Artificial Intelligence and Big Data Analytics for Smart Healthcare

Artificial Intelligence and Big Data Analytics for Smart Healthcare
Copyright
Dedication
Contents
List of contributors
Preface: artificial intelligence and big data analytics for smart healthcare: a digital transformation of healthcare primer
	Introduction
	Overview
		List of Abstracts
			Chapter 1 Healthcare in the times of artificial intelligence: setting a value-based context
			Chapter 2 High-level strategy for implementing artificial intelligence (AI) at the Saudi Commission for Health Specialties ...
			Chapter 3 Big data infrastructure: data mining, text mining, and citation context analysis in scientific literature
			Chapter 4 Place attachment theories: a spatial approach to smart health and healing
			Chapter 5 Utilizing IoT-based sensors and prediction model for health-care monitoring system
			Chapter 6 QoS of mobile cloud computing applications in healthcare
			Chapter 7 Analysis of Parkinson’s disease based on mobile application
			Chapter 8 Mobile Partogram—m-Health technology in the promotion of parturient’s health in the delivery room
			Chapter 9 Self-evaluation mobile application on mild cognitive impairment based on Mini-Mental State Examination with bilin...
			Chapter 10 Spatiotemporal Big Data-driven vessel traffic risk estimation for promoting maritime healthcare: lessons learnt ...
			Chapter 11 Neurofeedback using video games for attention-deficit/hyperactivity disorder
			Chapter 12 Medical diagnosis in Alzheimer's disease based on supervised and semisupervised learning
			Chapter 13 A support vector machine–based voice disorders detection using human voice signal
			Chapter 14 COVID-19 detection from X-ray images using artificial intelligence
			Chapter 15 Empowering the One Health approach and health resilience with digital technologies across OECD countries: the ca...
			Chapter 16 An overview of artificial intelligence and Big Data Analytics for smart healthcare: requirements, applications, ...
	Conclusion
	References
Acknowledgments
1 Healthcare in the times of artificial intelligence: setting a value-based context
	1.1 Introduction—mapping the current challenges in the health domain
	1.2 Value-based approach to healthcare
	1.3 Current state of artificial intelligence utilization in the health domain/artificial intelligence metaphors and its con...
	1.4 Conclusion
	References
	Further reading
2 High-level strategy for implementing artificial intelligence at the Saudi Commission for Health Specialties
	2.1 Introduction
	2.2 Literature review
	2.3 Current state of AI utilization at the SCFHS
		2.3.1 Matching prospective trainees (residents) to residency training programs
		2.3.2 Professional accreditation of health-care practitioners
		2.3.3 ML for recommending (individualized) professional development activities and programs
		2.3.4 The utility of natural language processing to improve performance at the SCFHS
		2.3.5 The utility of robotics/RPA to improve performance at the SCFHS
			2.3.5.1 Opportunities for implementing robotics/RPA at the SCFHS
			2.3.5.2 Desired future state of robotics/RPA at the SCFHS
			2.3.5.3 Important enablers and considerations for implementing robotics/RPA at the SCFHS
			2.3.5.4 Potential impact of AI implementation on workforce and its dynamics at the SCFHS
	2.4 AI implementation is an opportunity for successful human–machine collaboration
	2.5 Conclusion and ethical considerations
	References
	Further reading
3 Big data infrastructure: data mining, text mining, and citation context analysis in scientific literature
	3.1 Introduction
	3.2 Literature review
	3.3 Data and methodology
		3.3.1 Data and preprocessing
		3.3.2 Feature engineering
	3.4 Results and discussion
		3.4.1 Training and testing data
