Predictive Modeling in Biomedical Data Mining and Analysis

Front Cover
Predictive Modeling in Biomedical Data Mining and Analysis
Copyright
Contents
Contributors
About the Editors
Preface
Chapter 1: Data mining with deep learning in biomedical data
1. Introduction
2. Role of deep learning techniques in epileptic seizure detection
3. Proposed method of seizure detection
3.1. CNN
3.2. LSTM
3.3. CNN-LSTM
4. Results and discussion
5. Conclusions
References
Chapter 2: Applications of supervised machine learning techniques with the goal of medical analysis and prediction: A cas ...
1. Introduction
2. A brief literature survey
3. Dataset and modus operandi
4. Data visualization
5. Feature selection and dimensionality reduction
5.1. CFS
5.2. PCA
6. Experimental results and discussions
7. Conclusions
References
Chapter 3: Medical decision support system using data mining
1. Introduction
1.1. Objective of the work
1.2. Medical decision support system
2. Medical decision support system: A review
2.1. Clinical decision support system
2.2. Machine learning techniques to address medical information challenge
2.3. Decision support systems
2.4. Mining algorithms
3. Ontological representation of MDSS
3.1. Ontological model of the knowledge base class diagram: Scenario1
3.2. Ontological model of the knowledge base class diagram: Scenario2
3.3. Graphical illustration of the medical decision support system
3.4. Viewing the query results
4. Integrated medical decision support system
4.1. Integrated MDSS design considerations
4.2. Architectural design
4.2.1. Architecture for integrated medical decision support system
4.3. Unified decision-making algorithm for medical decision support system
4.4. Pseudo code for prescribing the drug
4.5. Pseudo code for designing inference rules
4.5.1. Rule for drug-to-drug interaction
4.5.2. Rule for drug-to-condition interaction
4.6. Performance evaluation of J48, JRip, and Bagging Algorithms
5. Conclusion and future enhancement
5.1. Future work
References
Chapter 4: Role of AI techniques in enhancing multi-modality medical image fusion results
1. Introduction
2. Modalities
3. Fusion process
3.1. Upfront
3.2. Decomposition based
4. AI based fusion
4.1. Fuzzy logic
4.2. ANFIS
5. Evaluation
5.1. Conventional metrics
5.2. Subjective evaluation
6. Experimental results
7. Conclusion and future scope
Acknowledgment
References
Chapter 5: A comparative performance analysis of backpropagation training optimizers to estimate clinical gait mechanics
1. Introduction
2. Methods: Related work and dataset
3. Backpropagation neural network and training optimizers
3.1. Levenberg-Marquardt (LM)
3.2. Resilient backpropagation (RP)
3.3. Gradient descent with momentum (GDM)
4. BPNN implementation
5. Results and discussions
6. Conclusions
References
Chapter 6: High-performance medicine in cognitive impairment: Brain-computer interfacing for prodromal Alzheimer'
1. Introduction
2. Related works
3. Methodology
3.1. Data collection
3.2. Data preprocessing
3.3. Feature extraction process
3.4. Classification process
4. Results
4.1. Results of the signal preprocessing stage
4.2. Experimental results
4.3. Analysis of the results
5. Conclusion
References
Chapter 7: Brain tumor classifications by gradient and XG boosting machine learning models
1. Introduction
2. Research background
3. Methods
3.1. Dataset
3.2. Data visualization
3.3. Gradient and XG boosting algorithms
3.4. Cross-validation (CV)
3.5. Performance measures
4. Results and discussions
5. Conclusions
Conflicts of interest
References
Chapter 8: Biofeedback method for human-computer interaction to improve elder caring: Eye-gaze tracking
1. Introduction
2. Anatomy of the human eye
3. Overview of eye-gaze tracking
3.1. Shape-based method
3.2. Appearance-based method
3.3. Feature-based method
4. Eye-gaze tracking for human-computer interaction
5. Proposed design
5.1. Eye tracking and gaze estimation
5.2. Eye landmarks localization
5.3. Eye-gaze direction classification
6. Results
7. Conclusion
References
Chapter 9: Prediction of blood screening parameters for preliminary analysis using neural networks
1. Introduction
2. Related work
3. Methodology
4. Results
5. Conclusion
References
Chapter 10: Classification of hypertension using an improved unsupervised learning technique and image processing
1. Introduction
2. Related work
3. Methodology
3.1. Pre-processing
3.2. Segmentation
3.3. Feature extraction
4. Experimental results
4.1. Results
4.2. Performance analysis
5. Conclusion
References
Chapter 11: Biomedical data visualization and clinical decision-making in rodents using a multi-usage wireless brain stim ...
