This book presents a systematic evolution of artificial intelligence (AI), its applications, challenges and solutions in the field of healthcare. The book mainly covers the foundations and various methods of learning in artificial intelligence with its application in healthcare industry. This book provides a comprehensive introduction to data analysis using AI as a tool in the generation, normalization and analysis of healthcare data in association with several evaluation techniques and accuracy measurements. The book is divided into three major sections describing the basic foundations of AI and its associated algorithms, history of artificial intelligence in healthcare, recent developments and several modeling techniques for the same. The last section of the book provides insights into several implementations and methods of evaluation and accuracy prediction for healthcare analysis in AI. Extensive use of data for analysis and prediction using several technologies has transformed the lives of normal people indirectly effecting our process to communicate, learn, work and socialize within the society. Thus, the book also provides an insight into the ethics of AI that is very vital in the process of implementation and evaluation of healthcare data. The book provides an organized analysis to a considerable part of data in a digitized society. In view of this, it covers the theory, methodology, perfection and verification of empirical work for health-related data processing. Particular attention is devoted to in-depth experiments and applications.
Author(s): Jyotismita Talukdar, Thipendra P. Singh, Basanta Barman
Publisher: Springer
Year: 2023
Language: English
Pages: 207
City: Singapore
Contents
About the Authors
1 Introduction to Human and Artificial Intelligence
1.1 Introduction to Human Intelligence
1.2 Where We've Come from and Where We're Going with AI in the Past
1.3 Machine Learning
1.4 Deep Learning
1.5 Neural Networks
1.6 Introduction to Theoretical Frameworks and Neuroscience
1.7 Information Theory
1.8 How Do We Measure Information?
1.9 What Is Entropy?
1.10 How Are Information Theory, Entropy, and Machine Learning Related?
1.11 Applications of AI in Healthcare
1.12 Achieving the Full Potential of AI in Healthcare
1.13 Conclusion
References
2 Knowledge Representation and Reasoning
2.1 Knowledge Representation and Reasoning
2.2 Types of Knowledge
2.3 AI Knowledge Cycle [1]
2.4 Primary Approaches to Knowledge Representation
2.5 Features of Knowledge Representation System
2.6 Techniques of Knowledge Representation [3]
2.7 Propositional Logic
2.8 Logical Connectives
2.9 Truth Table
2.10 First-Order Logic
2.11 Quantifiers and Their Use in FOL [5]
2.12 Uncertainty
2.13 Probabilistic Reasoning
2.14 Bayesian Belief Network in Artificial Intelligence
References
3 Methods of Machine Learning
3.1 Supervised Machine Learning
3.2 Categories of Supervised Machine Learning
3.3 Unsupervised Machine Learning
3.4 Semi-supervised Learning
3.5 Reinforcement Learning
3.6 What Is Transfer Learning and Why Should You Care?
References
4 Supervised Learning
4.1 How Supervised Learning Works
4.2 Steps Involved in Supervised Learning
4.3 Supervised Learning Algorithms
4.4 Theorem of Bayes
4.5 Linear Regression
4.6 Multiple Linear Regression
4.7 Logistic Regression
4.8 Support Vector Machine (SVM)
4.9 K-Nearest Neighbour
4.10 Random Forest
4.11 Decision Tree
4.12 Neural Networks
4.13 Artificial Neural Networks
4.14 Deep Learning
4.15 Recurrent Neural Network (RNN)—Long Short-Term Memory
4.16 Convolutional Neural Network
References
5 Unsupervised Learning
5.1 Introduction
5.2 Types of Unsupervised Learning Algorithm
5.3 K-Means Clustering Algorithm
5.4 Association Rule Learning
5.5 Confusion Matrix in Machine Learning
5.6 Dimensionality Reduction
5.7 Approaches of Dimension Reduction
5.8 Genetic Algorithms
5.9 Use Case: Type 2 Diabetes
References
6 Time-Series Analysis
6.1 Introduction
6.2 Examples of Time-Series Analysis
6.3 Implementing Time-Series Analysis in Machine Learning
6.4 ML Methods For Time-Series Forecasting
6.5 ML Models for Time-Series Forecasting
6.6 Autoregressive Model
6.7 ARIMA Model
6.8 ARCH/GARCH Model
6.9 Vector Autoregressive Model or VAR Model
6.10 LSTM
References
7 Artificial Intelligence in Healthcare
7.1 An Overview of the Development of Intelligent and Expert Systems in the Healthcare Industry
7.2 The Internet of Things in Healthcare: Instant Alerts, Reports, and Automation
7.3 Statistical Descriptions
7.4 Analytical Diagnosis
7.5 Analytical Prediction
7.6 Example Application: Realising Personalised Healthcare
7.7 The Difficulties Presented by Big Data
7.8 Management of Data and Information
7.9 Healthcare-Relevant AI Categories
7.10 What’s Next for AI in the Medical Field
7.11 Summary
References
8 Rule-Based Expert Systems
8.1 Introduction
8.2 The Guidelines for a Knowledge-Representation Method
8.3 Expert System
8.4 Interacting with Expert Systems
8.5 The Anatomy of a Rule-Based Expert System
8.6 Properties of an Expert System
8.7 Inference Methods that Go Forward and Backward in a Chain
References
9 Robotic Process Automation: A Path to Intelligent Healthcare
9.1 Introduction
9.2 The Inner Workings of RPA-Based Medical Solutions
9.3 Applications of RPA in Healthcare
9.4 Advantages of Using Robots in Healthcare Processes
9.5 Use Cases of Robotic Process Automation in Healthcare
9.6 RPA’s Potential Impact on the Healthcare Industry
References
10 Tools and Technologies for Implementing AI Approaches in Healthcare
10.1 Introduction
10.2 Importance of Patient Data Management in Healthcare Industry
10.3 Participants in Healthcare Information Management
10.4 Types of Healthcare Data Management Tools
10.5 Health Fidelity—NLP-Enabled Healthcare Analytics Solution
10.6 Conclusion
References
11 Learning Evaluation for Intelligence
11.1 Introduction
11.2 Modelling Processes and Workflow
11.3 Evaluation Metrics
11.4 Parameters and Hyperparameters
11.5 Tests, Statistical Power, and the Size of an Effect
11.6 Data Variance
References
12 Ethics of Intelligence
12.1 Introduction
12.2 What Is Ethics?
12.3 Principles and Values for Machine Learning and AI
12.4 Health Intelligence
12.5 Policies for Managing Data and Information
References