		3.4.2 Discussion of ROC curves
		3.4.3 Discussion on precision–recall curves
		3.4.4 Discussion on important features
		3.4.5 Evaluation
	3.5 Concluding remarks
	Appendix A
	References
4 Place attachment theories: a spatial approach to smart health and healing
	4.1 Introduction—smart healthcare, smart-home services, and the place attachment theory
		4.1.1 Contributions
		4.1.2 Linking this study to artificial intelligence and big data analytics
	4.2 Literature review—using place attachment to define “home”
		4.2.1 Home as a place for healing
		4.2.2 Place attachment and the home environment
	4.3 Methodology—case studies
		4.3.1 Case study 1—smart lighting
			4.3.1.1 Smart lighting creating a homely environment
		4.3.2 Case study 2—IoT connectivity of devices
			4.3.2.1 IoT creating homely environments
		4.3.3 Case study 3—personalization of spaces
			4.3.3.1 Smart-home technology in health-care environments
	4.4 Implementation
		4.4.1 A scenario of implementing the three case studies—St George’s Hospital, Port Elizabeth, and a three-dimensional analysis
	4.5 Conclusion and recommendations
	4.6 Future research
	References
5 Utilizing IoT-based sensors and prediction model for health-care monitoring system
	5.1 Introduction
	5.2 Literature review
	5.3 Health-care monitoring system
		5.3.1 System design and implementation
		5.3.2 Blood glucose prediction model
	5.4 Result and discussion
		5.4.1 Health-care monitoring system
		5.4.2 Blood glucose prediction model
	5.5 Conclusion
	References
6 QoS of mobile cloud computing applications in healthcare
	6.1 Introduction
	6.2 Cloud computing and mobile cloud computing
	6.3 QoS in CC and MCC
	6.4 CC and MCC applications in the health area
	6.5 New trends of security of CC in the health area
	6.6 Evaluation of performance and QoS in the health area
	6.7 Conclusion
	References
7 Analysis of Parkinson’s disease based on mobile application
	7.1 Introduction
	7.2 Related work
	7.3 Methods and materials
		7.3.1 Monitoring and data collection
			7.3.1.1 The manual dexterity
			7.3.1.2 The walking test
			7.3.1.3 The spatial memory test
			7.3.1.4 A symptom questionnaire (life quality)
		7.3.2 Data preprocessing
			7.3.2.1 Integration of data sources and data filtering
			7.3.2.2 Data transformation
			7.3.2.3 Extraction of characteristics
	7.4 Experimental results
		7.4.1 The manual dexterity activity
		7.4.2 The walking activity
		7.4.3 The memory activity
	7.5 Conclusion and future work
	References
8 Mobile Partogram—m-Health technology in the promotion of parturient’s health in the delivery room
	8.1 Introduction
	8.2 The Mobile Partogram conception—m-Health technology in parturient care in the delivery room
	8.3 Participatory user-centered interaction design to support and understand the conception of partograma mobile
	8.4 Identifying needs and defining requirements
		8.4.1 Design of alternatives
	8.5 Building an interactive version (high-fidelity prototype)
	8.6 Evaluation (usability)
	8.7 Final considerations
	8.8 Teaching assignments
	References
9 Self-evaluation mobile application on mild cognitive impairment based on Mini–Mental State Examination with bilingual support
	9.1 Introduction
		9.1.1 Our contribution
	9.2 Overview of the Mini–Mental State Examination
	9.3 Our mobile application
		9.3.1 Overview of the solution
		9.3.2 User interface design for seniors and the elderly
		9.3.3 Question types of the evaluation
		9.3.4 Record tracking
	9.4 Preliminary evaluation
		9.4.1 Evaluation with users
		9.4.2 Discussion with selected users
		9.4.3 Feedbacks from nursing domain experts
	9.5 Conclusion and future enhancement
	References
10 Spatiotemporal Big Data-Driven Vessel Traffic Risk Estimation for Promoting Maritime Healthcare: Lessons Learnt from Ano...
