Big Data in Oncology: Impact, Challenges, and Risk Assessment

Cover
Half Title
Series
Title
Copyright
Dedication
Contents
Preface
Acknowledgement
List of Figures
List of Tables
List of Reviewers
List of Contributors
List of Abbreviations
1 Big Data Analysis – A New Revolution in Cancer Management
1.1 Introduction
1.2 Big Data for Personalized Medicine
1.3 Big Data Analytics in Oncology: Challenges
1.3.1 Data acquisition
1.3.2 Ensuring representativeness and mitigating bias
1.3.3 Sources of big data
1.3.3.1 Media
1.3.3.2 Cloud
1.3.3.3 Web
1.3.3.4 Internet of Things (IoT)
1.4 Databases
1.4.1 National Cancer Databases
1.4.2 Cancer genomics databases
1.4.3 Commercial–private databases
1.4.4 The practical applicability of various sources of big data in cancer care
1.5 Inferring Clinical Information with Big Data
1.5.1 Utilization of administrative records for cancer care
1.5.2 Big data and cancer research
1.5.3 FAIR data
1.5.4 Cancer genome sequencing of humans
1.5.5 High-throughput sequence analysis
1.5.6 Sequencing genomes of other organisms
1.5.7 Transcriptome analysis for better cancer monitoring
1.5.8 Diagnostic modeling and machine learning algorithms
1.5.9 Disease prognosis
1.6 Correlation of Clinical Data with Cancer Relapses
1.7 Conclusion
2 Implication of Big Data in Targeted Therapy of Cancer
2.1 Introduction
2.1.1 Big data in medicine
2.1.2 The shifting paradigm in medical research
2.2 Changes in Research
2.2.1 Changes in study design
2.2.2 New study design
2.2.3 Umbrella design
2.2.4 Platform trials
2.2.5 Adverse drug events (ADE)
2.2.6 Real-world evidence (RWE)
2.3 Big data: technology and security concern
2.3.1 Utility of big data
2.3.2 Daily diagnostics
2.3.3 Quality of care measurements
2.3.4 Biomedical research
2.3.5 Personalized medicine
2.3.6 FAIR data
2.4 Archiving and Sharing of Biomolecular Patient Data in Repositories
2.5 Data Sources of Big Data in Medicine
2.5.1 Integration of big data in head and neck cancer (HNC)
2.5.2 Challenges and future perspectives
2.5.3 Archiving and sharing of biomolecular patient data in repositories and databases
2.6 Conclusion
3 Big Data and Precision Oncology in Healthcare
3.1 Introduction
3.1.1 Precision medicine
3.1.2 Big data and its metaphors in healthcare
3.2 Precision Medicine (PM), Biomarkers, and Big Data (BD)
3.2.1 BD’s influence and predictions in precision oncology
3.2.2 Impact of BDs in radiology and biomarker-related datasets
3.3 Electronic Health Records (EHR) and Precision Oncology
3.4 BD Predictive Analytics and Analytical Techniques
3.5 Sources of Data for BD
3.6 BD Exchange in Radiation Oncology
3.6.1 Data integration
3.6.2 Data interoperability
3.7 Clinical Trial Updates on Precision Medicine
3.8 Challenges and Future Perspectives
3.9 Conclusion
4 Big Data in Oncology: Extracting Knowledge from Machine Learning
4.1 Introduction
4.2 Application of Healthcare Big Data
4.2.1 Internet of Things (IoT)
4.2.2 Digital epidemiology
4.3 Big Data Analytics in Healthcare
4.3.1 Machine learning for healthcare big data
4.3.2 Deep learning for healthcare big data
4.3.3 Drug discovery
4.3.4 Medical imaging
4.3.5 Alzheimer’s disease
4.3.6 Genome
4.4 Tools and Tasks
4.4.1 Supervised learning
4.4.2 Linear models
4.4.3 Decision tree models
4.4.4 Ensemble models
