Deep Learning for Healthcare Decision Making / editors, Vishal Jain [and three others].

Format:

Book

Contributor:

Jain, Vishal, 1983- editor.

Series:

River Publishers series in biomedical engineering.

Biomedical Engineering Series

Language:

English

Subjects (All):

Medicine--Decision making--Data processing.

Medicine.

Deep learning (Machine learning).

Medical informatics--Data processing.

Medical informatics.

Medical care--Data processing.

Medical care.

Physical Description:

1 online resource (312 pages)

Edition:

First edition.

Place of Publication:

Gistrup, Denmark : River Publishers, [2022]

Summary:

This book is an attempt to unveil the hidden potential of the enormous amount of health information and technology. This book is written with the intent to uncover the stakes and possibilities involved in realizing personalized health-care services through efficient and effective deep learning algorithms.

Contents:

Cover

Half Title

Series Page

Title Page

Copyright Page

Table of Contents

Preface

Acknowledgment

List of Figures

List of Tables

List of Contributors

List of Abbreviations

Chapter 1: Amalgamation of Deep Learning in Healthcare Systems

1.1: Introduction to Deep Learning

1.2: Deep Learning in Healthcare

1.3: Artificial Intelligence in the Healthcare System

1.4: Machine Learning in Healthcare

1.5: Natural Language Processing (NLP) in Healthcare

1.6: Deep Learning Models

1.6.1: Interpretation of deep learning models in medical images

1.6.1.1: Convolutional neural networks (CNNs)

1.6.1.2: Recurrent neural networks (RNNs)

1.6.1.3: Restricted boltzmann machines (RBMs) and deep belief networks (DBNs)

1.6.1.4: Deep neural network (DNN)

1.6.1.5: Generative adversarial network (GAN)

1.7: Radiologic Applications using Deep Learning

1.7.1: Image classification

1.7.2: Object detection

1.7.3: Image segmentation and registration

1.7.4: Image generation

1.7.5: Image transformation

1.7.5.1: Without the use of a generative adversarial network, image to image translation is possible

1.7.5.2: GAN for image-to-image translation

1.8: Predictive Analysis using Deep Learning and Machine Learning

1.9: Clinical Trials using Deep Learning

1.10: Applications of Deep Learning in the Healthcare System

1.10.1: Drug discovery

1.10.2: Medical imaging

1.10.3: Insurance fraud

1.10.4: Alzheimer's disease

1.10.5: Genome

1.10.6: Healthcare data analytics

1.10.7: Mental health chatbots

1.10.8: Personalized medical treatments

1.10.9: Prescription audit

1.10.10: Responding to patient queries

Conclusion

References

Chapter 2: Deep Neural Network Architecture and Applications in Healthcare

2.1: Introduction

2.2: Deep Neural Network.

2.3: Deep Learning Architectures Applied in the Healthcare Field

2.3.1: Alzheimer's disease

2.3.2: Brain mris

2.3.3: Osteoarthritis

2.3.4: Breast cancer

2.3.5: Diabetic retinopathy

2.3.6: Forecasting type of medicine based on patient history

2.3.7: Forecasting diseases through patient's clinical status

2.3.8: Forecasting suicide

2.3.9: Forecasting readmission of patients after the discharge

2.3.10: Forecasting disease from lab test

2.3.11: Forecasting the quality of sleep by awake time activities

2.4: Pneumonia Detection using Deep Learning from X-ray Images

2.4.1: Overview

2.4.2: Methodology

2.4.2.1: Visualizing the images

2.4.2.2: Resizing

2.4.3: Results

2.4.3.1: ROC curve

2.4.3.2: Confusion matrix

Chapter 3: The State of the Art of using Artificial Intelligence for Disease Identification and Diagnosis in Healthcare

3.1: Introduction

3.2: A Review of the Literature on Machine Learning and Artificial Intelligence in Healthcare

3.2.1: Machine learning applications in healthcare

3.2.2: Applications of artificial intelligence in healthcare

3.3: How to Develop Machine Learning Methods for Healthcare

3.3.1: Healthcare problem selection

3.3.2: Dataset construction

3.3.3: Model development

3.3.4: Model performance evaluation

3.3.5: Clinical impact evaluation

3.4: Disease Prediction and Diagnosis Using Artificial Intelligence

3.4.1: Disease prediction and diagnosis using machine learning

3.4.2: Artificial intelligence technology for clinical diagnosis

3.5: Challenges of using Artificial Intelligence Algorithms in Healthcare

Chapter 4: Segmentation of MRI Images of Gliomas using Convolutional Neural Networks

4.1: Introduction

4.2: Aim

4.3: Objectives

4.4: Methodology.

