, results, and user interface
171(5)
5.1 Dataset
171(2)
5.2 Predictive analytics using machine learning
173(3)
5.3 User interface design
176(1)
6 Discussion and conclusion
176(3)
Acknowledgments
178(1)
References
178(1)
15 Predictions on diabetic patient datasets using big data analytics and machine learning techniques
Pratiyush Guleria
1 Introduction
179(1)
1.1 Challenges of healthcare data
180(1)
2 Big data analytics using mapreduce, Pig, Hive, and Spark
180(3)
2.1 Hadoop MapReduce framework
181(1)
2.2 Apache Pig
181(1)
2.3 Apache Hive
181(1)
2.4 Apache Spark
182(1)
3 Methodology adopted
183(14)
3.1 Big data and machine learning techniques for healthcare
189(8)
4 Conclusion
197(4)
References
198(3)
16 Skin cancer prediction using big data analytics and Al techniques
Piyush Kumar
Rishi Chauhan
Radhika Goyal
Nishi Bhati
Shubham Garg
Shucbi Mala
1 Introduction
201(3)
1.1 Dimensions of big data
201(2)
1.2 Types of big data
203(1)
1.3 Big data analytics
203(1)
1.4 Platforms of big data analytics
204(1)
2 Hadoop
204(1)
3 Spark
204(1)
4 Literature review
205(2)
5 Methodology
207(3)
5.1 Dataset
208(1)
5.2 Device/platform used
208(1)
5.3 Techniques/models/algorithms
208(1)
5.4 Logistic regression
208(1)
5.5 Support vector machine
208(1)
5.6 Gradient boosting
209(1)
5.7 VGG19
209(1)
5.8 InceptionResNetV2
209(1)
5.9 Mobile Ne tSSD
209(1)
5.10 MelConvo2d
210(1)
6 Data visualization and analysis
210(2)
7 Results and discussion
212(4)
7.1 Model implementation of combination of logistic regression, support vector machine, and gradient boosting
212(1)
7.2 Model implementation using VGG19 architecture
213(1)
7.3 Model implementation of lnceptionResNetV2
214(1)
7.4 Model implementation of MobileNet SSD
214(1)
7.5 Model implementation MelConvo2D
215(1)
8 Conclusion
216(5)
References
217(4)
Section V Big medical fake news analytics for preventing medical misinformation and myths
17 COVID-19 fake news analytics from social media using topic modeling and clustering
Sherrylin Anak John
Pantea Keikhosrokiani
1 Introduction
221(1)
2 Background and related work
221(1)
2.1 Misinformation and fake news
222(1)
2.2 Related studies of misinformation and medical fake news on social media related to COVID-19
222(1)
3 Methodology
222(1)
3.1 Data collection
222(1)
3.2 Topic modeling
223(1)
3.3 Programming tools
223(1)
4 Data ana Vysis and results (COVID-19 news classification)
223(7)
4.1 COVID-19 news dataset
223(1)
4.2 Data cleaning and data preprocessing
224(1)
4.3 Initial analysis and data exploration
224(3)
4.4 LDA topic modeling
227(3)
5 Conclusion
230(3)
Acknowledgments
231(1)
References
231(2)
18 Big medical data mining system (BigMed) for the detection and classification of COVID-19 misinformation
Nurul Husna Binti Rosli
Pantea Keikhosrokiani
1 Introduction
233(1)
2 Background and related works
233(1)
3 Development methodology
234(1)
4 System design and implementation
234(5)
4.1 System architecture and module design
234(2)
4.2 Use case diagram
236(1)
4.3 System interface design
236(2)
4.4 Implementation strategy
238(1)
5 Data analytics and user interface
239(1)
5.1 Dataset and data preprocessing
239(1)
5.2 News detection and classification
239(1)
5.3 Analytical dashboard
239(1)
6 System testing and evaluation
240(3)
6.1 Testing strategy
240(3)
7 Conclusion
243(4)
Acknowledgments
244(1)
References
244(3)
Section VI Challenges and future of big data in healthcare
19 Privacy security risks of big data processing in healthcare
Zhihan Lv
Liang Qiao
1 Introduction
247(1)
2 Related work
247(1)
2.1 HBD mining
247(1)
2.2 Privacy issues of HBD
248(1)
2.3 Solution of the privacy problem of HBD
248(1)
3 Methodology
248(7)
3.1 Big data analysis in China's healthcare sector
248(1)
3.2 Key technologies of HBD mining
248(2)
3.3 Establishment of indicator system for privacy and security risk assessment of HBD
250(1)
3.4 Assessment model for privacy security risk
251(4)
4 Results
255(7)
4.1 Analysis on the development status of China's medical and healthcare field
255(1)
4.2 Analysis of medical and healthcare costs of major diseases in China
256(1)
4.3 Testing of privacy and security risk assessment model for HBD in cloud environment
257(3)
4.4 Application of parallel random forest algorithm in hospital intelligent guidance
260(2)
5 Conclusion
262(3)
Acknowledgment
262(1)
References
262(3)
20 Opportunities and challenges in healthcare with the management of big biomedical data
Gopi Battineni
1 Introduction
265(1)
2 Biomedical data types and role of machine learning
266(3)
2.1 Electronic health records
266(1)
2.2 Medical scan images
267(2)
3 Current big data challenges in healthcare
269(3)
3.1 Big data and healthcare
269(2)
3.2 Big data challenges in healthcare
271(1)
4 Healthcare data management and its limitations