4.4.5 Neural networks
4.4.6 Unsupervised learning
4.4.7 Medical data resources
4.4.8 EMR
4.4.9 Data curation challenges
4.4.10 Data extraction and transfer
4.4.11 Data imputation
4.4.12 Clinical validation
4.5 Applications
4.5.1 Diagnosis and early detection
4.5.2 Cancer classification and staging
4.5.3 Evaluation and prediction of treatment reactions
4.6 Conclusion
5 Impact of Big Data on Cancer Care and Research
5.1 Introduction
5.2 What Is Big Data?
5.3 The Outcome of Big Data on the Cancer Care/Research
5.3.1 Daily diagnostics
5.3.2 Population health management
5.3.3 Biomedical research
5.3.4 Personalized medicine
5.3.5 Cancer genome sequencing
5.3.6 Transcriptome analysis monitoring cancer better
5.3.7 Clinician decision support
5.3.8 Incorporating machine learning algorithms for diagnostic modeling
5.3.9 Presenting greater clarity on disease prognosis
5.3.10 Feasible responses for cancer relapses through clinical data
5.3.11 Pathology
5.3.12 Quality care measurements
5.3.13 FAIR data
5.4 Database for Cancer Research
5.4.1 Cancer Genomics Hub
5.4.2 Catalog of Somatic Mutations in Cancer
5.4.3 Cancer Program Resource Gateway
5.4.4 Broad’s GDAC
5.4.5 SNP500Cancer
5.4.6 canEvolve
5.4.7 MethyCancer
5.4.8 SomamiR
5.4.9 cBioPortal
5.4.10 GEPIA Database
5.4.11 Genomics of Drug Sensitivity in Cancer
5.4.12 canSAR
5.4.13 NONCODE
5.5 Bioinformatics Tools for Evaluating Cancer Prognosis
5.5.1 UCSC Cancer Genomics Browser
5.5.2 Cancer Genome Work Bench
5.5.3 GENT2
5.5.4 PROGgeneV2
5.5.5 SurvExpress
5.5.6 PRECOG
5.5.7 Oncomine
5.5.8 PrognoScan
5.5.9 GSCALite
5.5.10 UALCAN
5.5.11 CAS-viewer
5.5.12 MEXPRESS
5.5.13 CaPSSA
5.5.14 TCPAv3.0
5.5.15 TRGAted
5.5.16 MethSurv
5.5.17 TransPRECISE and PRECISE
5.6 Conclusion
6 Big Data in Disease Diagnosis and Healthcare
6.1 Introduction
6.2 Concepts of BD in Disease Diagnosis and Healthcare
6.2.1 BD and cancer diagnosis
6.2.2 BD platform in healthcare
6.3 Predictive Analysis, Quantum Computing, and BD
6.3.1 Predictive analytics
6.3.2 Predictive analysis in health records and radiomics
6.3.3 Advances in quantum computing
6.4 Challenges in Early Disease Detection and Applications of BD in Disease
6.4.1 BD in cancer diagnosis
6.4.2 BD in the diagnosis of bipolar disorder
6.4.3 BD in orthodontics
6.4.4 BD in diabetes care
6.4.5 BD role in infectious diseases
6.4.6 BD analytics in healthcare
6.5 Data Mining in Clinical Big Data
6.6 BD and mHealth in Healthcare
6.7 Utility of BD
6.8 Challenges and Future Perspectives
6.9 Conclusion
7 Big Data as a Source of Innovation for Disease Diagnosis
7.1 Introduction
7.1.1 Data
7.1.2 Big data
7.2 Electronic Health Records
7.3 Digitization of Healthcare and Big Data
7.4 Healthcare and Big Data
7.4.1 Descriptive analytics
7.4.2 Diagnostic analytics
7.4.3 Predictive Analytics
7.4.4 Prescriptive analytics
7.5 Big Data Analytics in Healthcare
7.5.1 Image analytics in healthcare
7.6 Big Data in Diseases Diagnosis
7.6.1 Comprehend the issue we are attempting to settle (need to treat a patient with a specific type of cancer)
7.6.2 Distinguish the cycles in question
7.6.2.1 Determination and testing (identify genetic mutation)
7.6.2.2 Results investigation including exploring treatment choices, clinical preliminary examination, hereditary examination, and protein investigation
