Advancing healthcare through decision intelligence : machine learning, robotics, and analytics in biomedical informatics /

Advancing Healthcare through Decision Intelligence: Machine Learning, Robotics, and Analytics in Biomedical Informatics demonstrates real-world applications of decision intelligence - specifically machine learning, robotics, and analytics - to drive innovation and improvements in healthcare delivery...

Full description

Bibliographic Details
Corporate Author:	ScienceDirect (Online service)
Other Authors:	Dey, Somen (Editor), Kumar, Vidyapati (Editor), Pratihar, Dilip Kumar (Editor), SIngh, Vibhav Prakash (Editor), Islam, Sardar (Editor)
Format:	eBook
Language:	English
Published:	London : Academic Press, 2025.
Subjects:	Artificial intelligence > Medical applications. Electronic books.
Online Access:	Connect to the full text of this electronic book

Table of Contents:

Front Cover
Advancing Healthcare through Decision Intelligence
Copyright Page
Contents
List of contributors
1 Foundations of decision intelligence in healthcare: Integrating machine learning, robotics, and biomedical analytics
1.1 Introduction to the edited volume
References
Theme 1 Biomedical informatics: data analytics for improved healthcare outcomes
2 Deep learning techniques for agricultural plant health assessment: a case study on tomato plant
2.1 Introduction
2.2 Methodology
2.2.1 Dataset preparation
2.2.2 Data augmentation
2.2.3 Deep learning models
2.2.3.1 VGG16
2.2.3.2 ResNet50
2.2.3.3 InceptionV3
2.2.3.4 MobileNetV2
2.2.4 Loss function and optimiser
2.2.5 Model training
2.2.6 Evaluation metrics
2.3 Results and discussion
2.4 Conclusions
References
3 A systematic analysis of effectiveness of music therapy in children with autism spectrum disorder
3.1 Introduction
3.1.1 Literature survey
3.2 Methodology
3.2.1 Research design
3.2.2 Participant delection
3.2.3 Randomization and control
3.2.4 Intervention
3.2.5 Outcome measures
3.2.6 Data collection and analysis
3.2.7 Ethical considerations
3.2.8 Limitations and future directions
3.2.9 Architecture
3.2.10 Pretraining
3.2.11 Input and preprocessing
3.2.12 Feature extraction
3.2.13 Fully connected layers
3.2.14 Training
3.2.15 Face recognition
3.2.16 Quiz version
3.2.17 Webcam version
3.3 Results
3.4 Discussion
Acknowledgment
References
4 Bioinformatics, healthcare informatics and analytics: an imperative for improved healthcare system
4.1 Introduction
4.1.1 Importance of bioinformatics in healthcare
4.1.1.1 Bioinformatics' significance in medication development and repurposing
4.1.1.1.1 Drug development
4.1.1.1.2 Drug repurposing.
4.1.1.1.3 The importance of bioinformatics for precision medicine
4.1.1.1.4 Bioinformatics's significance in daily life
4.1.2 Role of healthcare informatics in improving patient care
4.1.2.1 Health informatics enhances patient care in five ways
4.2 Bioinformatics in healthcare
4.2.1 DNA sequencing and analysis
4.2.1.1 Excelra: enabling next-generation sequencing modalities
4.2.1.2 Molecular biology, genomics, and DNA sequencing: the three-pronged indicator of scientific breakthrough
4.2.1.3 Examining the potential of DNA sequence analysis in drug development
4.2.2 Drug development &amp
pharmacogenomics
4.2.2.1 Drug target identification
4.2.2.2 Bioinformatics and pharmacogenomics' roles in the process of finding and developing new drugs
4.2.2.3 Healthcare informatics
4.2.3 Predictive analytics for disease prevention
4.2.3.1 Use of predictive analytics in healthcare
4.2.3.2 Benefits of predictive analytics in healthcare: (Fig. 4.4)
4.2.4 Challenges in bioinformatics: data integration, scalability, and standardization
4.2.4.1 Data integration
4.2.4.2 Challenges and opportunities
4.2.4.3 Integration of healthcare informatics systems
4.2.4.4 Future directions
4.2.4.5 Where is bioinformatics headed?
4.2.4.6 Key player in the future of bioinformatics
4.2.5 Artificial intelligence and machine learning in healthcare
4.2.5.1 Clinical risk prediction models that are self-monitoring, dynamic, and automatically updated
4.2.5.2 Predictive modeling and the learning health system's vision
4.2.5.3 Frameworks for clinical predictive algorithms validation
4.2.6 Blockchain technology for secure medical data management
4.2.6.1 Data integrity
4.2.6.2 Security
4.2.6.3 Decentralization
4.2.6.4 Interoperability
4.2.6.5 Transparency and auditability.
4.2.6.6 Research and analytics
4.2.6.7 Supply chain management
4.3 Conclusion
References
5 Measuring the impact of predictive analytics on patient satisfaction
5.1 Introduction
5.2 Literature review
5.3 Methodology
5.3.1 Study design
5.3.2 Data collection
5.3.2.1 Patient demographics and historical data
5.3.2.2 Real-time patient feedback
5.3.2.3 Predictive analytics data
5.3.2.4 External factors
