Index
Big Data Analytics and Intelligence: A Perspective for Health Care
ISBN: 978-1-83909-100-1, eISBN: 978-1-83909-099-8
Publication date: 30 September 2020
This content is currently only available as a PDF
Citation
(2020), "Index", Tanwar, P., Jain, V., Liu, C.-M. and Goyal, V. (Ed.) Big Data Analytics and Intelligence: A Perspective for Health Care, Emerald Publishing Limited, Leeds, pp. 281-289. https://doi.org/10.1108/978-1-83909-099-820201022
Publisher
:Emerald Publishing Limited
Copyright © 2020 Emerald Publishing Limited
INDEX
Accuracy
, 51
Activation functions
, 43
Actuators
, 140, 148
Adaptive boosting (AdaBoost)
, 48–49
Administrative data
, 79
Affordable Care Act
, 120
Affymetrix algorithm
, 131
Air quality
, 99–101
Alcoholism
, 231
Amazon Web Services
, 21
American Recovery and Reinvestment Act (ARRR)
, 117
American Telemedicine Association (ATA)
, 247
Analytical tools
, 4
Annual Health Survey (AHS)
, 63
Apache Pig
, 21
Apollo TeleHealth Services (ATHS)
, 250
Arduino
, 142
Artificial intelligence (AI) (see also Business intelligence (BI))
, 32, 57, 66, 94, 207, 224
Artificial neural network (ANN)
, 234–235, 267–269
ATMEGA328P microcontroller
, 141–142, 144
Automatic tomography
, 174
Autumn eats
, 229–230
Averaging
, 49–50
Bagging technique
, 40, 49
“Banyan of Knowledge” system
, 56
Barometric pressure
, 102
Base learners (see First-level learners)
Bayes theorem
, 35, 270–271
Bell’s palsy
, 174, 176
Beta-blockers
, 206
Big data (BD)
, 17–18, 116, 207, 264
anatomy
, 123–126
definitions in health sector
, 18
methods and technology progress in
, 118–120
needs in health sector
, 18–19
Big data analytics (BDA) (see also Computer-aided big healthcare data analytics; Predictive big data analytics in healthcare)
, 17–18, 56, 59–61, 66–67, 118
achievements
, 71
analysis
, 62–71
applications in health care
, 4–15
challenges
, 23–24, 71–72
concept and emergence of big data
, 59
curing cancer
, 9–10
data as fuel of modern economy
, 57–59
EHRs
, 19
EMRs
, 19
health care analytics environment
, 19
historical perspective
, 65–66
and intelligence
, 2–4
internet of things
, 20
need for security and a mechanism to reducing fraud
, 11–12
objectives
, 61
opportunities in health through BDA use
, 21–23
research methodology
, 61
sensor data
, 19–20
sources of data, methods, and challenges
, 4–6
strategies to overcoming challenges of BDA in health sector
, 24–25
techniques, tools, and technologies in health sector
, 20–21
Big Data to Knowledge (BD2K)
, 119, 127
Big Healthcare Data (BHD)
, 119
BMP180 Breakout
, 102
Body mass index (BMI)
, 272
Boosting
, 48–49
Bootstrap aggregation (see Bagging technique)
Botulinum toxin
, 177
Breast cancer (BC)
, 190
related work on BC prediction
, 190–192
Breastfeeding
, 231
Brownian movement
, 101
Business intelligence (BI)
, 153, 155
contribution
, 154–155
data warehouse design
, 160–161
dataset
, 161–162
ETL process
, 163
evolution
, 156
in healthcare industry and benefits
, 156–157
implementation
, 167–170
literature survey
, 157–159
problem identification
, 159
vision
, 154
workflow
, 159
Business models of telehealth
, 249–252
C4.5 decision tree algorithm technique
, 275
Cadmium Sulfide (CdS)
, 143
Cancer (see also Breast cancer (BC))
, 227
Carbohydrates
, 226, 231
deficiency
, 231
Carbon filter