7.7 Meaning of Treatment Convention, Perhaps Including Quality or Protein Treatment
7.8 Screen Patients and Change Treatment Depending on the Situation
7.8.1 The patient uses web-based media to archive general insight
7.8.2 Recognize the data needed to tackle the issue
7.8.2.1 Patient history
7.8.2.2 Blood, tissue, test results, etc.
7.8.2.3 Measurable consequences of treatment choices
7.8.2.4 Clinical preliminary information
7.8.2.5 Hereditary qualities information
7.8.2.6 Protein information
7.8.2.7 Online media information
7.9 Accumulate the Information, Process It, and Examine the Outcomes
7.9.1 Begin treatment
7.9.2 Screen patients and change treatment on a case-by-case basis
7.10 Conclusion
8 Various Cancer Analysis Using Big Data Analysis Technology – An Advanced Approach
8.1 Introduction
8.2 Predictive Analysis and Big Data in Oncology
8.3 Application of Big Data Analytics in Biomedical Science
8.4 Data Analysis from Omics Research
8.5 Oncology Predictive Data Analysis: Recent Application and Case Studies
8.5.1 Population health management
8.5.2 Pathology
8.5.3 Radiomics
8.6 Utilizing Cases for the Future
8.6.1 Decision-making assistance for clinicians
8.6.2 Genomic risk stratification
8.7 Challenges for Big Data Analysis and Storages
8.7.1 Current challenges
8.7.2 Perspectives and challenges for the future
8.7.3 Data acquisition
8.7.4 Prospective validation of the algorithm
8.7.5 Interstation
8.8 Big Data in Cancer Treatment
8.8.1 The cancer genome atlas (TCGA) research network
8.8.2 The International Cancer Genome Consortium (ICGC)
8.8.3 The cancer genome hub
8.8.4 The cosmic database
8.9 Conclusion
9 Dose Prediction in Oncology using Big Data
9.1 Introduction
9.1.1 Data should be reviewed and organized
9.1.2 Information database management
9.2 Significance of “Big Data”
9.2.1 Requirement of big data (BD)
9.2.2 Medical big data analysis
9.2.3 The application of big data in the therapy of head and neck cancer/melanoma (Hd.Nk.C)
9.3 Efficacy of BD
9.3.1 Diagnostics are carried out daily
9.3.2 Determining the quality level of care
9.3.3 Biological and medical research
9.3.4 Personalized medication
9.4 Fair Data
9.5 Ontologies are used to extract high-quality data
9.5.1 Procedure for developing a predictive model
9.6 Standard Statistical Techniques
9.6.1 Machine learning techniques (ML)
9.6.2 Support vector machines
9.6.3 Artificial neuron network
9.7 Deep Learning
9.7.1 Big data in the field of radioactivity oncology
9.7.2 ML and AI in oncology research
9.8 Correction of the Oncology Risk Stratification Gap
9.8.1 Current use cases for oncology predictive analysis
9.8.2 Management of the general population’s health
9.8.2.1 Radiomics
9.8.2.2 Pathology
9.8.3 Advanced used cases
9.8.3.1 Medical decision support
9.8.3.2 Classification of genetic risk
9.9 Challenges Faced in Analytics in Cancer
9.9.1 Information gathering
9.9.2 Algorithm validation in the future
9.9.3 Mitigation of bias and representation
9.9.4 Predictive analytics is ready to take the next step in precision oncology
9.9.5 Machine learning – ML
9.9.6 Diagnosis, assessment, and consultation of patients
9.9.6.1 In the part, diagnose, assess, and consult with patients
9.9.6.2 Detection of a crime using computer technology
9.9.6.3 Making use of a computer to help in diagnosing
9.10 Evaluation and Recommendations
9.11 Obtaining 3D/4D CT Images
9.11.1 Making an image from the ground up
9.11.2 Image fusion/registration
9.11.3 Image segmentation and reshaping software that works automatically
9.12 Treatment Preparation
9.12.1 Making use of data to influence treatment planning
9.12.2 Automated planning procedure for self-driving vehicles
9.13 Treatment Administration and Quality Control
9.13.1 Quality control and conformance assurance
9.14 In This Part, We Will Go Through How to Give the Therapy
9.14.1 Patients are given two and a half follow-ups
9.14.2 Radiomics in radiotherapy for “precise medicine”
9.15 General Discussion
9.15.1 The issues with big data in radiation oncology
9.15.2 The use of machine learning algorithms offers both advantages and disadvantages
9.15.3 How accurate are the investigators’ findings, according to them?
9.15.4 What changes would you make to the stated results?
9.15.5 The influence on healthcare procedure automation
9.15.6 The influence of precision medicine on clinical decision-making assistance in radiation oncology
9.15.7 Closing comments
9.16 Future Opportunities and Difficulties