	10.1 Introduction
	10.2 Ship domain
	10.3 Proposed method
		10.3.1 Trajectory data interpolation
		10.3.2 Cross area calculation of ship domain
		10.3.3 Ship collision risk assessment
	10.4 Experimental results and analysis
		10.4.1 The verification of Monte Carlo probabilistic algorithm
		10.4.2 Simulate three situations of ship behavior
		10.4.3 AIS data experiment
	10.5 Conclusion
	References
11 Neurofeedback using video games for attention-deficit/hyperactivity disorder
	11.1 Introduction
	11.2 Problems of ADHD
	11.3 Background
		11.3.1 Why neurofeedback
		11.3.2 Limitations of neurofeedback
		11.3.3 Treatments of ADHD
		11.3.4 Supportive treatments
		11.3.5 Neurofeedback training
		11.3.6 Neurofeedback treatment protocols
			11.3.6.1 Alpha protocol
			11.3.6.2 Beta protocol
			11.3.6.3 Alpha/theta protocol
			11.3.6.4 Delta protocol
			11.3.6.5 Gamma protocol
			11.3.6.6 Theta protocol
			11.3.6.7 Low-frequency versus high-frequency training
		11.3.7 Hypothesis
		11.3.8 Data collection
			11.3.8.1 Visit to Hope Center
			11.3.8.2 Observation results
			11.3.8.3 Visit to King Faisal Specialist Hospital
				11.3.8.3.1 Interview discussion
			11.3.8.4 Online surveys
				11.3.8.4.1 Survey results
				11.3.8.4.2 Discussion
		11.3.9 Game architecture
			11.3.9.1 Game scenario
	11.4 Conclusion and future recommendations
	References
	Further reading
12 Medical diagnosis in Alzheimer’s disease based on supervised and semisupervised learning
	12.1 Introduction
	12.2 Notations and review of related work
		12.2.1 Notations
		12.2.2 Linear discriminant analysis
		12.2.3 Review of graph-based semisupervised learning
	12.3 Trace ratio linear discriminant analysis for medical diagnosis: a case study of dementia via supervised learning
		12.3.1 An improved algorithms for solving the trace ratio problem of TR-LDA
			12.3.1.1 Convergence analysis of iterative trace ratio algorithm
			12.3.1.2 Computation analysis
	12.4 Identifying demented patients via TR-LDA
		12.4.1 Data descriptions
		12.4.2 Prediction stage
	12.5 Simulations
		12.5.1 Diagnosis results
		12.5.2 Visualization
	12.6 Compact graph-based semisupervised learning for medical diagnosis in Alzheimer’s disease: a case study of dementia via...
		12.6.1 Review of graph construction
			12.6.1.1 The compact graph construction
			12.6.1.2 Symmetrization and normalization of graph weight
		12.6.2 Identifying demented patients via compact graph semisupervised learning
			12.6.2.1 Model stage
			12.6.2.2 Diagnosis process
			12.6.2.3 Out-of-sample inductive extension for new-coming data
		12.6.3 Simulation
	12.7 Conclusion
	References
	Further reading
13 A support vector machine–based voice disorders detection using human voice signal
	13.1 Introduction
	13.2 Literature review
	13.3 Methodology of support vector machine–based voice disorders detection
		13.3.1 Programming tool
		13.3.2 VOIce ICar fEDerico II (VOICED) database
		13.3.3 Feature extraction
		13.3.4 Voice disorders detection using support vector machine
	13.4 Performance evaluation of proposed support vector machine algorithm for voice disorders detection
	13.5 Research challenges of smart health-care applications
		13.5.1 Data collection
		13.5.2 Data selection
		13.5.3 Expenditure
		13.5.4 New knowledge and skills to learn
		13.5.5 Urban versus rural health
		13.5.6 Linked databases
		13.5.7 Optimizing treatment
		13.5.8 Privacy
	13.6 Research limitations and future research directions
	13.7 Visions and conclusion
	References
14 COVID-19 detection from X-ray images using artificial intelligence
	14.1 Introduction
	14.2 Deep learning in COVID-19 prognosis using X-ray images
	14.3 Classification methods
		14.3.1 Convolutional neural networks
		14.3.2 Transfer learning
	14.4 Results and discussion
		14.4.1 Dataset
		14.4.2 Experimental setup
		14.4.3 Performance measures
		14.4.4 Experimental results
		14.4.5 Discussion
	14.5 Conclusion
	References
15 Empowering the One Health approach and health resilience with digital technologies across OECD countries: the case of CO...
	15.1 Introduction
	15.2 Aims and methodology of this study
	15.3 Findings and suggestions regarding the research questions
		15.3.1 The COVID–19 case in OECD countries: some background information
		15.3.2 Digital technologies in the service of health and healthcare
		15.3.3 Multidimensional framework and future recommendations
	15.4 Conclusion
	References
	Further reading
16 An overview of artificial intelligence and big data analytics for smart healthcare: requirements, applications, and chal...
	16.1 Introduction
	16.2 Requirements of smart health-care applications
		16.2.1 Mission critical applications
		16.2.2 Scalable design
		16.2.3 Cost-effective design
		16.2.4 User-centered design
	16.3 Smart health-care applications using AI and BDA techniques
		16.3.1 Health-care monitoring and keeping well
		16.3.2 Disease diagnosis and prediction
		16.3.3 Drug discovery and development
		16.3.4 Intensive care
		16.3.5 Education and training
	16.4 Challenges
		16.4.1 Large-scale open health-care data
		16.4.2 Technology transfer
		16.4.3 Public acceptance in AI- and BDA-based applications
		16.4.4 Policy establishment
	16.5 Conclusion
	References
Index