, 100
Carbs (see Carbohydrates)
CART techniques
, 40
Cassandra
, 84
Cells
, 224–225
Central facial palsy
, 174
Chi-square
algorithm
, 38
test
, 210
Chip
, 142
Chronic facial paralysis
, 177
Chronic kidney disease (CKD)
, 276
Citizen-consumer
, 57
City Block Distance (see Manhattan distance)
Classification algorithms
activation functions
, 43
bagging
, 49
boosting
, 48–49
chi-square algorithm
, 38
CNN and RNN
, 47
combination methods
, 49–50
cost function
, 41–42
data mining in health care
, 32–33
decision trees
, 37–38
E-health
, 52–53
ensemble learning
, 47–48
gradient descent algorithm
, 47
KNN
, 33–34
linear activation function
, 43
logistic regression
, 40–41
model evaluation
, 50–52
Naïve Bayes algorithm
, 34–35
neural networks
, 42–43
pruning
, 39
random forest algorithm
, 39–40
ROC curve
, 52
sigmoid function
, 41
SVM
, 35–37
Clinical decision support (CDD)
, 116
Clinical trials
, 80
Cloudera
, 21
Cluster analysis
, 20
Collaborative Assessment and Recommendation Engine (CARE)
, 131
Combination methods
, 49–50
Committee-based learning
, 48
Complex carbohydrates
, 226
Computational fluid dynamics
, 59
Computer-aided big healthcare data analytics (see also Smart nursery with health monitoring system)
anatomy of big data
, 123–126
benefits of BHD analytics
, 126–127
BHD applications in real clinics
, 127–131
methods and technology progress in big data
, 118–120
motivation
, 120–123
Conductivity sensor
, 101
Confusion matrix
, 51–52
Congestive heart failure (CHF)
, 47
Convolution
, 235
Convolution(al) neural networks (CNNs)
, 47, 235–237
Coronary artery disease (CAD)
, 206
Correlation matrix
, 154, 159, 167
Cosine distance
, 34
Cost function
, 41–42
CRDC tool
, 10
Cross-facial re-innervation processes
, 178
Data
data-citizens
, 57
data-driven economy
, 57
as fuel of modern economy
, 57–59
mining
, 20, 32–33, 66, 264
quality, structure, and accessibility
, 22
set
, 104
Data warehouse (DW)
, 154
DCM education tool
, 210
Decision trees
, 37–39, 158–159, 168, 272
Deep learning
, 42, 234–238
Deming’s PDCA Cycle
, 61
Descriptive analytics
, 56, 67
DHT11 module
, 143, 146
Diabetes (see Diabetes mellitus (DM))
Diabetes distress (DD)
, 210
Diabetes management self-efficacy (DMSE)
, 210
Diabetes mellitus (DM)
, 204, 227
age group and gender distribution
, 212
experimental setup
, 211
future scope, applications, and limitations
, 217–220
insulin consumption
, 213–216
literature survey/previous findings
, 209–211
novelty in work
, 216–217
recommendations
, 220
study and analysis
, 211
Diagnostic analytics
, 56
Dietary fiber
, 227
Digital disease surveillance
, 80
Dimension table
, 160
Disease level of patient
, 176
District Level Household Survey (DLHS)
, 63
Doctor Insta
, 252
Dynamic programming
, 66
E-health
, 13, 52–53
Education
, 14
Electrocardiogram (ECG)
, 116
Electroencephalogram (EEG)
, 116
Electromyography (EMG)
, 116, 174
Electronic health records (EHR)
, 2, 6–7, 19, 76, 83, 116, 156, 248, 264
Electronic medical records (EMR)
, 19, 77–78, 116
Electronic patient records (EPRs)
, 118
Electronic wellbeing records (EWRs)
, 117
Emerging technological ecosystem
, 66
Enhanced Multiclass Support Vector Machine (EMSVM)
, 191
Ensemble
learning
, 47–48
model
, 275
Entropy
, 37
Error matrix (see Confusion matrix)
Euclidean distance
