Video Health Monitoring in Hospitals.

Format:

Book

Author/Creator:

Wang, Wenjin.

Language:

English

Subjects (All):

Patient monitoring.

Video recording in medicine.

Physical Description:

1 online resource (0 pages)

Edition:

1st ed.

Place of Publication:

Chantilly : Elsevier Science & Technology, 2025.

Summary:

Video Health Monitoring in Hospitals discusses the emergence of camera-based, contactless physiological measurement as a groundbreaking solution in healthcare monitoring.The book highlights the technology's non-invasiveness, capacity for continuous and long-term monitoring, and its ability to capture not only vital signs but also contextual.

Contents:

Front Cover

Video Health Monitoringin Hospitals

Copyright Page

Contents

List of contributors

About the authors

Preface

List of abbreviations

1 Introduction

2 Camera-based physiological measurement: fundamentals and methodologies

2.1 Introduction

2.2 Circulatory system

2.3 Respiratory system structure and functions

2.4 Cardiovascular system structure and functions

2.5 Hemodynamics

2.6 Blood pressure

2.7 Pulse wave propagation

2.8 Skin structure and properties

2.9 Skin perfusion

2.10 Observable and measurable effects

2.11 Typical ranges of measured parameters

2.12 Camera-based physiological measurement and applications

2.13 Conclusion

References

3 Monitoring of deterioration in intensive care units patients

3.1 Introduction

3.1.1 Aim

3.1.2 Outline

3.2 Research status

3.2.1 Application of camera-based visual technology in critical care environments in hospitals

3.2.2 Autonomous decision systems based on cameras in clinical settings

3.3 Experimental device design and clinical data collection

3.3.1 Pulse rate and respiration rate data collection from critically ill patients

3.3.2 Cardiovascular rate variability clinical data collection

3.4 Remote vital signs monitoring system

3.4.1 Algorithmic framework for extracting cardiopulmonary physiological parameters from video

3.4.2 Analysis and processing for extracting pulse rate variability features from videos

3.4.2.1 Camera-photoplethysmography extraction and processing

3.4.2.2 Cardiovascular rate variability analysis methods

3.4.2.3 Design of an early warning classification model

3.5 Experimental results and discussion in intensive care unit scenarios

3.5.1 Monitoring performance of closed-circuit television cameras.

3.5.2 Physiological signal monitoring during ultrasound diagnosis

3.5.3 Continuous monitoring capability of the system for patient physiological signals

3.5.4 Comparison and analysis of cardiovascular rate variabilityfeature estimation using contact and noncontact devices

3.5.5 Classifying healthy individuals and intensive care unit patients based on heart rate variability/pulse rate variability

