Artificial Intelligence : A Tool for Effective Diagnostics.

Format:

Book

Author/Creator:

Khare, Smith K.

Contributor:

Taran, Sachin.

Jamthikar, Ankush D.

Series:

IOP Ebooks Series

Language:

English

Subjects (All):

Artificial intelligence--Medical applications.

Artificial intelligence.

Medical informatics.

Physical Description:

1 online resource (339 pages)

Edition:

1st ed.

Place of Publication:

Bristol : Institute of Physics Publishing, 2024.

Summary:

The book serves a comprehensive resource offering medical research community with all the essential information needed to analyze and study physiological and physical signals as well as Smear Blood Images.

Contents:

Intro

Acknowledgments

Editor biographies

Smith K Khare

Sachin Taran

Ankush D Jamthikar

List of contributors

Contributor biographies

Chapter Introduction to AI-driven diagnostics and human-machine interfaces

1.1 Introduction

1.2 Pipeline for automated decision-making

1.2.1 Input source

1.2.2 Data preparation

1.2.3 Feature engineering and selection

1.2.4 Classification strategies

1.2.5 Performance evaluation

1.3 Effective diagnostics and human-machine interfacing using AI techniques

1.3.1 Effective diagnostics using physiological signals and medical imaging

1.3.2 Effective human-machine interfacing using physiological signals

1.4 Challenges in today's automated decision-making systems

1.4.1 Explainable artificial intelligence

1.4.2 Role of uncertainty quantification

1.4.3 Need for multimodal data

1.4.4 Data privacy

1.5 Conclusions

References

Chapter Recent advancements in emerging technology for healthcare management systems

2.1 Introduction

2.2 Healthcare management systems

2.2.1 The healthcare system in India

2.2.2 Traditional healthcare systems in India

2.2.3 Modern (allopathic) healthcare systems in India

2.3 Literature review

2.4 Artificial intelligence (AI)

2.4.1 Key applications of AI in healthcare

2.4.2 Challenges of AI in healthcare

2.4.3 Advantages of AI

2.5 Blockchain technology (BT)

2.5.1 Need for blockchain in healthcare

2.5.2 Blockchain use cases in healthcare

2.6 IoMT

2.6.1 Challenges of IoMT in healthcare

2.6.2 Advantages of IoMT in healthcare

2.7 IoT-assisted wearable sensor devices

2.7.1 Challenges of IoT-assisted wearable sensor devices in healthcare

2.8 Conclusion

Chapter The role of high-performance computing in processing electronic healthcare records

3.1 Introduction.

3.2 Foundation of electronic healthcare systems

3.2.1 State of electronic health records

3.2.2 Optimization of care delivery

3.2.3 Economic and quality incentives

3.2.4 Data interoperability and exchange

3.2.5 Telehealth and remote care

3.3 Healthcare analytics and big data

3.3.1 Patient-centered innovations

3.3.2 Security and privacy considerations

3.3.3 Implementing high-performance systems

3.3.4 Challenges and barriers to adoption

3.3.5 Scalable solutions for big data analytics in electronic health records

3.3.6 Clinical research and population health

3.3.7 Ethical and regulatory considerations

3.4 Success stories and case studies

3.5 Future trends in health information technology

3.6 Conclusions

Chapter Detection of attention deficit hyperactivity disorder using electroencephalogram signals: a review

4.1 Introduction

4.2 Introduction to the detection of ADHD using EEG signals

4.2.1 Data set

4.2.2 Preprocessing

4.2.3 Feature extraction

4.2.4 Feature selection

4.2.5 Classification

4.3 Literature review

4.4 Conclusions

Chapter Artificial neural network-based classification of eye states using electroencephalogram signals: a comparative analysis of algorithms and artifact removal techniques

5.1 Introduction

5.1.1 Human brain

5.1.2 EEG rhythms

5.1.3 EEG recording using the 10-20 electrode system

5.1.4 Ambulatory EEG recording systems

5.2 Artifacts that contaminate EEG signals

5.3 Existing methods for eliminating various artifacts

5.3.1 Independent component analysis

5.3.2 Principal component analysis

5.3.3 Singular spectrum analysis-adaptive noise cancellation

5.3.4 Fourier-Bessel series expansion empirical wavelet transform-based linear periodic time variation approach.

5.4 Existing artificial neural network-based methods

5.4.1 Wavelet neural network method

5.4.2 Federated learning with matching optimization-based algorithm

5.4.3 Hybrid blind source separation-support vector machine algorithm

5.4.4 Convolutional neural network approach for EEG artifact removal

5.4.5 Recurrent neural network with long short-term memory architecture for EEG artifact removal

5.5 Database

5.6 Proposed algorithm

5.7 Results

5.8 Conclusions

Chapter Hybrid reptile search algorithm-snake optimizer and rational wavelet filter banks for Alzheimer's disease detection