, 33–34
European Union (EU)
, 59
Evidence-based decision-making
, 22
Executive Information Systems (EIS)
, 156
Expression quantitative trait loci (EQTLs)
, 131
Extraction, transformation, and loading process (ETL process)
, 155, 163
eXtreme Gradient Boosting algorithm (XGBoost algorithm)
, 49
ExxonMobil Research and Engineering Company (EMRE)
, 58
F1 score
, 52
Facial palsy
, 173–175
comparative study of existing solution
, 178–181
levels
, 185
literature survey
, 175–176
problem identification
, 177
proposed solution
, 181–183
pros and cons of solution
, 183
Facial paralysis, initial surgery for
, 177
Fact table
, 160
Failure of heart (see Congestive heart failure (CHF))
False negative (FN)
, 51
False positive (FP)
, 51
Fat(s)
, 226
deficiency of
, 231–232
fat-soluble vitamins
, 226
Feature
ranking
, 193
selection
, 190
Filtering
, 105
First-level learners
, 50
Flaccid paralysis
, 177
Flattening
, 237
Food
choices
, 223
dyes
, 227
effect of weather
, 228
role and value of nutrients
, 224–227
security
, 230
Forest optimization algorithm (FOA)
, 191
Fraud detection
, 22
Frequency table
, 37
G1 Dispensaries
, 251
GDC tool
, 9
GEneralizable Medical Information Analysis and Integration System (GEMINI)
, 129
Genetic algorithm (GA)
, 190
Genome Analysis ToolKit (GATK)
, 131
Genome-wide association study (GWAS)
, 131
Genomics
, 78
Gestational diabetes
, 204
Gini importance
, 40
Gini index
, 38
Global Pulse project
, 119
Glocal Digital Dispensaries
, 250–251
Glocal Healthcare Systems Private Limited
, 250–251
Goodness of split criterion
, 272
Government agencies
, 13
Gradient boosting
, 48
Gradient descent algorithm
, 42, 47
Graph analytics
, 21
Gross data product
, 58
Gross domestic product (GDP)
, 121
Grove–Gas Sensor
, 99–100
Hadoop
, 21
Hadoop distributed file system (HDFS)
, 66, 84
Hamming distance
, 33–34
Health Information Technology (HIT)
, 117, 248
Health Insurance Portability and Accountability Act legislation
, 23
Health sector
BD definitions in
, 18
BD needs in
, 18–19
Health-threat detection
, 22
Healthcare
, 14, 139, 155
AI in
, 207
analytics environment
, 19
applications of BD in
, 208
big data applications in
, 4–15
data mining in
, 32–33
IoT in
, 208
ML in
, 207
predictive analytics in
, 10–11
technology in addressing problem of integration
, 208–209
Healthcare electronic record (HER)
, 116
Healthy diet with balanced nutrients
, 223
HEPA filter
, 100–101
High blood pressure
, 227
HIT for Economical and Clinical Health (HITECH)
, 117
Hold out method
, 191
Hospitalization
, 276
House Brackman grading system
, 176
Hyperbolic tangent activation function
, 45
Hyperplanes
, 36
ID3 algorithm
, 158
IECM algorithm
, 183
Image
acquisition
, 182
conversion to arrays
, 105
processing
, 175
segmentation
, 182–183
Information gain
, 37–38
Information gain ratio (IGR)
, 191
Information technology (IT)
, 15, 125
Infrared sensor (IR sensor)
, 142, 144
Infrastructure Plus Program
, 119
Instance-based KNN
, 34
Institute for Health Technology Transformation (IHTT)
, 117, 120
Insulin consumption
, 213–216
Insurance
, 14
Intensive care unit (ICU)
, 124
Intergovernmental Panel Climate Change (IPCC)
, 95
International development
, 13
Internet of Things (IoT)
, 14–15, 19–20, 57, 94, 208
Intrusion detection and security system (IDS system)
