This book provides various insights into machine learning techniques in healthcare system data and its analysis. Recent technological advancements in the healthcare system represent cutting-edge innovations and global research successes in performance modelling, analysis, and applications. The extensive use of machine learning in numerous industries, including healthcare, has been made possible by advancements in data technologies, including storage capacity, processing capability, and data transit speeds. The need for a personalized medicine or ""precision medicine"" approach to healthcare has been highlighted by current trends in medicine due to the complexity of providing effective healthcare to each individual.
Personalized medicine aims to identify, forecast, and analyze diagnostic decisions using vast volumes of healthcare data so that doctors may then apply them to each unique patient. These data may include, but are not limited to, information on a person's genes or family history, medical imaging data, drug combinations, patient health outcomes at the community level, and natural language processing of pre-existing medical documentation.
The introduction of digital technology in the healthcare industry is marked by ongoing difficulties with implementation and use. Slow progress has been made in unifying different healthcare systems, and much of the world still lacks a fully integrated healthcare system. The intrinsic complexity and development of human biology, as well as the differences across patients, have repeatedly demonstrated the significance of the human element in the diagnosis and treatment of illnesses. But as digital technology develops, healthcare providers will undoubtedly need to use it more and more to give patients the best treatment possible.
Author(s): C. Karthik Chandran, M. Rajalakshmi, Sachi Nandan Mohanty, Subrata Chowdhury
Publisher: River Publishers
Year: 2023
Language: English
Pages: 251
Cover
Half Title
Series Page
Title Page
Copyright Page
Table of Contents
Preface
List of Contributors
List of Figures
List of Tables
List of Abbreviations
Chapter 1: Investigation on Improving the Performance of Class-imbalanced Medical Health Datasets
1.1: Introduction
1.2: Problem Formulation
1.3: Techniques to Handle Imbalanced Datasets
1.3.1: Random undersampling (RUS)
1.3.2: Random oversampling (RUS)
1.3.3: Synthetic minority oversampling technique (SMOTE)
1.4: Classification Models
1.4.1: Naive Bayes
1.4.2: k-Nearest neighbor classifier
1.4.3: Decision tree classifier
1.4.4: Random forest
1.5: Dataset Collection
1.5.1: Heart failure clinical records dataset
1.5.2: Diabetes dataset
1.6: Experimental Results and Discussion
1.6.1: Heart failure clinical records dataset
1.6.2: Diabetes dataset
1.7: Conclusion
References
Chapter 2: Improving Heart Disease Diagnosis using Modified Dynamic Adaptive PSO (MDAPSO)
2.1: Introduction
2.2: Background and Related Work
2.2.1: PSO modification
2.2.2: Feature selection
2.2.3: Classification and clustering
2.3: Proposed Approach
2.3.1: PSO algorithm
2.3.2: Inertia weight
2.3.3: Modified dynamic adaptive particle swarm optimization (MDAPSO)
2.4: Experimental Setup and Results
2.4.1: Dataset
2.4.2: Performance metrics
2.4.3: Result
2.5: Conclusion
References
Chapter 3: Efficient Diagnosis and ICU Patient Monitoring Model
3.1: Introduction
3.2: Main Text
3.2.1: Disease prediction
3.2.2: Hospital monitoring system
3.3: Experimentation
3.3.1: The threshold for the Levenshtein distance
3.3.2: The threshold for heart rate and respiratory rate
3.4: Conclusion
References
Chapter 4: Application of Machine Learning in Chest X-ray Images
4.1: Introduction
4.2: Chest X-ray Images
4.3: Literature Review
4.4: Application of Machine Learning in Chest X-ray Images
4.4.1: Clustering
4.4.2: Regression
4.4.3: Segmentation
4.4.4: Classification
4.5: Case Study: Lung Chest X-ray Images
4.5.1: Methodology
4.5.2: JSRT dataset
4.5.3: Image pre-processing
4.5.4: CNN
4.6: Conclusion
4.7: Future Study
References
Chapter 5: Integrated Solution for Chest X-ray Image Classification
5.1: Introduction
5.2: Related Work
5.3: The Method
5.3.1: Feature extraction
5.3.2: Feature reduction
5.3.3: Classification
5.3.4: Algorithm
5.4: Experimental Results
5.5: Discussion and Conclusions
References
Chapter 6: Predicting Genetic Mutations Among Cancer Patients by Incorporating LSTM with Word Embedding Techniques
6.1: Introduction
6.2: Related Work
6.2.1: Basic feature engineering
6.2.2: Classification method
6.3: Data Overview
6.3.1: Dataset structure
6.3.2: Data pre-processing
6.3.3: Most frequent genes and class
6.3.4: Most frequent variation and class
6.3.5: Text length distribution and class
6.3.6: Word cloud to visualize data
6.4: Methodology
6.4.1: Pre-processing and feature extraction
6.4.2: Word embedding
6.4.3: Classifier
6.5: Experiments
6.6: Results
6.7: Evaluation Parameters
6.8: Conclusion and Future Work
References
Chapter 7: Prediction of Covid-19 Disease using Machine-learning-based Models
7.1: Introduction
7.2: Literature Survey
7.3: Different Models used in Covid-19 Disease Prediction
7.3.1: Holt’s linear model
7.3.2: Holt−Winters method
7.3.3: Linear regression
7.3.4: Polynomial regression
7.3.5: Support vector machine
7.3.6: Moving average model
7.3.7: Autoregressive model
7.3.8: ARIMA
7.4: Evaluation Parameters used in Models
7.4.1: Root mean square error
7.4.2: Mean square error
7.4.3: Mean absolute error
7.5: Experimental Result Analysis
7.5.1: Future forecasting of death rates
7.5.2: Future forecasting of confirmed cases
7.5.3: Future forecasting of recovery rate
7.6: Conclusion
References
Chapter 8: Intelligent Retrieval Algorithm using Electronic Health Records for Healthcare
8.1: Introduction
8.2: EHR Datasets
8.2.1: EHR repositories
8.3: Machine Learning Algorithm
8.3.1: Data mining techniques and algorithms
8.3.2: Machine learning algorithms using EHR for cardiac disease prediction
8.4: Machine Learning and Wearable Devices
8.5: Studies based on Data Fusion
8.6: Data Pre-processing
8.7: Conclusion
References
Chapter 9: Machine Learning-based Integrated Approach for Cancer Microarray Data Analysis
9.1: Introduction
9.2: Related Work
9.3: Background Study
9.3.1: Machine learning
9.3.2: Microarray data
9.4: Proposed Work
9.4.1: RFE
9.4.2: Cuckoo search
9.4.3: Dataset
9.5: Empirical Analysis
9.6: Conclusion
References
Chapter 10: Feature Selection/Dimensionality Reduction
10.1: Introduction
10.2: Feature Selection
10.2.1: Characteristics
10.2.2: Classification of feature selection methods
10.2.3: Importance of feature selection in machine learning
10.3: Dimensionality Reductio
10.3.1: Techniques for dimensionality reduction
10.3.2: Advantages of dimensionality reduction
10.3.3: Disadvantages of dimensionality reduction
10.4: Conclusion
References
Chapter 11: Information Retrieval using Set-based Model Methods,Tools, and Applications in Medical Data Analysis
11.1: Introduction
11.2: Literature Review
11.3: Set-based Model for Reinforcement Learning Design for Medical Data
11.3.1: Case study
11.3.2: Rank computation
11.3.3: Tools for evaluation
11.3.4: Applications
11.4: Conclusion
References
Index
Author Biographies
About the Editors