5.3.3 Predictive analytics models
5.3.3.1 Machine learning models
5.3.3.2 Deep learning models
5.3.3.3 Real-time analytics
5.3.3.4 Model evaluation and refinement
5.3.4 Ethical considerations
5.3.5 Statistical
5.3.6 Reporting and feedback loop
5.4 Result analysis
5.5 Conclusion
References
Theme 2 Decision intelligence in biomedical data analytics and management
6 Hybrid optimization of bag composition for disease diagnosis: integrating teaching-learning-based optimization with genetic algorithm
6.1 Introduction
6.1.1 Background
6.1.2 Motivation
6.2 Proposed methodology
6.2.1 Novel fitness function
6.3 Experimental setup and results analysis
6.3.1 Experimental results
6.3.2 Analysis of results
6.3.3 Statistical analysis
6.4 Conclusion
6.4.1 Future Directions
References
Theme 3 Robotics and robots in biomedical informatics
7 Blockchain in healthcare: Unveiling trends and applications through bibliometric and thematic analysis
7.1 Introduction
7.2 Methodology
7.3 Results
7.3.1 Annual scientific production
7.3.2 Global cited documents
7.3.3 Trend topics
7.3.4 Most influential sources
7.3.5 Word cloud analysis
7.3.6 Thematic analysis
7.4 Conclusion
References
8 Enhancing social skills development in children with autism through robotic interventions
8.1 Introduction.
8.2 Traditional therapies and their limitations
8.3 Types of robotic interventions
8.4 Social engagement in human-robot interaction
8.5 Practical considerations of robotic interventions
8.6 Considerations and challenges
8.7 Conclusion and future directions
References
9 Intelligent ankle-foot prosthetics: from engineering fundamentals to integrated artificial intelligence systems
9.1 Introduction
9.2 Engineering fundamentals of ankle-foot prosthetics
9.2.1 Material selection
9.2.2 Gait biomechanics
9.3 Prosthetic foot
9.3.1 Passive ankle-foot
9.3.2 Powered ankle-foot
9.3.3 Sensor-based data acquisition and artificial intelligence
9.3.4 Integration of artificial intelligence and control systems
9.4 Summary
References
Theme 4 Precision medicine and personalized treatment
10 Precision medicine and personalized treatment
10.1 Introduction
10.2 Related work
10.3 Foundations of precision medicine
10.3.1 Genomics and molecular biology
10.3.2 Advances in Omics technologies
10.3.3 Biomarkers and their significance
10.4 Role of data in precision medicine
10.4.1 Data analytics and artificial intelligence in precision medicine
10.4.2 Integration of big data in healthcare analytics
10.5 Transformative impact on patient outcomes and healthcare economics
10.5.1 Tailored treatment regimens and individualized care
10.6 Interoperability and standardization
10.6.1 Interoperability
10.6.2 Standardization
10.7 Case studies
10.7.1 Global Initiatives and collaborations
10.7.2 Precision medicine initiatives worldwide
10.7.3 Collaborative efforts and consortia
10.7.4 ELSI implications
10.8 Conclusion
References
11 Voxel-based analysis and advanced techniques for MRI scan classification in early diagnosis of Parkinson's disease
11.1 Introduction.
11.2 Methodology
11.2.1 Data collection
11.2.2 Voxel-based morphometry
11.2.3 Data augmentation
11.2.4 Detection of region of interest
11.2.5 Feature extraction from region of interest
11.2.6 Feature selection
11.2.6.1 Principal component analysis
11.2.7 Classification algorithm
11.2.7.1 Support vector machine
11.2.7.2 K-nearest neighbours
11.2.7.3 Random Forest
11.2.7.4 Navie Bayes
11.2.7.5 Multi-layer perceptron
11.2.7.6 Logistic regression
11.3 Result
11.4 Conclusion
Acknowledgement
References
12 Predicting metallic implant degradation through patient-specific computational modeling
12.1 Introduction
12.2 Popular methods for degradation prediction of metallic implants
12.2.1 Finite element analysis
12.2.2 Molecular dynamics
12.2.3 Machine learning driven modeling
12.3 Conclusion
References
Theme 5 Ethics, trust, and explainability in biomedical analytics
13 Ethical concerns in healthcare analytics: exploring the complexities of data-driven decision making
13.1 Introduction
13.2 Ethical considerations in healthcare analytics
13.2.1 Importance of ethics
13.2.2 Informed consent in data collection and use
13.2.3 Bias and fairness
13.3 Discrimination in healthcare analytics
13.4 Privacy concerns in healthcare analytics
13.4.1 Data protection regulations
13.4.2 Anonymization and deidentification
13.5 Security in healthcare analytics
13.5.1 Cybersecurity threats
13.5.2 Security measures
13.5.3 Best practices
13.6 Explainability and Interpretability in healthcare analytics
13.6.1 Challenges
13.6.1.1 Complexity of models
13.6.1.2 Trade-off between accuracy and interpretability
13.6.1.3 Data quality and bias
13.6.1.4 Model validation and performance
13.6.1.5 Regulatory and legal considerations.