, 141
future scope
, 148–149
hardware assembly and implementation
, 144–147
literature review
, 140–141
system architecture
, 141–144
working
, 148
Jaccard distance
, 34
Jaql
, 21
K-most similar data points
, 34
k-Nearest Neighbours (KNN)
, 33–34, 233–234, 267, 269–270
Knowledge-based economy
, 57
Lab testing
, 78
Lazy learning KNN
, 34
Leaky rectified linear unit activation function (Leaky ReLU)
, 45–46
Learning
multiple classifier systems
, 48
phase
, 267
Light-dependent resistor (LDR)
, 141
module
, 142–143, 146
sensor
, 94, 97–98
Linear activation function
, 43
Linear regression
, 40–41, 272–273
Lipomics
, 78
LitmusDx
, 251
LM35 gadget
, 101
Logistic regression
, 40–41, 273–274
Machine learning (ML)
, 21, 32, 42, 66, 190, 207, 224, 233–234, 265
classifiers
, 193–194
Macronutrients
, 226
Magnetic resonance imaging (MRI)
, 116, 174
Mahalanobis distance
, 34
Mahout
, 21
Majority voting
, 50
Malnutrition
, 230–231
Mammography
, 116
Man to machine interaction (M2M interaction)
, 120
Manhattan distance
, 33–34
Manufacturing
, 14
MapReduce
, 21, 84
Margin in SVM
, 36
Max pooling
, 236–237
Meal classification and assessment of nutrients
autumn eats
, 229–230
carbohydrates
, 231
deep learning
, 234–238
fat deficiency
, 231–232
food security
, 230
future scope
, 239–240
life-threatening diseases caused by unhealthy food
, 227
machine learning
, 233–234
malnutrition
, 230–231
mineral deficiency
, 233
problem identification
, 230
proposed solution
, 238–239
protein deficiency
, 232
role and value of nutrients in food
, 224–227
spring eats
, 229
summer eats
, 228
vitamin deficiency
, 232
effect of weather on food
, 228
winter eats
, 229
Mean decrease in impurity (MDI) (see Gini importance)
Media
, 14
Median
, 195–196
filtering
, 183
Medical
claims
, 79–80
imaging
, 3
Medical Termination of Pregnancy (MTP)
, 64
Medicines
, 231
history of
, 244
Medongo
, 251
Memory analytics
, 66
Meta learner
, 50
Metal oxide-semiconductor (MOS)
, 142
Microcontroller
, 141–142
Micronutrients
, 226
MiCS-2714 Gas Sensor
, 100
Migraine
, 204–205
Mineral(s)
, 227
deficiency
, 233
Minkowski distance
, 34
Model
evaluation
, 50–52
selection
, 50
Moisture sensor
, 94, 98
Morphological processing
, 183
Mosaic plot
, 159, 167
MQ2 Sensor
, 99–100, 142, 145
MQ9 Sensor
, 100
Multiple voxel pattern analysis (MVPA)
, 209
Multiway frequency analysis
, 274
Mutation
, 244
“My Kardio” framework
, 256
Naïve Bayes (NB)
, 190, 194
algorithm
, 34–35
classification modeling
, 270–272
classifier
, 34–35
National Family Health Survey (NFHS)
, 63
National Health Service (NHS)
, 127
National Institute of Health (NIH)
, 119
NCI tool
, 10
Nerve transfer
, 178
Neural networks
, 21, 42–43
activation functions
, 43
hyperbolic tangent activation function
, 45
Leaky ReLU
, 45–46
linear activation function
, 43
ReLU function
, 45
sigmoid activation function
, 43
Softmax activation function
, 46–47
Neurosynaptic communications
, 249–250
Neurosynaptic Communications Private Ltd (NCPL)
, 249
Noise removal methods
, 105
Non-essential nutrients
, 227
Non-parametric KNN
, 34
Non-suicidal trauma factor (NSSI)
, 209
Normal AC Filter
, 101
Numeric predictions
, 36
Nutrients
, 223–224
role and value of nutrients in food
, 224–227
Obesity
, 205, 227
Object-oriented programs
, 56
Omics