9.17 The learning health system is a future vision
9.17.1 Consequences for future clinical research
9.17.2 Databases and archives of biomolecular patient data should be preserved and disseminated
9.18 Conclusion
10 Big Data in Drug Discovery, Development, and Pharmaceutical Care
10.1 Introduction
10.2 Role of BD in Drug Candidate Selection, Drug Discovery
10.2.1 CADD, QSAR, and chemical data-driven techniques
10.2.2 Biological BD
10.2.3 Applications of BD in drug discovery
10.3 Drug–Target Interactions (DTI)
10.4 BD Predictive Analytics and Analytical Techniques
10.4.1 ML- and DL-based analytical techniques
10.4.2 Natural language processing
10.5 BD and Its Applications in Clinical Trial Design and Pharmacovigilance
10.5.1 Clinical trial design
10.5.2 Pharmacovigilance
10.6 Assessing the Drug Development Risk Using BD
10.7 Advantages of BD in Healthcare
10.8 BD Analytics in the Pharmaceutical Industry
10.9 Conclusion
11 Targeted Drug Delivery in Cancer Tissue by Utilizing Big Data Analytics
11.1 Introduction
11.2 Application of Big Data in New Drug Discovery
11.2.1 Involvement of data science in drug designing
11.3 Need for This Approach
11.3.1 Drug discovery
11.3.2 Research and development
11.3.3 Clinical trial
11.3.4 Precision medicine
11.3.5 Drug reactions
11.3.6 Big data and its pertinence inside the marketing sector
11.4 Barriers
11.4.1 Cellular defenses
11.4.2 Organellar and vesicular barriers
11.4.3 A novel strategy for therapeutic target identification
11.4.4 Data integration on drug targets
11.5 AI Approaches in Drug Discovery
11.6 Several Approaches Exist for AI to Filter Through Large Amounts of Data
11.6.1 Machine learning
11.6.2 Regularized regression
11.6.3 Variants in the deep learning model
11.6.4 Protein modeling and protein folding methods
11.6.5 The RF method
11.6.6 SVM regression model
11.6.7 Predictive toxicology
11.7 Implementation of Deep Learning Models in De Novo Drug Design
11.7.1 Autoencoder
11.7.2 Deep belief networks
11.8 Future Prospective
11.9 Conclusion
12 Risk Assessment in the Field of Oncology using Big Data
12.1 Introduction
12.1.1 What is big data?
12.1.2 The potential benefits of big data
12.1.3 Determining what constitutes “big data”
12.2 Biomedical Research using Big Data
12.3 The Big Data “Omics”
12.4 Commercial Healthcare Data Analytics Platforms
12.4.1 Ayasdi
12.4.2 Linguamatics
12.4.3 IBM Watson
12.5 Big Data in the Field of Pediatric Cancer
12.5.1 Data
12.5.2 Research supported a medicine cancer register
12.5.3 Epidemiologic descriptive analysis
12.6 The Study of Genomics
12.7 Data Sharing Faces Technical Obstacles and Barriers
12.7.1 Which data should be taken into account, and also how they should be managed?
12.7.2 Data collection and administration
12.7.3 The data deluge
12.8 Cancer in Kids in Poor Countries
12.8.1 Screening and diagnosis
12.8.2 Distribution as well as identifying
12.9 Gaps in Oncology Risk Stratification Strategies
12.10 Predictive Analytics of Tumors: Presently Employed Case Studies
12.10.1 Management of public health
12.10.2 Radiomics
12.11 Big Data in Healthcare Presents Several Challenges
12.11.1 Storage
12.11.2 Cleaning
12.11.3 Format unification
12.11.4 Approximation
12.11.5 Pre-processing of pictures
12.12 Case Studies for Future Applications
12.12.1 Support for clinicians’ decisions
12.12.2 Stratification of genomic risk
12.13 The Next Breakthrough in Exactitude Medicine Is Prophetical Analytics
12.13.1 Perspectives for the future
12.13.2 Clinical trials and the development of new therapies
12.14 Conclusion
13 Challenges for Big Data in Oncology
13.1 Oncology
13.2 Big Data
13.3 Utility of Big Data
13.3.1 In every day diagnostics
13.3.2 Nature of care estimations
13.3.3 Biomedical exploration
13.3.4 Customized medication
13.3.5 FAIR information
13.3.6 Data sourced elements of big data in medicine
13.4 Big Data in Oncology
13.5 Ethical and Criminal Troubles for the Powerful Use of Big Data in Healthcare
13.6 Challenges with Big Data in Oncology
13.6.1 Data acquisition
13.6.2 Impending validation of algorithms
13.6.3 Representativeness and mitigating bias
13.6.4 Stores and datasets for documenting and sharing biomolecular patient information
13.7 Big Data Challenges in Healthcare
13.7.1 Capture
13.7.2 Cleaning
13.7.3 Capacity
13.7.4 Security
13.7.5 Stewardship
13.7.6 Questioning
13.7.7 Detailing
13.7.8 Perception
13.7.9 Refreshing
13.7.10 Sharing
13.8 Big Data Applications in Healthcare
13.9 Conclusion
Index
About the Editors