Applications of Artificial Intelligence in E-Healthcare Systems

Description

Increased use of artificial intelligence (AI) is being deployed in many hospitals and healthcare settings to help improve health care service delivery. Machine learning (ML) and deep learning (DL) tools can help guide physicians with tasks such as diagnosis and detection of diseases and assisting with medical decision making. This edited book outlines novel applications of AI in e-healthcare. It includes various real-time/offline applications and case studies in the field of e-Healthcare, such as image recognition tools for assisting with tuberculosis diagnosis from x-ray data, ML tools for cancer disease prediction, and visualisation techniques for predicting the outbreak and spread of Covid-19. Heterogenous recurrent convolution neural networks for risk prediction in electronic healthcare record datasets are also reviewed. Suitable for an audience of computer scientists and healthcare engineers, the main objective of this book is to demonstrate effective use of AI in healthcare by describing and promoting innovative case studies and finding the scope for improvement across healthcare services. Cover Contents About the editors 1 Introduction to AI in E-healthcare Abstract 1.1 Introduction to artificial intelligence 1.2 Machine Learning 1.3 Deep Learning 1.4 AI timeline in the healthcare sector 1.4.1 AI discovery and the development of drugs 1.4.2 AI personalized healthcare 1.5 AI devices in healthcare 1.5.1 Role of AI in healthcare 1.6 Framework for AI in healthcare using AI devices 1.6.1 Step 1: Analytic integration 1.6.2 Step 2: Choose/build predictive models 1.6.3 Step 3: Optimizing predictive models 1.6.4 Step 4: Retrospective comparison 1.6.5 Step 5: Prescriptive optimization 1.7 Support smart devices and applications 1.8 IoT devices 1.9 Backend facilitator 1.10 Architecture design for an e-healthcare system 1.10.1 UI layers 1.10.2 Information-handling layer 1.10.3 Remote diagnoses and guidelines 1.10.4 Data exchange machine 1.11 Bigdata devices (storage) 1.12 Data mining 1.13 AI assistance for surgical robotics 1.14 AI e-healthcare risk factors 1.14.1 Risk factors in supporting AI e-healthcare 1.14.2 Patient e-record security applications 1.15 Challenges to the use of AI devices in healthcare 1.16 AI devices and managing healthcare data 1.17 AI in e-healthcare applications 1.17.1 Overview of AI applications in e-healthcare References 2 The scope and future outlook of artificial intelligence in healthcare systems Abstract 2.1 Introduction 2.1.1 Importance of AI in healthcare 2.1.2 Life cycle approach to AI 2.2 Leadership and oversight 2.2.1 Standards and regulation 2.3 AI and machine learning are entering a new era 2.4 Exploring the clinical value of AI 2.4.1 Ecosystem 2.5 How is AI transforming the healthcare industry? 2.5.1 Digital consultation 2.5.2 Smart diagnosis 2.5.3 Drug discovery 2.5.4 Robotic assistance 2.5.5 Virtual follow-up system 2.6 Potential of AI in various fields of healthcare systems 2.6.1 Comparison of various fields of healthcare using AI technology 2.6.2 Good at-risk phase 2.6.3 Acute care phase 2.6.4 Chronic care process 2.7 Analyzing the priority areas in healthcare systems 2.8 Challenges associated with the implementation of an AI-driven healthcare system 2.8.1 Regulatory challenges 2.8.2 Standardization challenges 2.8.3 Ethical and social challenges 2.8.4 Challenges for a transforming discipline 2.9 Vision and future potential of AI in healthcare 2.10 Conclusion References 3 Class dependency-based learning using Bi-LSTM coupled with the transfer learning of VGG16 for the diagnosis of tuberculosis from chest X-rays Abstract 3.1 Introduction 3.2 Related works 3.3 Methods 3.3.1 Data preprocessing 3.3.2 Proposed methodology 3.4 Results and discussion 3.4.1 Databases 3.4.2 Performance metrics 3.4.3 Results reported 3.4.4 Comparison 3.5 Conclusion References 4 Drug discovery clinical trial exploratory process and bioactivity analysis optimizer using deep convolutional neural network for E-prosperity Abstract 4.1 Introduction 4.2 Related works 4.3 Neural network 4.3.1 Artificial neuron 4.3.2 Spiral basis function neural network 4.3.3 Multilayer perceptron 4.3.4 Longand short-term memory 4.3.5 Modular neural network 4.3.6 Sequence-to-sequence models 4.4 Convolutional neural network 4.4.1 Deep convolutional neural network 4.4.2 Convolutional layer 4.5 Simulation and analysis 4.6 Conclusion References 5 An automated NLP methodology to predict ICU mortality CLINICAL dataset using multiclass grouping with LSTM RNN approach Abstract 5.1 Introduction to natural language processing 5.1.1 Text representation 5.1.2 Medical field impacted using NLP 5.1.3 NLP – a driven resource for healthcare to improve outcomes 5.1.4 LSTM–RNN a novel approach in prediction 5.1.5 RNN 5.2 Data collection 5.2.1 Multiclass feature analysis 5.3 Proposed system 5.4 Results and discussion 5.5 Conclusion References 6 Applying machine learning techniques to build a hybrid machine learning model for cancer prediction Abstract 6.1 Introduction 6.2 Literature review 6.3 Dataset description 6.4 System methodology 6.4.1 Dataset analysis 6.4.2 Splitting of the dataset and preprocessing 6.4.3 