Cover Image

Predictive analytics using MATLAB(R) for biomedical applications /

Predictive Analytics using MATLAB(R) for Biomedical Applications is a comprehensive and practical guide for biomedical engineers, data scientists, and researchers on how to use predictive analytics techniques in MATLAB(R) for solving real-world biomedical problems. The book offers a technical overvi...

Full description

Bibliographic Details
Main Author: Kumar, L. Ashok (Author)
Corporate Author: ScienceDirect (Online service)
Format: eBook
Language:English
Published: London, United Kingdom : Academic Press, an imprint of Elsevier, [2025]
Subjects:
MATLAB.
Biomedical engineering > Data processing.
Génie biomédical > Informatique.
Electronic books.
Online Access:Connect to the full text of this electronic book
Table of Contents:
  • Front Cover
  • Predictive Analytics Using MATLAB® for Biomedical Applications
  • Copyright Page
  • Contents
  • About the author
  • Preface
  • Acknowledgments
  • About the book
  • 1 Introduction to predictive analytics and MATLAB®
  • 1.1 Introduction
  • 1.1.1 Purpose and scope
  • 1.1.2 Audience
  • 1.1.3 Prerequisites
  • 1.1.4 Catering to different backgrounds
  • 1.2 Foundations of biomedical data
  • 1.3 Characteristics and challenges of processing biomedical signals
  • 1.3.1 Techniques for preprocessing and analyzing biomedical data
  • 1.4 Introduction to predictive analytics
  • 1.4.1 Data insights and its significance
  • 1.4.2 Models and algorithms
  • 1.4.3 Types of models
  • 1.4.3.1 Classification model
  • 1.4.3.2 Clustering model
  • 1.4.3.3 Forecast model
  • 1.4.3.4 Outliers model
  • 1.4.3.5 Time series model
  • 1.5 Predictive analytics in healthcare
  • 1.5.1 Use cases for predictive analytics in healthcare
  • 1.5.2 Benefits of predictive analytics in healthcare
  • 1.5.3 Process flow in predictive analytics
  • 1.5.3.1 Data collection
  • 1.5.3.2 Data preprocessing
  • 1.5.3.3 Modeling
  • 1.5.3.4 Evaluation
  • 1.5.3.5 Deployment
  • 1.6 Predictive analytics techniques
  • 1.6.1 Regression analysis: linear and logistic regression
  • 1.6.1.1 Linear regression
  • 1.6.1.2 Logistic regression
  • 1.6.2 Time series analysis
  • 1.7 Machine learning algorithms
  • 1.7.1 Decision trees
  • 1.7.2 Random forests
  • 1.7.3 Support vector machines
  • 1.7.4 Neural networks
  • 1.8 Introduction to MATLAB
  • 1.8.1 Motivation for using MATLAB in biomedical applications
  • 1.8.2 Overview of MATLAB's capabilities for data analysis, modeling, and predictive analytics
  • 1.8.3 Getting started with MATLAB
  • 1.8.3.1 Data handling and visualization in MATLAB
  • 1.8.3.2 Data manipulation techniques
  • 1.8.3.2.1 Filtering
  • 1.8.3.2.2 Interpolation.
  • 1.8.3.2.3 Data transformation
  • 1.8.3.3 Visualization tools in MATLAB
  • 1.8.3.3.1 Plotting signals
  • 1.8.3.3.2 Image display
  • 1.8.3.3.3 Graph visualization
  • 1.8.3.3.4 3D visualization
  • 1.8.3.4 Utilizing MATLAB's plotting functions for effective data representation
  • 1.8.3.4.1 Customization
  • 1.8.3.4.2 Multiple subplots
  • 1.8.3.4.3 Annotations
  • 1.8.3.4.4 Exporting figures
  • 1.9 Mathematical modeling in biomedical engineering
  • 1.9.1 Importance of mathematical modeling in biomedical engineering
  • 1.9.2 Basics of differential equations and their role in modeling dynamic systems
  • 1.9.2.1 Ordinary differential equations
  • 1.9.2.2 Partial differential equations
  • 1.9.3 Statistical modeling techniques for analyzing biomedical data variability
  • 1.10 Conclusion
  • References
  • 2 Prognostic insights: predictive analytics in nephrological diseases
  • 2.1 Introduction
  • 2.2 Kidney disease
  • 2.2.1 Types
  • 2.2.2 Characteristics of kidney disease
  • 2.2.3 Ratio of kidney disease over the years
  • 2.3 Need for kidney disease prediction
  • 2.4 Techniques for kidney disease assessment
  • 2.5 Publicly available dataset
  • 2.6 Related work
  • 2.7 Experimental analysis using MATLAB®
  • 2.7.1 Dataset description
  • 2.7.2 Statistical analysis on dataset
  • 2.7.2.1 Code appendix
  • 2.7.2.2 Code description
  • 2.7.3 Methodology
  • 2.7.4 MATLAB code appendix
  • 2.7.4.1 Code description
  • 2.8 Results and discussion
  • 2.9 Conclusion
  • References
  • 3 Harnessing predictive analytics for cardiovascular diseases
  • 3.1 Introduction
  • 3.1.1 Benefits of early prediction of CVD
  • 3.1.2 Patient data helpful in CVD risk assessment
  • 3.2 Open access datasets
  • 3.3 Related work
  • 3.4 K-means clustering
  • 3.4.1 Working algorithm
  • 3.4.2 Value of "K number of clusters" in K-means clustering
  • 3.4.3 Elbow method
  • 3.4.4 Distance measures.
  • 3.4.4.1 Euclidean distance measure
  • 3.4.4.2 Squared Euclidean distance measure
  • 3.4.4.3 Manhattan distance measure
  • 3.4.4.4 Cosine distance measure
  • 3.4.5 Advantages of K -means clustering
  • 3.4.6 Limitations
  • 3.4.7 MATLAB implementation
  • 3.4.8 Description of functions used in code
  • 3.4.9 Matlab code
  • 3.4.10 Output
  • 3.5 Decision tree
  • 3.5.1 Types of decision trees
  • 3.5.2 Attribute selection at each node
  • 3.5.3 Algorithm
  • 3.5.4 Advantages
  • 3.5.5 Limitations
  • 3.5.6 MATLAB implementation
  • 3.5.7 Statistical analysis of cardiovascular dataset
  • 3.5.8 Code explanation
  • 3.5.9 Description of functions used in code.