Medical Analytics for Clinical and Healthcare Applications

• Record Nr.: UNINA9911022471703321
• Autore: Kalita Kanak
• Pubbl/distr/stampa: Newark : , : John Wiley & Sons, Incorporated, , 2025; ©2025
• ISBN: 1-394-30148-0; 1-394-30147-2
• Edizione: [1st ed.]
• Descrizione fisica: 1 online resource (283 pages)
• Collana: Machine Learning in Biomedical Science and Healthcare Informatics Series
• Altri autori (Persone): ZindaniDivya; GaneshNarayanan; GaoXiao-Zhi
• Disciplina: 610.285
• Soggetti: Medical informatics
• Lingua di pubblicazione: Inglese
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Nota di contenuto: Cover -- Series Page -- Title Page -- Copyright Page -- Contents -- Preface -- Part 1: Foundations of Medical Analytics -- Chapter 1 Exploring Trends in Depression and Anxiety Using Machine and Deep Learning Models -- 1.1 Introduction -- 1.2 Exploratory Data Analysis -- 1.2.1 Exploratory Data Analysis (EDA) -- 1.2.2 Interactive Visualizations with Plotly -- 1.2.3 Data Cleaning and Transformation -- 1.2.4 Chart Creation with Matplotlib and Seaborn -- 1.2.5 Documentation and Report Writing -- 1.3 Problem Statement and Motivation -- 1.4 Literature Survey -- 1.5 Data Visualization -- 1.5.1 Integration of Machine Learning-Powered Insights -- 1.5.2 Dynamic Time-Series Visualizations with Plotly -- 1.5.3 Fusion of Art and Data with Seaborn Styling -- 1.5.4 Ethical Considerations in Visual Storytelling -- 1.5.5 Seamless Collaboration Through Git Version Control -- 1.6 Overview of Dataset -- 1.6.1 Dataset Acquisition Links -- 1.6.2 Household Pulse Survey -- 1.7 Methodology -- 1.7.1 Data Selection and Attributes -- 1.7.2 Data Pre-Processing -- 1.8 Modules -- 1.8.1 Linear Regression -- 1.8.2 K-Means Clustering -- 1.8.3 Random Forest -- 1.8.4 Simple Convolutional Neural Network (CNN) -- 1.8.5 MobileNetV2 -- 1.8.6 Basic Visualizations -- 1.9 Results and ; Discussion -- 1.10 Conclusion -- References -- Part 2: Disease Detection and Diagnosis -- Chapter 2 An Innovative Framework for the Detection and Classification of Breast Cancer Disease Using Logistic Regression Compared with Back Propagation Neural Network -- 2.1 Introduction -- 2.2 Materials and Methods -- 2.2.1 Back Propagation Neural Network (BPNN) -- 2.2.2 Logistic Regression (LR) -- 2.2.3 Statistical Analysis -- 2.3 Results -- 2.4 Discussion -- 2.5 Conclusion -- References -- Chapter 3 An Approach to Conduct the Diabetes Prediction Using AdaBoost Algorithm Compared with Decision Tree Classifier Algorithm.; 3.1 Introduction -- 3.2 Materials and Methods -- 3.2.1 AdaBoost Algorithm -- 3.2.1.1 Procedure for AdaBoost Algorithm -- 3.2.1.2 Decision Tree -- 3.2.1.3 Statistical Analysis -- 3.3 Results and Discussion -- 3.4 Conclusion -- References -- Chapter 4 Efficient Net V2-Based Pneumonia Detection: A Comparative Study with Transfer Learning Models -- 4.1 Introduction -- 4.2 Related Works -- 4.3 Materials and Methods -- 4.3.1 Dataset Details -- 4.3.2 CLAHE -- 4.3.3 Data Augmentation -- 4.3.4 Transfer Learning Models -- 4.3.4.1 VGG-16 -- 4.3.4.2 Xception -- 4.3.4.3 EfficientNetV2 -- 4.4 Results and Discussion -- 4.4.1 Ensemble Model -- 4.5 Conclusion and Future Work -- References -- Chapter 5 A Histogram Equalized Median Filtered SIFT-EfficientNet Based on Deep Learning Approach for Lung Disease Detection -- 5.1 Introduction -- 5.2 Related Works -- 5.3 Materials and Methods -- 5.3.1 Dataset -- 5.3.2 Methodology: HMS-E -- 5.3.3 