Training and testing the dataset using HMLM 6.4.4 Evaluation metrics 6.4.5 Output interpretation 6.4.6 Result analysis 6.5 Conclusion 6.6 Future work References 7 AI in healthcare: challenges and opportunities Abstract 7.1 Introduction 7.1.1 Progressive way of life: Healthcare 4.0 7.2 Development of Healthcare 4.0 7.2.1 Evolution of Industry 4.0 7.2.2 Evolution of Healthcare 4.0 7.3 Development of AI in the healthcare sector 7.3.1 Areas in which AI is used across healthcare 7.4 AI challenges in healthcare 7.5 AI developments in healthcare 7.6 AI opportunities in healthcare 7.7 Discussion and conclusion References 8 Impression of artificial intelligence in e-healthcare medical applications Abstract 8.1 Introduction 8.2 e-Healthcare 8.3 Application of e-Healthcare 8.3.1 Application of telemedicine 8.3.2 Telehealth (upcoming years) 8.4 Artificial intelligence 8.5 Significant advancements of technology 8.6 Artificial intelligence in medical sector 8.6.1 Artificial intelligence and robotics are transforming healthcare 8.7 Pros of artificial intelligence in healthcare 8.8 Cons of artificial intelligence in healthcare 8.9 Discussion and conclusion References 9 Heterogeneous recurrent convolution neural network for risk prediction in the EHR dataset Abstract 9.1 Introduction 9.2 Related work 9.3 Methodology 9.3.1 Gathering of the dataset 9.3.2 Data cleaning 9.3.3 Attribute/feature selection through MLSCO 9.3.4 Prediction of risk using HRCC 9.4 Result and examination 9.4.1 Examination parameters 9.4.2 Experimental examination 9.5 Conclusion References 10 A narrative review and impacts on trust for data in the healthcare industry using artificial intelligence Abstract 10.1 Introduction 10.2 Hypotheses development 10.2.1 Roles for healthcare artificial intelligence 10.3 The inconvenient truth about AI in healthcare 10.4 Role of cloud storage with AI in healthcare 10.5 Finally grasping the enormous potential of AI in healthcare 10.5.1 Prediction 10.5.2 Diagnosis 10.5.3 Personalized treatment options and behavioral interventions 10.5.4 Drug discovery 10.6 Several key challenges to the integration of healthcare and AI 10.6.1 Understanding the gap 10.6.2 Fragmented data 10.6.3 Appropriate security 10.6.4 Data governance 10.6.5 Software 10.7 Data exploration in healthcare for AI 10.7.1 Data cleansing 10.7.2 Data that are inconsistent or duplicate 10.7.3 Exploring anomalies in the data 10.8 Starting the cleaning up of typographical errors, clearing the values, and perfecting the formatting 10.8.1 Aggregation 10.8.2 Decomposition 10.8.3 Encoding 10.9 Artificial intelligence (AI) in healthcare using an open science approach 10.9.1 What is the difference between open data and open research? 10.10 Conclusion References 11 Analysis of COVID-19 outbreak using data visualization techniques: a review Abstract 11.1 Introduction 11.2 Methodology 11.2.1 Objective 11.2.2 Method 11.2.3 About dataset 11.3 Datewise analysis 11.3.1 Analysis of recovery rate (RR) and mortality rate (MR) throughout the world 11.4 Growth factor 11.5 Countrywise analysis 11.5.1 Journey of different countries in COVID-19 11.5.2 Proportion of each nation in CC, RC, and DC 11.6 Clustering of countries 11.6.1 Weekly data analysis for India 11.6.2 Datewise/daily data analysis for India with comparison 11.7 Machine learning models for prediction 11.7.1 Linear regression model prediction for confirmed cases 11.7.2 Polynomial regression for prediction of CC 11.7.3 SVM model regression for prediction of CC 11.7.4 Holt’s linear model 11.7.5 Holt’s winter model for everyday time series 11.7.6 AR model (using AUTO ARIMA) 11.7.7 MA model (using AUTO ARIMA) 11.7.8 ARIMA model (using AUTO ARIMA) 11.7.9 SARIMA model (using AUTO ARIMA) 11.7.10 Facebook’s Prophet model for forecasting 11.8 Forecasting results and summarizations using various models 11.8.1 Time-Series forecasting for DC 11.9 Conclusion References 12 Artificial intelligence-based electronic health records for healthcare Abstract 12.1 Introduction 12.1.1 Overview of artificial intelligence 12.1.2 E-healthcare and electronic health records 12.2 AI in E-healthcare structure 12.2.1 Use of AI in E-healthcare structure 12.2.2 Architecture of data retrieval and data processing in electronic health records (Figure 12.3) 12.3 Smart devices pre-owned in electronic health documentations 12.3.1 Health documentations construct use of wearable devices 12.3.2 Monitoring forbearing’s construct use of smart contract 12.4 Care and privacy of healthcare data 12.4.1 Care challenges 12.4.2 Care and protection highlights of current EHR frameworks 12.4.3 Data innovation care episodes in medical care position 12.5 Conclusion References 13 Automatic structuring on Chinese ultrasound report of Covid-19 diseases via natural language processing Abstract 13.1 Introduction 13.2 Natural language processing 13.2.1 NLP techniques 13.2.2 Sentiment analysis 13.2.3 Language translation 13.2.4 Text extraction 13.2.5 Chatbox 13.3 Machine learning for NLP 13.3.1 Unsupervised machine learning 13.3.2 Concept Matrix 13.3.3 Syntax Matrix 13.3.4 Syntax information 13.3.5 Hybrid Machine Learning Systems for NLP 13.4 Ultrasound devices 13.5 Results and analysis 13.6 Conclusion References Index Back Cover