Artificial Intelligence in Medical Sciences and Psychology: With Application of Machine Language, Computer Vision, and NLP Techniques

Table of Contents
About the Author
About the Technical Reviewer
Chapter 1: An Introduction to Artificial Intelligence in Medical Sciences and Psychology
    Context of the Book
    The Book’s Central Point
    Artificial Intelligence Subsets Covered in this Book
    Structure of the Book
    Tools Used in This Book
    Python Distribution Package
    Anaconda Distribution Package
        Jupyter Notebook
    Python Libraries
    Encapsulating Artificial Intelligence
    Implementing Algorithms
        Supervised Algorithms
        Unsupervised Algorithms
    Artificial Neural Networks
    Conclusion
Chapter 2: Realizing Patterns in Diseases with Neural Networks
    Classifying Cardiovascular Disease Diagnosis Outcome Data by Executing a Deep Belief Network
        Preprocessing the Cardiovascular Disease Diagnosis Outcome Data
        Debunking Deep Belief Networks
            Designing the Deep Belief Network
        Relu Activation Function
        Sigmoid Activation Function
        Training the Deep Belief Network
        Outlining the Deep Belief Network’s Predictions
        Considering the Deep Neural Network’s Performance
            Accuracy Fluctuations Across Epochs in Training and Cross-Validation
            Binary Cross-Entropy Loss Fluctuations Across Epochs in Training and Cross-Validation
    Classifying Diabetes Diagnosis Outcome Data by Executing a Deep Belief Network
    Executing a Deep Belief Network to Classify Diabetes Diagnosis Outcome Data
        Outlining the Deep Belief Network’s Predictions
        Considering the Deep Neural Network’s Performance
            Accuracy Fluctuations Across Epochs in Training and Cross-Validation
            Binary Cross-Entropy Loss Fluctuations Across Epochs in Training and Cross-Validation
    Conclusion
Chapter 3: A Case for COVID-19: Considering the Hidden States and Simulation Results
    Executing the Hidden Markov Model
        Descriptive Analysis
    Carrying Out the Gaussian Hidden Markov Model
        Considering the Hidden States in US Confirmed COVID-19 Cases with the Gaussian Hidden Markov Model
    Simulating US Confirmed COVID-19 Cases with the Monte Carlo Simulation Method
        US Confirmed COVID-19 Cases Simulation Results
    Conclusion
Chapter 4: Cancer Segmentation with Neural Networks
    Exploring Cancer
    Exploring Skin Cancer
        Classifying Patient Skin Cancer Outcomes by Executing a CNN
    A CNN Pipeline
    A CNN’s Architectural Structure
        Classifying Skin Cancer Diagnosis Image Data by Executing a CNN
        Preprocessing the Training Skin Cancer Image Data
        Preprocessing the Validation Skin Cancer Image Data
        Generating the Training Skin Cancer Diagnosis Image Data
        Tuning the Training Skin Cancer Image Data
    Executing the CNN to Classify Skin Cancer Diagnosis Image Data
        Considering the CNN’s Performance
            Accuracy Fluctuations Across Epochs in Training and Cross-Validation
            Sparse Categorical Cross-Entropy Loss Fluctuations Across Epochs in Training and Cross-Validation
    Visible Presence of Breast Cancer
        Classifying Ultrasound Scans of Breast Cancer Patients by Executing a CNN
        Preprocessing the Validation Breast Cancer Image Data
        Generating the Training Breast Cancer Diagnosis Image Data
        Tuning the Training Breast Cancer Image Data
    Executing the CNN to Classify Breast Cancer Diagnosis Image Data
        Considering the CNN’s Performance
            Accuracy Fluctuations Across Epochs in Training and Cross-Validation
            Sparse Categorical Cross-Entropy Loss Fluctuations Across Epochs in Training and Cross-Validation
    Conclusion
Chapter 5: Modeling Magnetic Resonance Imaging and X-Rays by Executing Artificial Neural Networks
    Brain Tumors
        MRI Procedure
        Preprocessing the Training MRI Image Data
        Preprocessing the Validation MRI Image Data
        Generating the Training MRI Image Data
        Tuning the Training MRI Image Data
    Executing the CNN to Classify MRI Image Data
        Considering the CNN’s Performance
            Accuracy Fluctuations Across Epochs in Training and Cross-Validation
            Sparse Categorical Cross-Entropy Loss Fluctuations Across Epochs in Training and Cross-Validation
    Pneumonia
    X-Ray Imaging Procedure
        Classifying X-Rays by Executing a CNN
            Processing the X-Ray Image Data
        Generating the Training Chest X-Ray Image Data
        Preprocessing the Validation Chest X-Ray Image Data
            Generating the Validation Chest X-Ray Image Data
        Tuning the Training Chest X-Ray Image Data
    Executing the CNN to Classify Chest X-Ray Image Data
        Considering the CNN’s Performance
            Accuracy Fluctuations Across Epochs in Training and Cross-Validation
            Sparse Categorical Cross-Entropy Loss Fluctuations Across Epochs in Training and Cross-Validation
    Conclusion
Chapter 6: A Case for COVID-19 CT Scan Segmentation
    A Simple Computer Tomography Scan Procedure
        Preprocessing the Training COVID-19 Data
        Preprocessing the Validation COVID-19 CT Scan Data
        Generating the Training COVID-19 CT Scan Data
        Tuning the Training COVID-19 CT Scan Data
    Carrying Out the CNN to Classify COVID-19 CT Scan Data
        Considering the CNN’s Performance
            Accuracy Fluctuations Across Epochs in Training and Cross-Validation
            Sparse Categorical Cross-Entropy Loss Fluctuations Across Epochs in Training and Cross-Validation
    Conclusion
Chapter 7: Modeling Clinical Trial Data
    Clinical Trials
    An Overview of Survival Analysis
    Context of the Chapter
    Exploring the Nelson-Aalen Additive Model
    Descriptive Analysis
    Realizing a Correlation Relationship
    Outlining the Survival Table
    Carrying Out the Nelson-Aalen Additive Model
        Outlining the Nelson-Aalen Additive Model’s Confidence Interval
        Discerning the Survival Hazard
        Discerning the Cumulative Survival Hazard
        Baseline Survival Hazard
    Conclusion
    Reference
Chapter 8: Medical Records Categorization
    Medical Records
    Context of the Chapter
    Categorization with Linear Discriminant Analysis
    Descriptive Analysis
    Preprocessing the Medical Records Data
        Carrying Out a Regular Expression
        Carrying Out Word Vectorization
    Executing the Linear Discriminant Analysis Model to Classify Patients’ Medical Records
        Considering the Linear Discriminant Analysis Model’s Performance
    Conclusion
Chapter 9: A Case for Psychology: Factoring and Clustering Personality Dimensions
    Personality Dimensions
    Questionnaires
    Likert Scale
    Scale Reliability
        Spearman-Brown Reliability Testing Strategy
        Carrying Out the Cronbach’s Reliability Testing Strategy
    Carrying Out the Factor Model
        Carrying Out the Bartlett Sphericity Test
        Carrying Out the Kaiser-Meyer-Olkin Test
        Discerning K with a Scree Plot
        Carrying Out Eigenvalue Rotation
            Varimax Rotation
        Discerning Proportional Variance and Cumulative Variances
    Carrying Out Cluster Analysis
        Carrying Out Principal Component Analysis
        Returning K-Means Labels
        Discerning K-Means Cluster Centers
    Conclusion
Index