Pre-Processing -- 5.3.4 Histogram Equalization -- 5.3.5 Median Filter -- 5.3.6 Feature Extraction -- 5.3.6.1 Detection of Scale-Space Extrema -- 5.3.6.2 Localization of Key Points -- 5.3.6.3 Generation of Key Point Descriptors -- 5.3.7 Deep Learning Model -- 5.3.7.1 EfficientNetB0 -- 5.4 Performance Measure -- 5.5 Results and Discussion -- 5.6 Conclusion and Future Work -- References -- Part 3: Predictive Analytics in Healthcare -- Chapter 6 Comparing the Efficiency of ResNet-50 and Convolutional Neural Networks for Facial Mask Detection -- 6.1 Introduction -- 6.2 Materials and Methods -- 6.3 ResNet-50 Architecture -- 6.4 Convolutional Neural Networks (CNN) -- 6.5 Statistical Analysis -- 6.6 Results and Discussion -- 6.7 Conclusion -- References -- Chapter 7 Enhancing Accuracy in Predicting Knee Osteoarthritis Progression Using Kellgren-Lawrence Grade Compared with Deep Convolutional Neural Network -- 7.1 Introduction.; 7.2 Materials and Methods -- 7.2.1 Kellgren-Lawrence Grade -- 7.2.2 Deep Convolutional Neural Network -- 7.2.3 Statistical Analysis -- 7.3 Results and Discussion -- 7.3.1 Accuracy and Loss Analysis -- 7.3.2 Group Statistical Analysis -- 7.3.3 Independent Sample T-Test Results -- 7.3.4 Performance Comparison -- 7.3.5 Discussion -- 7.4 Conclusion -- References -- Chapter 8 A Comparative Analysis of Support Vector Machine over K-Neighbors Classifier for Predicting Hospital Mortality with Improved Accuracy -- 8.1 Introduction -- 8.1.1 Integration of Present-On-Admission Indicators -- 8.1.2 Challenges in Implementing Machine Learning Models -- 8.1.3 Predicting in-Hospital Mortality in ICU Patients -- 8.1.4 Machine Learning Algorithms in Mortality Prediction -- 8.1.5 Ethical and Operational Considerations -- 8.2 Materials and Methods -- 8.2.1 Software and Hardware Configuration -- 8.2.2 SVM Algorithm -- 8.2.3 K-Nearest Neighbor Algorithm -- 8.2.4 Statistical Analysis -- 8.3 Results and Discussion -- 8.3.1 Accuracy and Loss Analysis -- 8.3.2 Independent Sample T-Test Analysis -- 8.3.3 Comparison of SVM and KNN -- 8.3.4 Real-World Application and Implications -- 8.3.5 Limitations and Future Scope -- 8.4 Conclusion -- References -- Chapter 9 Asthma Prediction Using ; Vowel Inspiration: A Machine Learning Approach -- 9.1 Introduction -- 9.2 Literature Survey -- 9.3 Motivation and Background -- 9.4 Proposed Method -- 9.4.1 Vowel Inspiration -- 9.4.2 Voice Activity Detection -- 9.4.3 Inspiration Filtering -- 9.4.4 Feature Extraction -- 9.4.4.1 Pause Frequency -- 9.4.4.2 Average Phonation Time -- 9.4.4.3 Vocalization-to-Inhalation Ratio -- 9.4.4.4 Inspiration Sound Energy -- 9.4.5 Classification -- 9.4.6 Praat Parameters -- 9.4.6.1 Jitter -- 9.4.6.2 NHR -- 9.4.6.3 HNR -- 9.5 Discussion -- 9.5.1 Classification for First Method -- 9.5.1.1 Logistic Regression.; 9.5.1.2 Naïve Bayes -- 9.5.1.3 K-Nearest Neighbor -- 9.5.1.4 Support Vector Machine -- 9.5.1.5 Decision Tree -- 9.5.1.6 Random Forest -- 9.5.1.7 Logistic Regression with Random Forest -- 9.5.2 Classification for Second Method -- 9.5.2.1 K-Nearest Neighbor with Classification Report -- 9.5.2.2 Logistic Regression with Discussion on Classification Report -- 9.5.2.3 Decision Tree with Discussion on Classification Report -- 9.5.2.4 Naïve Bayes with Discussion on Classification Report -- 9.6 Results -- 9.7 Conclusion -- References -- Part 4: Medical Data Analysis and Security -- Chapter 10 Improvement of Accuracy in Prevention