4.5: Implementation

4.5.1: Initial image processing

4.5.2: Training phase

4.5.3: Testing phase

4.5.4: Classification algorithm

4.6: Results

4.6.1: Training results

4.6.2: Test results

4.6.3: Dice scores

4.6.4: Positive Predictive Value (PPV)

4.6.5: Sensitivity

Future Prospects

Chapter 5: Automatic Liver Tumor Segmentation from Computed Tomography Images Based on 2D and 3D Deep Neural Networks

5.1: Introduction

5.2: Related Concepts

5.2.1: Segmentation

5.2.2: Computed tomography

5.2.3: 3D convolution

5.2.4: Separable convolution

5.2.5: Depthwise spatio-temporal separate

5.2.6: U-net

5.2.7: Efficientnet

5.2.8: Loss function

5.2.9: Metrics

5.2.9.1: Overlapping metrics

5.3: Related Work

5.4: Methodology

5.4.1: Data normalization and compression

5.4.2: Batch sampling

5.4.3: Data augmentation

5.4.4: Neural network architecture

5.4.5: Efficientnet modifications

5.4.6: Liver postprocessing

5.4.7: Mask combination

5.4.8: Tumor postprocessing

5.4.9: Network training

5.4.10: Dataset

5.5: Experiments

5.5.1: Local experiments setup

5.5.1.1: 2D models

5.5.1.2: 3D models

5.5.2: Local evaluation

5.5.3: LiTS challenge evaluation

Chapter 6: Advancements in Deep Learning Techniques for Analyzing Electronic Medical Records

6.1: Introduction

6.2: Overview of EHR

6.2.1: Characteristics of EHR

6.2.2: Categories of EHR data

6.2.3: Doctor's notes

6.3: Machine Learning and Deep Learning in EHR

6.3.1: Multilayer Perceptron (MLP) network

6.3.2: Convolutional Neural Network (CNN)

6.3.3: Recurrent Neural Network (RNN)

6.3.4: Restricted boltzmann machine

6.3.5: Autoencoders

6.4: Deep Learning Analysis of EHR

6.4.1: Extraction of information.

6.4.1.1: Concept extraction

6.4.1.2: Time event extraction

6.4.1.3: Correlation extraction

6.4.1.4: Acronym expansion

6.4.2: Ehr representation

6.4.3: Evaluation of representation

6.4.4: Diagnosis of disease

6.4.5: Evaluation metric

6.4.6: Risk identification and survival prediction

6.5: EHR Data Set

6.6: Research Gap

6.7: Suggestions for Improvement

6.7.1: Tuning activation function

6.7.2: Constraints

6.7.3: Qualitative clustering

6.7.4: MIMIC learning

Chapter 7: Telemedicine-based Development of M-Health Informatics using AI

7.1: Introduction

7.1: Objectives of Chapter

7.2: Literature Review

7.3: Wireless Technologies in m-Health

7.3.1: Wireless medical sensor technologies

7.4: Signals for Biomonitoring

7.4.1: Wireless communication for biomonitoring

7.5: Telemedicine Application Server

7.5.1: Server protocols

7.5.2: Server graphical user interface

7.6: Interface Program

7.6.1: Patient interface

7.6.2: Doctor browser interface

7.7: Experiment Work

Chapter 8: Health Informatics System using Machine Learning Techniques

8.1: Introduction

8.1.1: COVID-19 pandemic

8.1.2: Necessity of AI

8.1.3: Artificial intelligence vs. Machine learning vs. deep learning

8.1.4: Healthcare informatics systems and analytics

8.2: Concept of Blockchain

8.2.1: Network architecture of blockchain

8.3: Concept of Data Leak and How It Is Overcome using Blockchain

8.3.1: Data breach targets

8.3.2: Data breach threats

8.3.3: Data breach consequences

8.4: Present Situation and Future Perspective

8.4.1: Drug traceability

8.4.2: Clinical trials

8.4.3: Management of patient data

8.5: Existing Challenges in the Future

8.5.1: Data security and privacy

8.5.2: Storage capacity management.

8.5.3: Interoperability issues

8.5.4: Standardization challenges

8.5.5: Social challenges

Chapter 9: Blockchain in Healthcare: A Systematic Review and Future Perspectives

9.1: Introduction

9.2: Healthcare Challenges vs. Blockchain Opportunities

9.2.1: Interoperability

9.2.2: Tampering/data security

9.2.3: Insurance fraud

9.2.4: Drug stealing

9.3: Introduction to Blockchain

9.3.1: Structure of blocks and blockchain

9.3.2: Types of blockchain networks

9.3.3: Consensus algorithms

9.3.4: Smart contracts

9.4: Research Methodology

9.5: Literature Review

9.6: Discussion

9.6.1: RQ1: What type of blockchain network and blockchain platform has been used by researchers in their healthcare applications?

9.6.2: RQ2: What are the important consensus algorithms used in blockchain-based healthcare systems?

9.6.3: RQ3: What proportion of research works have built smart contracts in their healthcare systems and which programming languages have they used?

9.6.4: RQ4: What are the evaluation methods used by researchers for analyzing their models?

9.6.5: RQ5: What are the drawbacks of the existing blockchain systems related to healthcare and what are the future perspectives?

9.7: Challenges and Future Scope

9.7.1: Lack of standardization

9.7.2: Scalability

9.7.3: Latency

9.7.4: Privacy of outsourced data

Chapter 10: Fusion of Machine Learning and Blockchain Techniques in IoT-basedSmart Healthcare Systems

10.1: Introduction

10.2: Literature Review

10.3: Issues and Challenges While Establishing IoT In Healthcare

10.4: Involvement of Blockchain Technique in the Healthcare System

10.4.1: Securing and tracking health supplies

10.4.2: Storing health information

10.4.3: Remote patient monitoring.

10.4.4: Disease outbreak and tracking.

Notes:

Includes index.

Includes bibliographical references and index.

Description based on print version record.

ISBN:

9781003373261

1003373267

9781000846546

1000846547

9781000846522

1000846520

9788770223881

8770223882

OCLC:

1347783482