3.6 Conclusions

4 Patient facial attribute monitoring for sleep wake detection

4.1 Introduction

4.1.1 Aim

4.1.2 Outline

4.2 Clinical trial

4.2.1 Intensive care unit dataset construction

4.2.2 Neonatal intensive care unit dataset construction

4.3 Methodology

4.3.1 Handcrafted feature-based method

4.3.1.1 Handcraft feature extraction

4.3.1.2 Handcraft-based model applied in intensive care unit

4.3.1.3 Handcraft-based model applied in neonatal intensive care unit

4.3.2 End-to-end method

4.3.2.1 Deep learning features with transfer learning

4.3.2.2 Consistent deep representation constraint for neonatal intensive care unit infants

4.3.2.2.1 Intrasubject consistency constraint, Lintra-sub

4.3.2.2.2 Intrasubject consistency constraint, Linter-sub

4.4 Results and discussion

4.4.1 Statistical analysis for intensive care unit scenario

4.4.1.1 Evaluation metrics

4.4.1.2 Statistical analysis of benchmark and transfer model

4.4.2 Statistical analysis for neonatal intensive care unit scenario

4.4.2.1 Evaluation metrics

4.4.2.2 Statistical analysis of benchmark system

4.4.3 Statistical analysis of consistent deep representation constraint

4.4.4 External validation of consistent deep representation constraint

4.5 Conclusions

5 Video-based sleep staging in sleep centers

5.1 Introduction

5.1.1 Aim

5.1.2 Outline

5.2 Methods and materials.

5.2.1 Clinical trial

5.2.2 Sleep feature extraction

5.2.2.1 Pulse rate and respiratory rate

5.2.2.2 Pulse rate variability

5.2.2.3 Motion

5.2.3 Optimization strategies

5.2.3.1 Motion-assisted quality metrics

5.2.3.2 Wake stage based model personalization

5.2.3.3 Fusion rapid eye movement stage detection

5.2.4 Classification methods

5.2.4.1 Feature trend analysis

5.2.4.2 Sleep classification model

5.3 Experimental results

5.3.1 Basic evaluation

5.3.1.1 Pulse rate and respiratory rate

5.3.1.2 Pulse rate variability

5.3.1.3 Motion

5.3.1.4 Basic performance

5.3.2 Optimization outcomes

5.3.2.1 Motion-assisted quality metrics

5.3.2.2 Wake stage based model personalization

5.3.2.3 Fusion rapid eye movementstage detection

5.3.3 Evaluation

5.3.3.1 Overall performance

5.3.3.2 Result with practical challenges

5.3.3.3 Camera versus polysomnography

5.4 Discussion

5.5 Conclusions

6 Privacy-protected sleep monitoring

6.1 Introduction

6.1.1 Aim

6.1.2 Outline

6.2 Methods and materials

6.2.1 Defocusing principle

6.2.2 Pulse rate, respiratory rate, and movement

6.2.3 Sleep posture

6.3 Experimental setup

6.3.1 Measurement system and protocol

6.3.2 Benchmark dataset

6.3.3 Reference data

6.3.4 Evaluation metrics

6.3.4.1 Pulse rate, respiratory rate, and movement

6.3.4.2 Sleep posture

6.4 Results and discussion

6.4.1 Facial privacy protection test

6.4.2 Pulse rate, respiratory rate, and movement

6.4.3 Sleep posture

6.5 Conclusion

7 Premature infant monitoring in neonatal intensive care units

7.1 Introduction

7.1.1 Aim

7.1.2 Outline

7.2 Methods and materials

7.2.1 Clinical study

7.2.1.1 Study design and protocol

7.2.1.2 Instrumentation

7.2.2 Cardiorespiratory parameters monitoring.

7.2.2.1 Predefined body-RoI and skin-RoI

7.2.2.2 Local remote plethysmography extraction

7.2.2.3 Local respiration extraction

7.2.2.4 Pulse rate and respiratory rate estimation

7.2.2.5 Cardiovascular rate variability analysis

7.2.2.6 Respiratory rate variability analysis

7.2.3 Postmenstrual age estimation using cardiovascular rate variability

7.2.3.1 Postmenstrual age prediction using cardiovascular rate variability

7.2.3.2 Preterm/term classification using cardiovascular rate variability

7.3 Results and discussions

7.3.1 Local pulse-RoI and resp-RoI detection

7.3.2 Pulse rate and respiratory rate estimation

7.3.3 Pulse rate variability analysis

7.3.4 Respiratory rate variability analysis

7.3.5 Postmenstrual age regression and preterm/term classification

7.4 Conclusions

8 Infant cry detection and interpretation in neonatal care

8.1 Introduction

8.1.1 Aim

8.1.2 Outline

8.2 Related work

8.2.1 Automatic infant cry detection and interpretation

8.2.2 Multitask convolutional neural networks

8.2.3 Attention mechanisms

8.3 Infant cry datasets

8.3.1 deBarbaroCry dataset

8.3.2 Unconstrained clinical dataset

8.3.3 Baby Chillanto dataset

8.3.4 Preprocessing

8.4 Methods

8.4.1 System overview

8.4.2 Efficient multitask attention

8.4.2.1 Efficient multitask spatial attention

8.4.2.2 Efficient multitask channel attention

8.4.3 Contrastive mixture-of-experts

8.4.3.1 Mixture-of-experts

8.4.3.2 Supervised contrastive learning

8.4.4 Hybrid loss function

8.5 Experiments and discussion

8.5.1 Experimental setup

8.5.2 Analysis of infant cry detection and interpretation

8.5.2.1 Arrangement of efficient multitask attention modules

8.5.2.2 Analysis of contrastive mixture-of-experts

8.5.3 Performance comparison.

8.5.4 Result visualization

8.5.5 Discussion

8.6 Conclusions

9 Image-based infant height and weight estimation in obstetrics

9.1 Introduction

9.1.1 Aim

9.1.2 Outline

9.2 Materials and methods

9.2.1 Clinical infant dataset

9.2.2 Network architecture

9.2.3 Evaluation metrics

9.3 Results and discussion

9.3.1 Implementation details

9.3.2 Results and analysis

9.3.3 Limitations and challenges

9.4 Conclusions

Acknowledgment

10 Chest respiratory imaging for assessing rehabilitation of thoracic surgery patients

10.1 Introduction

10.1.1 Aim

10.1.2 Outline

10.2 Methods and materials

10.2.1 Clinical trial

10.2.2 Camera-based respiratory imaging

10.2.3 Classification methods

10.2.3.1 Handcrafted feature-based model

10.2.3.2 End-to-end model

10.2.4 Classification enhancement

10.2.4.1 Prior knowledge-based data augmentation

10.2.4.2 Multiple-prototype generation and contrast

10.3 Experimental results

10.3.1 Evaluation strategy

10.3.2 Lesion detection

10.3.3 Statistical analysis

10.3.4 Benchmark results

10.4 Discussion

10.5 Conclusions

11 Foot plantar perfusion imaging for predicting peripheral arterial diseases

11.1 Introduction

11.1.1 Aim

11.1.2 Outline

11.2 Methods and materials

11.2.1 Experimental design

11.2.2 Camera-based plantar perfusion imaging

11.2.3 Camera-based plantar perfusion imaging feature engineering

11.2.4 Classification model and evaluation strategy

11.3 Results and discussion

11.3.1 Feasibility of camera-based plantar perfusion imaging for evaluating arterial blockage

11.3.2 Performance of camera-based plantar perfusion imaging on arterial blockage detection

11.3.3 Performance of camera-based plantar perfusion imaging on arterial blockage classification.

11.3.4 Limitations and future works.

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:

0-443-26587-9

9780443265877

OCLC:

1558598730