6.1 Introduction

6.2 Methodology

6.2.1 Data set details

6.2.2 Low-complexity orthogonal wavelet filter banks

6.2.3 Feature extraction

6.2.4 Feature selection

6.2.5 Classification models

6.3 Results

6.4 Discussion

6.5 Conclusions

Chapter Mother tree optimization for early detection of focal seizure using entropy-based features

7.1 Introduction

7.2 Used database

7.3 Proposed framework

7.3.1 Derivative operator

7.3.2 Fixed EWT

7.3.3 Feature extraction

7.3.4 Mother tree optimization for feature selection (MTO-FS)

7.3.5 Evaluation of method and classification

7.4 Result and discussion

7.5 Conclusion

List of abbreviations

Chapter Automatic detection of seizure activity using EEG signals

8.1 Introduction

8.2 Resources and method

8.2.1 Databases used

8.2.2 Setting up empirical wavelet transform to separate EEG rhythms

8.2.3 Feature extraction

8.2.4 Feature selection

8.2.5 Classification

8.3 Results and discussion

8.4 Conclusions

Chapter Prediction of rhythm-based abnormalities in electrocardiograms using time-frequency representations

9.1 Introduction.

9.2 Physiology and the basics of the ECG

9.2.1 Anatomy and physiology

9.2.2 Basics of the ECG and its interpretation

9.3 Search strategy

9.4 Acquisition and preprocessing

9.4.1 ECG acquisition and anatomical placement of electrodes

9.4.2 Capturing cardiac activity: understanding the recording process of ECG signals

9.4.3 Preprocessing methods

9.5 Time-frequency representations

9.5.1 Short-time Fourier transform

9.5.2 Wavelet transform

9.6 Role of AI in ECG analysis

9.6.1 Supervised AI algorithms for CVD detection

9.6.2 Unsupervised AI algorithms for CVD detection

9.6.3 Combining supervised and unsupervised AI algorithms for enhanced CVD detection

9.7 Preliminary analysis for predicting ECG rhythm-based abnormality

9.8 Conclusions

Chapter Real-time implementation of ECG beat identification using Hilbert transform and artificial neural network

10.1 Introduction

10.2 Artifacts/noises affecting ECGs

10.3 Related works

10.4 Methodology

10.4.1 Preprocessing

10.4.2 Feature enhancement

10.4.3 QRS complex detection

10.4.4 Feature extraction

10.5 Theory of ANN

10.5.1 Rectified linear unit functions

10.5.2 Softmax function

10.5.3 Step function

10.5.4 Sigmoid function

10.5.5 Hyperbolic tangent function

10.5.6 Exponential linear unit function

10.5.7 Implementation of ANN

10.6 Results and discussion

10.6.1 Experimental setup

10.6.2 R peak identification

10.6.3 ECG beat identification

10.7 Conclusions

References and further reading

Chapter Simulation and review of blood smear image-based leukemia classification using machine learning methods

11.1 Introduction

11.2 Literature review

11.3 Materials and method

11.3.1 Overview of machine vision techniques in PBS image analysis

11.3.2 Methodology.

11.4 Results

11.5 Discussion

11.5.1 Implications

11.5.2 Challenges

11.5.3 Future directions

11.6 Conclusion

Chapter Subject-independent emotion classification using galvanic skin response and electroencephalogram data

12.1 Introduction

12.2 Methodology

12.2.1 Preprocessing

12.2.2 Feature extraction

12.3 Results and discussion

12.4 Conclusions

Chapter Speech emotion recognition using empirical wavelet transform and cubic support vector machine

13.1 Introduction

13.2 Related work

13.3 Methodology

13.3.1 Empirical wavelet transform

13.3.2 Feature extraction

13.3.3 Auditory spectrograms

13.3.4 Auditory cepstral coefficients

13.3.5 Periodicity and harmonicity

13.3.6 Spectral descriptor

13.3.7 Classification algorithms: cubic support vector machine

13.4 Data set

13.5 Results and discussion

13.6 Conclusions

Data availability statement

Conflict of interest statement

Chapter Spectral and spatial analysis of EEG signals for imagined speech recognition

14.1 Introduction

14.2 Materials and methods

14.2.1 Data acquisition

14.2.2 Data pre-processing

14.2.3 Variational mode decomposition

14.2.4 Feature extraction

14.2.5 Classifiers

14.2.6 Performance evaluation

14.3 Experimental protocol

14.3.1 Pre-processing

14.3.2 Selection of an ML algorithm

14.3.3 Expanding the number of classes

14.4 Results

14.4.1 Classification using spectral features

14.4.2 Classification using spatial features

14.4.3 Performance evaluation

14.4.4 Selection of ML algorithm

14.4.5 Expanding the number of classes

14.5 Discussion

14.5.1 Superior performance in the frequency band

14.5.2 Superior performance in the brain area

14.5.3 Best ML algorithm for binary and multiclass classification.

14.5.4 Robustness in expanding the number of classes.

Notes:

Description based on publisher supplied metadata and other sources.

Part of the metadata in this record was created by AI, based on the text of the resource.

ISBN:

9780750359665

0750359668

OCLC:

1477224331