of Medical Images from Security Threats Using Novel Lasso Regression in Comparison with K-Means Classifier -- 10.1 Introduction -- 10.2 Materials and Methods -- 10.2.1 Dataset Variables -- 10.2.2 Machine Learning Algorithms: Novel Lasso Regression and K-Means Classifiers -- 10.2.2.1 Novel Lasso Regression -- 10.2.2.2 K-Means Classifier -- 10.2.3 Statistical Analysis -- 10.3 Result -- 10.4 Discussion -- 10.5 Conclusion -- References -- Chapter 11 Renal Cancer Detection from Histopathological Images Using Deep Learning -- 11.1 Introduction -- 11.1.1 Motivation -- 11.2 Materials and Methods -- 11.2.1 Dataset Used -- 11.2.2 Models Used -- 11.3 Results and Discussions -- 11.3.1 High Classification Accuracy -- 11.3.2 Strong Performance on Classification Metrics -- 11.3.3 Fuhrman Grade Classification -- 11.4 Conclusion and Future Work -- References -- Chapter 12 A Novel Method to Predicting Tumor in Fallopian Tube Using DenseNet Over Linear Regression with Enhanced Efficiency -- 12.1 Introduction -- 12.2 Materials and Methods -- 12.2.1 DenseNet Algorithm -- 12.2.1.1 Pseudocode for DenseNet -- 12.2.2 Linear Regression -- 12.2.2.1 Pseudocode for Linear Regression -- 12.2.3 Statistical Analysis -- 12.3 Results and Discussion.; 12.3.1 Accuracy and Loss Comparison -- 12.3.2 Statistical Analysis Results -- 12.3.3 Group Statistical Analysis -- 12.3.4 Discussion -- 12.3.5 DenseNet's Performance Advantages -- 12.3.6 Linear Regression's Limitations -- 12.3.7 Significance of Statistical Analysis -- 12.3.8 Limitations and Future Work -- 12.4 Conclusion -- References -- Chapter 13 Protected Medical Images Against Security Threats Using Lasso Regression and K-Means Algorithms -- 13.1 Introduction -- 13.2 Materials and Methods -- 13.3 K-Means Classifier -- 13.4 Procedure for K-Means Classifier -- 13.5 Lasso Regression -- 13.6 Procedure for Lasso Regression -- 13.7 Statistical Analysis -- 13.8 Results -- 13.9 Discussion -- 13.10 Conclusion -- References -- Part 5: Emerging Trends and Technologies -- Chapter 14 Predicting the Factors Influencing Alcoholic Consumption of Teenagers Using an Optimized Random Forest Classifier in Comparison with Logistic Regression -- 14.1 Introduction -- 14.2 Materials and Methods -- 14.3 Random Forest Classifier -- 14.4 Algorithm for Random Forest Classifier -- 14.5 Logistic Regression Classifier -- 14.6 Algorithm for Logistic Regression Classifier -- 14.7 Results -- 14.8 Discussion -- 14.9 Conclusion -- References -- Chapter 15 Harnessing Food Waste Potential: Advancing Protein Sequence Motif Analysis with Novel Cluster Sequence Analyzer Machine Learning Model -- 15.1 Introduction -- ; 15.1.1 Motif Regions -- 15.2 Suffix Tree -- 15.3 Clustering Algorithms in PPI -- 15.4 Classification Agorithms in PPI -- 15.5 CSA and PPI Interaction Results -- 15.6 Conclusion -- Bibliography -- Chapter 16 "Hi-Tech People, Digitized HR- Are We Missing the Humane Link?"-Use of People Analytics as an Effective HRM Tool in a Selected Healthcare Sector -- 16.1 Introduction -- 16.2 Research Background -- 16.3 Literature Review -- 16.4 Research Gaps -- 16.5 Research Methodology.; 16.6 Objectives.
• Sommario/riassunto: The book is essential for anyone exploring the forefront of healthcare innovation, as it offers a thorough exploration of transformative data-driven methodologies that can significantly enhance patient outcomes and clinical efficiency in today's evolving medical landscape.