, 78–79
Oozie
, 21
Optical imaging
, 116
Optimized delivery in telehealth care
, 252
Osteoporosis
, 227
Palsy
, 173
Partial facial paralysis
, 174
Patient
engagement
, 8–9
health record
, 116
patient-centric care
, 22
predication
, 3
Patient disease (Pdis)
, 161
Pattern recognition technique
, 21
Peripheral facial palsy
, 174
Personalized healthcare
, 77
pH sensor
, 94, 98
Photograph objects
, 183
Photoresistor
, 97–98
Photosynthesis
, 96
PIG Latin
, 84
PlantVillage
, 104
Plurality voting
, 50
PM 2.5 Sensor
, 100
Population health
, 22
Positron emission tomography (PET)
, 116
Potentiometric pH meter
, 98
Power Grid Data
, 4
PPD42NJ Particle Sensor Unit
, 99
Precision
, 51
Prediabetes
, 204
Predictive analytics
, 56, 67, 220
in health care
, 10–11
Predictive big data analytics in healthcare (see also Big data analytics (BDA))
, 76
advantages
, 84–85
areas of application
, 81–84
challenges
, 86–88
claims data
, 79–80
clinical data
, 77–79
clinical research data
, 80
data-related concerns
, 87
infrastructural concerns
, 86
IT infrastructure benefits
, 84
managerial benefits
, 85
operational benefits
, 84–85
organization-related concerns
, 88
organizational benefits
, 85
patient–generated data
, 80–81
security/privacy concerns
, 87–88
sources of big data in healthcare
, 77–81
strategic benefits
, 85
Predictive healthcare
, 77
Predictive modeling in health care data analytics
, 264–266
applications
, 274–277
disease diagnosis and treatment selection
, 274–276
health care management
, 276–277
reducing health care costs
, 277
techniques for
, 267–274
Prescription claims
, 79–80
Prescriptive analytics
, 56, 67
Preservatives
, 227
Pressure sensor
, 102
“Process of transformation”
, 60
Protein(s)
, 226
deficiency
, 232
Proteomics
, 78
Pruning
, 39
PS2 Pollen Sensor
, 99
Public health
, 22
Radionuclide imaging
, 116
Random decision forest
, 193
Random forest (RF)
, 190–191, 193, 275
algorithm
, 39–40
classifier
, 40
experimental results
, 197–200
machine learning classifiers
, 193–194
proposed methodology
, 196–197
statistical analysis
, 194–196
Raspberry Pi
, 141
Recall
, 51–52
Receiver Operating Characteristics curve (ROC curve)
, 52
Recommender system
, 131
Rectified linear unit activation function (ReLU function)
, 45, 236
Recurrent Neural Networks (RNN)
, 47, 237–238
Relay
, 143–144
ReMeDi Nova
, 250
ReMeDi Platform
, 250
ReMeDi Solution
, 249–250
Research and development professionals (R&D professionals)
, 56
Resizing images
, 105
Right to Information Act (2005)
, 71
Risk-scoring
, 79
Root mean square error (RMSE)
, 191, 196
Root relative squared error (RRSE)
, 191
Search Engine Data
, 4
Second-level learner (see Weak learners)
Security
, 11, 139–140
Semi-supervised learning
, 193
Sensor(s)
, 140
data
, 19–20
Shannon’s entropy
, 37
Sigmoid activation function
, 43
Sigmoid function
, 41
Simple averaging
, 49
Simple carbohydrates
, 226
Smart nursery with health monitoring system
data acquiring and preprocessing
, 104–105
data modeling
, 105–106
literature survey
, 95–103
methodology
, 103–106
results
, 110–112
solution
, 106–110
Smartwatches (see Wristwatches)
Social media data
, 80
Soft voting
, 50
Softmax activation function
, 46–47
Software for Flexible Integration of Annotation (SoFIA)
, 131
Soil pressure
, 102
Spatial analysis