1. Introduction
2. Architectural design and circuit modeling
2.1. Design objectives of ICSS and ICMS experiments
2.1.1. ICSS
2.1.2. ICMS
2.2. Block level design
2.3. Modeling for ICSS
2.3.1. Headstage
2.3.2. Backpack
2.3.3. Modeling of ICMS
2.3.4. Power supply
2.4. Current source
2.5. PCB-Design and development
2.6. Programming
3. Implementation and experimental verification
3.1. ICSS-In vivo
3.1.1. Experimental setup
3.1.2. ICMS-In vivo
4. Results and discussions
4.1. Intracranial self stimulation
4.1.1. In vitro
4.1.2. In vivo
4.2. Intracortical microstimulation
5. Conclusion and future directions
References
Chapter 12: LSTM neural network-based classification of sensory signals for healthy and unhealthy gait assessment
1. Introduction
2. Dataset collection
3. LSTM neural network model
3.1. Stochastic gradient descent (SGD)
3.2. Adaptive moment estimation (Adam)
4. Implementation of LSTM neural network
5. Results and discussions
6. Conclusions
References
Chapter 13: Data-driven machine learning: A new approach to process and utilize biomedical data
1. An introduction to artificial intelligence and machine learning in healthcare
1.1. Types of machine learning algorithms
2. Challenges and roadblocks to be addressed
2.1. Unreliability
2.2. Choice of attributes and overfitting
2.3. Circularity and insufficient validation
2.4. Data leakage
2.5. Lack of transparency
2.6. Occurrence of Bias and distributional shifts
2.7. Data outsourcing and breach of privacy
2.8. Other data-related challenges
2.9. Accountability and responsibility
3. The need to address these issues
4. Recommendations and guidelines for the improvement of ML-based algorithms
4.1. Improvements related to data quality and quantity
4.2. Data security enhancements
4.3. Calibration and eradication of biases
4.4. Improving transportability
4.5. Suggestions regarding ethical aspects
5. Applications in the present scenarios
6. Future prospects and conclusion
References
Chapter 14: Multiobjective evolutionary algorithm based on decomposition for feature selection in medical diagnosis
1. Introduction
2. Medical applications
2.1. Medical imaging
2.2. Biomedical signal processing
2.3. DNA microarray
3. Feature selection
3.1. The process of feature selection
3.1.1. Searching criteria
3.1.2. Feature subset evaluation criteria
4. Literature review
5. Metaheuristics and MOO
5.1. Issues in solving MOOPs using metaheuristics
6. Multiobjective optimization problems (MOOPs)
7. Role of EA in MOO
8. MOEA based on decomposition
8.1. Scalarization of MOOP
8.1.1. Weighted sum technique
8.1.2. -constraint method
8.1.3. Weighted metric methods: Chebyshev method
8.1.4. Benson's method
9. Application of MOEA/D in feature selection for medical diagnosis
9.1. Problem formulation
9.2. Description of the dataset
9.3. MOEA/D algorithm on feature selection
9.3.1. Multiple ref. points based decomposition
9.3.2. Allocation of the reference points
9.3.3. Repairing mechanism
10. Experimental results
10.1. Evaluation matrices
10.2. Results
11. Conclusion
References
Chapter 15: Machine learning techniques in healthcare informatics: Showcasing prediction of type 2 diabetes mellitus dise ...
1. Introduction
2. Machine learning in healthcare
2.1. Real-life examples of machine learning in healthcare
2.2. Machine learning techniques
2.2.1. Supervised learning
2.2.2. Semi-supervised learning
2.2.3. Unsupervised learning
2.3. Machine learning algorithms for healthcare
2.3.1. K-nearest neighbor
2.3.2. Logistic regression
2.3.3. Naive Bayes
2.3.4. Support vector machine
2.3.5. Decision tree
2.3.6. Random forest
2.3.7. Artificial neural network
3. Proposed framework
4. Results and discussion
5. Conclusion and future scope
References
Index
Back Cover