272(1)
4.1 Data interoperability
272(1)
4.2 Data quality
272(1)
4.3 Data insecurity
273(1)
4.4 Policy settings
273(1)
5 Conclusion
273(4)
References
273(4)
21 Future direction for healthcare based on big data analytics
Maria Jose Sousa
Paul Barach
Antonio Pesqueira
1 Introduction
277(1)
2 Theoretical framework
277(3)
2.1 Leadership conceptual framework
277(1)
2.2 Big data analytics and Al in the health sector
278(2)
3 Empirical methodological approach
280(2)
3.1 Results
281(1)
4 Discussion
282(2)
5 Implications and future research
284(1)
5.1 Theoretical implications of the study findings
284(1)
5.2 Policy implications
284(1)
5.3 Future research avenues
284(1)
6 Conclusions
284(7)
Annex 1
285(1)
Questionnaire
285(1)
References
286(5)
Section VII Case studies of big data in healthcare arena
22 Big data in orthopedics: between hypes and hopes
Carlo Biz
Nicola Luigi Bragazzi
1 Introduction
291(2)
2 Roles and applications of epidemiological big data in current orthopedics research
293(2)
3 Roles and applications of molecular big data in current orthopedics research
295(1)
4 Roles and applications of big data generated by imaging techniques and wearable technologies/smart sensors in current orthopedics research
295(1)
5 Roles and applications of infodemiological big data in current orthopedics research
296(1)
6 "Participatory orthopedics": integrating basic and translational orthopedics and citizen science
296(1)
7 Conclusions and future prospects
297(4)
References
297(4)
23 Predicting onset (type-2) of diabetes from medical records using binary class classification
Md Habib Al Mamun
Pantea Keikhosrokiani
1 Introduction
301(1)
1.1 Background of the study
301(1)
1.2 Problem statement, objectives, and scope of the study
301(1)
2 Paper review
301(3)
2.1 Defining the field
301(2)
2.2 Related works
303(1)
3 Proposed methodology
304(2)
3.1 Model diagram
304(1)
3.2 Brief description of algorithms used
304(1)
3.3 Data mining tools
305(1)
3.4 Dataset
305(1)
3.5 Evaluation measures
305(1)
4 Result and discussion
306(5)
4.1 Classifier's performance based on of classified instance
306(1)
4.2 Confusion matrix
307(1)
4.3 F-measure
307(1)
4.4 Precision
307(1)
4.5 Recall
308(1)
4.6 Accuracy
309(1)
4.7 Comparative analysis summary
310(1)
5 Conclusion
311(2)
References
311(2)
24 Screening programs incorporating big data analytics
Kevin Sheng-Kai Ma
1 Introduction: disease screening and screening programs
313(3)
1.1 Goals and measures for screening programs
313(1)
1.2 Measures and utility of a screening program
314(1)
1.3 Databases and training sets of screening programs
314(1)
1.4 Nationwide screening programs
314(2)
2 Evidence-based medicine for big data analytics--facilitated screening programs
316(3)
2.1 Principles of evidence-based medicine
316(1)
2.2 Gap between clinical research and best practices
317(1)
2.3 Hierarchy and levels of clinical evidence and information
318(1)
3 Screening programs incorporating big data analytics
319(3)
3.1 Cancer screening programs in the era of big data analytics
319(1)
3.2 Diabetes screening programs in the era of big data analytics
320(1)
3.3 Drug allergy screening in the era of big data analytics
321(1)
4 Challenges of big data--acilitated screening programs
322(2)
4.1 Acquisition of high-quality clinical data
322(1)
4.2 Overdiagnoses in big data--facilitated screening programs
322(1)
4.3 External validation with prospective studies
323(1)
4.4 Ensuring representativeness and mitigating bias
323(1)
5 Conclusions: toward next generation big data analytics--facilitated disease screening
324(5)
References
324(5)
Index 329
Pantea Keikhosrokiani is a Senior Lecturer at the School of Computer Sciences, Universiti Sains Malaysia (USM; Penang, Malaysia). She was a teaching fellow at the National Advanced IPv6 Centre of Excellence (Nav6), USM. She has received her PhD in Service System Engineering, Information System, and her masters degree in information technology from the School of Computer Sciences, USM. She has been graduated in Bachelor of Science in Electrical Engineering Electronics. Her articles have been published in distinguished edited books and journals including Elsevier (Telematics & Informatics), Springer (Cognition, Technology, & Work), Taylors and Francis and IGI global, and have been indexed by ISI, Scopus and PubMed. Her recent book is published by Elsevier entitled Perspectives in The Development of Mobile Medical Information Systems: Life Cycle, Management, Methodological Approach and Application. Her areas of interest for research and teaching are Information Systems Development, Behavior-change support systems, Database Systems, Health and Medical Informatics, Business Informatics, Location-Based Mobile Applications, Big Data, and Technopreneurship.