, 21
Spring eats
, 229
Sqoop
, 21
Stacking
, 50
Staffing levels
, 5
Standard deviation (SD)
, 196
Statistical analysis
, 194–196
Stress
, 204
Sulfur dioxide
, 96
Summer eats
, 228
Supervised learning
, 37, 193, 265
Support vector machines (SVM)
, 35–37, 190, 192–194, 234, 256, 267
advantages and disadvantages
, 234
Support vectors (SV)
, 234
Synkinesis
, 177
Tanimoto distance
, 34
Telecardiology
, 248
Teledermatology
, 248
Telehealth
, 243, 246–247
barriers to
, 252–257
business models
, 249–252
early civilization
, 245
evolution
, 246
history of medicine
, 244
methodology
, 257
modern history
, 245–246
optimized delivery in telehealth care
, 252
pre-historic ERA
, 244–245
process of evolution
, 244
results
, 257–261
Telemedicine
, 12–13, 77, 247–249
Telenephrology
, 248
Teleneurology
, 248
Teleobstetrics
, 249
Teleoncology
, 249
Teleophthalmology
, 248
Telepathology
, 249
Telepsychiatry
, 248
Telerehabilitation
, 249
Temperature sensor
, 101
Tension-type headaches (TTH)
, 205, 215
Text mining
, 66
medical records
, 11
Thermography
, 116
Tin dioxide (SnO2)
, 142
True negative (TN)
, 51
True positive (TP)
, 51
Type 1 diabetes (T1D)
, 204, 204, 216
Ultrasonography (US)
, 116
Undernourishment
, 231
Unsupervised learning
, 193, 265
Valance
, 125
Validity
, 126
Value
, 126
Variance
, 196
Variety
, 4, 18, 124
Velocity
, 4, 18, 124
Veracity
, 125
Visualization
, 126
Vitamin(s)
, 226–227
deficiency
, 232
Volatility
, 126
Volume
, 4, 18, 123
Voting
, 50
Vulnerability
, 126
Water
, 226
water-soluble vitamins
, 227
Weak learners
, 48
Wearable sensors
, 81
Weighted averaging
, 50
Weighted voting
, 50
Whole-genome association study (WGAS)
, 131
Winter eats
, 229
Wireless sensor network (WSN)
, 141
Wisconsin Breast Cancer Data (WBCD)
, 190
World Health Organization (WHO)
, 122, 275
Wristwatches
, 116
X-ray
computed tomography
, 116
radiography
, 116
YOLO Health
, 251
Zookeeper
, 21, 84
- Prelims
- Chapter 1: Big Data Analytics and Intelligence: A Perspective for Health Care
- Chapter 2: Big Data Analytics in Health Sector: Need, Opportunities, Challenges, and Future Prospects
- Chapter 3: Use of Classification Algorithms in Health Care
- Chapter 4: Big Data Analytics in Excelling Health Care: Achievement and Challenges in India
- Chapter 5: Predictive Big Data Analytics in Healthcare
- Chapter 6: Smart Nursery with Health Monitoring System Through Integration of IoT and Machine Learning
- Chapter 7: Computer-aided Big Healthcare Data (BHD) Analytics
- Chapter 8: Intrusion Detection and Security System
- Chapter 9: Decision Making with BI in Healthcare Domain
- Chapter 10: Assistance for Facial Palsy using Quantitative Technology
- Chapter 11: Constructive Effect of Ranking Optimal Features Using Random Forest, SupportVector Machine and Naïve Bayes forBreast Cancer Diagnosis
- Chapter 12: Intelligent Establishment of Correlation of TTH and Diabetes Mellitus on Subject’s Physical Characteristics: MMBD* and ML Perspective in Healthcare
- Chapter 13: A Machine Learning Approach Toward Meal Classification and Assessment of Nutrients Value Based on Weather Conditions
- Chapter 14: Telehealth: Former, Today, and Later
- Chapter 15: Predictive Modeling in Health Care Data Analytics: A Sustainable Supervised Learning Technique
- Index