Tracking and Preventing Diseases with Artificial Intelligence (Intelligent Systems Reference Library, 206)

Description

This book presents an overview of how machine learning and data mining techniques are used for tracking and preventing diseases. It covers several aspects such as stress level identification of a person from his/her speech, automatic diagnosis of disease from X-ray images, intelligent diagnosis of Glaucoma from clinical eye examination data, prediction of protein-coding genes from big genome data, disease detection through microscopic analysis of blood cells, information retrieval from electronic medical record using named entity recognition approaches, and prediction of drug-target interactions. The book is suitable for computer scientists having a bachelor degree in computer science. The book is an ideal resource as a reference book for teaching a graduate course on AI for Medicine or AI for Health care. Researchers working in the multidisciplinary areas use this book to discover the current developments. Besides its use in academia, this book provides enough details about the state-of-the-art algorithms addressing various biomedical domains, so that it could be used by industry practitioners who want to implement AI techniques to analyze the diseases. Medical institutions use this book as reference material and give tutorials to medical experts on how the advanced AI and ML techniques contribute to the diagnosis and prediction of the diseases. Preface Contents Contributors Abbreviations 1 Stress Identification from Speech Using Clustering Techniques 1.1 Introduction 1.2 Related Work 1.3 Stress Identification System Setup 1.3.1 Signal Aquisition and Pre-processings 1.3.2 Speech Feature Extraction 1.3.3 Support Vector Machine (SVM) 1.4 Implementation and Results 1.5 Conclusion References 2 Comparative Study and Detection of COVID-19 and Related Viral Pneumonia Using Fine-Tuned Deep Transfer Learning 2.1 Introduction 2.2 Literature Review 2.2.1 The COVID-19 Coronavirus 2.2.2 COVID-19 Clinical Features 2.2.3 Related Works on the Detection of COVID-19 2.3 Methodology 2.3.1 Dataset Description 2.3.2 The VGGNet Architecture 2.4 Experimentation and Results 2.4.1 Evaluation of Results 2.5 Conclusion References 3 Predicting Glaucoma Diagnosis Using AI 3.1 AI in Medical Diagnosis 3.2 AI in Ophthalmology Diagnosis 3.3 Artificial Intelligent Techniques in Glaucoma Diagnosis 3.4 Ensemble Method for Classification 3.5 Ensemble FGLAUC-99 3.6 Results and Discussions 3.7 Conclusion References 4 Diagnosis and Analysis of Tuberculosis Disease Using Simple Neural Network and Deep Learning Approach for Chest X-Ray Images 4.1 Introduction 4.2 Related Work 4.3 Proposed Methodology of Neural Network (NN)-Based Approach of TB Disease Classification 4.3.1 Image Preprocessing 4.3.2 Image Segmentation 4.4 Feature Extraction 4.4.1 Classification 4.5 Result Analysis of Proposed NN Based TB Disease Classification 4.6 Deep Learning Approach of TB Disease Classification 4.6.1 Data Collection 4.6.2 Network Architecture 4.6.3 Experiments and Results Discussion 4.6.4 Experimental Setup and Evaluation 4.7 Conclusion References 5 Adaptive Machine Learning Algorithm and Analytics of Big Genomic Data for Gene Prediction 5.1 Introduction 5.2 Background: Common Machine Learning Algorithms and Public Referenced Genome Databases for Bioinformatics Tasks 5.3 Our Naive Bayes Algorithm 5.3.1 Apache Spark Framework 5.3.2 Data Preprocessing and Munging 5.3.3 Our Adaptive NBML Algorithm 5.4 Evaluation Results and Discussion 5.5 Conclusions References 6 Microscopic Analysis of Blood Cells for Disease Detection: A Review 6.1 Introduction 6.1.1 Background 6.2 Literature Review 6.2.1 Collection and Exclusion of Articles for Review 6.2.2 Generalized Methodology of Disease Detection 6.2.3 State-of-the-Art Methods for Different Stages of Microscopic Analysis for Disease Detection 6.3 Research Gaps 6.4 Conclusion 6.5 Future Scope References 7 Investigating Clinical Named Entity Recognition Approaches for Information Extraction from EMR 7.1 Introduction 7.2 Clinical Named Entity Recognition 7.2.1 Rule-Based Approach 7.2.2 Machine Learning-Based Approaches 7.2.3 Hybrid Approaches 7.3 Experimental Evaluation 7.3.1 spaCy NER Model 7.3.2 Conditional Random Field NER Model 7.3.3 BLSTM NER 7.3.4 BLSTM with CRF 7.4 Result Discussion 7.5 Conclusion and Future Scope References 8 Application of Fuzzy Convolutional Neural Network for Disease Diagnosis: A Case of Covid-19 Diagnosis Through CT Scanned Lung Images 8.1 Introduction 8.2 Background Technologies 8.2.1 Fuzzy Logic 8.2.2 Convolutional Neural Network 8.2.3 Adding Fuzziness in the Neural Network 8.3 Related Work 8.4 Generic Architecture of the Disease Diagnosis System Based on Fuzzy Convolutional Neural Network 8.5 Detailed Method, Experiment, and Results 8.6 Conclusion References 9 Computer Aided Skin Disease (CASD) Classification Using Machine Learning Techniques for iOS Platform 9.1 Introduction 9.1.1 Background on Existing System 9.2 System Analysis 9.2.1 Literature Survey on Existing System 9.2.2 Proposed CASD System 9.2.3 Requirements for CASD System 9.3 System Design 9.3.1 Create ML Model 9.3.2 Core ML Model 9.3.3 Apple iOS Architecture for CASD Machine Learning System 9.3.4 Firebase Architecture for CASD Database System 9.3.5 Dataset Images for CASD System 9.3.6 Database Structure of CASD System 9.4 System Implementation 9.4.1 Four View Controllers of CASD System 9.4.2 Skin Lesion Classifier Model of CASD System 9.4.3 Steps of Model Creation 9.4.4 Lıve Testing Output Using the Developed CASD System in iOS Platform 9.5 Conclusion and Future Scope References 10 A Comprehensive Study of Mammogram Classification Techniques 10.1 Introduction 10.2 Mammography and Mammogram Datasets 10.3 Related Works in Classification of Lesions Using Data Mining Techniques 10.4 Techniques for Classifying Mammogram Images 10.4.1 Function-Based Methods 10.4.2 Probability-Based Methods 10.4.3 Similarity-Based Methods 10.4.4 Rule-Based Methods 10.5 Challenges in Classifying Mammogram Images 10.5.1 Dataset Related Challenges 10.5.2 Classification Techniques Related Challenges 10.6 Techniques to Improve Performance of Machine Learning Models 10.7 Towards Deep Learning 10.8 Conclusion References 11 A Comparative Discussion of Similarity Based Techniques and Feature Based Techniques for Interaction Prediction of Drugs and Targets 11.1 Introduction 11.2 Similarity Based Techniques 11.2.1 Neighborhood Models 11.2.2 Bipartite Local Models 11.2.3 Network Diffusion Models 11.2.4 Matrix Factorization Models 11.3 Feature Based Techniques 11.3.1 SVM Based Models 11.3.2 Ensemble Based Models 11.3.3 Miscellaneous Models 11.4 Comparison of Similarity Based and Feature Based Techniques 11.5 Conclusion References