HEALTHCARE TECHNOLOGIES SERIES 43 Evolving Predictive Analytics in Healthcare IETBookSeriesone–HealthTechnologies BookSeriesEditor:ProfessorJoelJ.P.C.Rodrigues,CollegeofComputerScienceand Technology,ChinaUniversityofPetroleum(EastChina),Qingdao,China;SenacFacultyof Ceara´,Fortaleza-CE,BrazilandInstitutodeTelecomunicac¸o˜es,Portugal BookSeriesAdvisor:ProfessorPranjalChandra,SchoolofBiochemicalEngineering,Indian InstituteofTechnology(BHU),Varanasi,India Whilethedemographicshiftsinpopulationsdisplaysignificantsocio-economicchallenges,they triggeropportunitiesforinnovationsine-Health,m-Health,precisionandpersonalized medicine,robotics,sensing,theInternetofthings,cloudcomputing,bigdata,softwaredefined networks,andnetworkfunctionvirtualization.Theirintegrationishoweverassociatedwith manytechnological,ethical,legal,social,andsecurityissues.Thisbookseriesaimsto disseminaterecentadvancesfore-healthtechnologiestoimprovehealthcareandpeople’s wellbeing. Couldyoubeournextauthor? Topicsconsideredincludeintelligente-Healthsystems,electronichealthrecords,ICT-enabled personalhealthsystems,mobileandcloudcomputingfore-Health,healthmonitoring, precisionandpersonalizedhealth,roboticsfore-Health,securityandprivacyine-Health, ambientassistedliving,telemedicine,bigdataandIoTfore-Health,andmore. Proposalsforcoherentlyintegratedinternationalmulti-authorededitedorco-authored handbooksandresearchmonographswillbeconsideredforthisbookseries.Eachproposalwill bereviewedbythebookSeriesEditorwithadditionalexternalreviewsfromindependent reviewers. Todownloadourproposalformorfindoutmoreinformationaboutpublishingwithus,please visithttps://www.theiet.org/publishing/publishing-with-iet-books/. PleaseemailyourcompletedbookproposalfortheIETBookSeriesone-HealthTechnologies to:[email protected][email protected]. Evolving Predictive Analytics in Healthcare New AI techniques for real-time interventions Edited by Abhishek Kumar, Ashutosh Kumar Dubey, Surbhi Bhatia, Swarn Avinash Kumar and Dac-Nhuong Le The Institution of Engineering andTechnology PublishedbyTheInstitutionofEngineeringandTechnology,London,UnitedKingdom TheInstitutionofEngineeringandTechnologyisregisteredasaCharityinEngland& Wales(no.211014)andScotland(no.SC038698). †TheInstitutionofEngineeringandTechnology2022 Firstpublished2022 ThispublicationiscopyrightundertheBerneConventionandtheUniversalCopyright Convention.Allrightsreserved.Apartfromanyfairdealingforthepurposesofresearch orprivatestudy,orcriticismorreview,aspermittedundertheCopyright,Designsand PatentsAct1988,thispublicationmaybereproduced,storedortransmitted,inany formorbyanymeans,onlywiththepriorpermissioninwritingofthepublishers,orin thecaseofreprographicreproductioninaccordancewiththetermsoflicencesissued bytheCopyrightLicensingAgency.Enquiriesconcerningreproductionoutsidethose termsshouldbesenttothepublisherattheundermentionedaddress: TheInstitutionofEngineeringandTechnology FuturesPlace KingsWay,Stevenage Hertfordshire,SG12UA,UnitedKingdom www.theiet.org Whiletheauthorsandpublisherbelievethattheinformationandguidancegiveninthis workarecorrect,allpartiesmustrelyupontheirownskillandjudgementwhenmaking useofthem.Neithertheauthorsnorpublisherassumesanyliabilitytoanyoneforany lossordamagecausedbyanyerrororomissioninthework,whethersuchanerroror omissionistheresultofnegligenceoranyothercause.Anyandallsuchliabilityis disclaimed. Themoralrightsoftheauthortobeidentifiedastheauthorofthisworkhavebeen assertedbyhiminaccordancewiththeCopyright,DesignsandPatentsAct1988. BritishLibraryCataloguinginPublicationData AcataloguerecordforthisproductisavailablefromtheBritishLibrary ISBN978-1-83953-511-6(hardback) ISBN978-1-83953-512-3(PDF) TypesetinIndiabyMPSLimited PrintedintheUKbyCPIGroup(UK)Ltd,Croydon Contents Abouttheeditors xv 1 COVID-19detectioninX-ray images usingcustomized CNNmodel 1 Deepshikha Jain, Venkatesh GauriShankar, Bali Devi and Surbhi Bhatia 1.1 Introduction 2 1.2 Related work 3 1.2.1 Key contributions and proposed work 5 1.3 Materials and methods 6 1.3.1 Feature extractionand selection 9 1.4 Results and discussion 11 1.5 Conclusion and future scope 15 References 17 2 Introducing deep learning in medical diagnosis 21 N. Padmapriya, N. Kumaratharan,M. Pavithra, R. Rajmohan, P. Kanimozhi and D.J. Samuel 2.1 Introduction 22 2.2 Literature survey 23 2.3 Overview of DLalgorithms 24 2.3.1 Convolutional neural network 25 2.3.2 Recurrent neural network 25 2.3.3 Long short-term memory 26 2.3.4 Restricted Boltzmann machine 27 2.3.5 Deep belief networks 28 2.4 ProposedDL framework for neuro disease diagnosis 28 2.4.1 FAST-RCNN 29 2.4.2 Ten fully connected layer 31 2.5 Preprocessingof dataset 32 2.6 Implementation and results 34 2.7 Conclusion 36 References 36 3 Intelligent approach for network intrusiondetection system(NIDS) utilizing machine learning (ML) 41 ShubhamSharma,Pronika Chawla, Naincy Chamoli, DishaPahuja andMaanya Mocha 3.1 Introduction 42 vi Evolvingpredictive analytics in healthcare 3.1.1 DoSand DDoSattacks 43 3.1.2 Man-in-the-middle (MitM) attack 44 3.1.3 Phishing and spear-phishing attacks 44 3.1.4 Passwordattack 44 3.1.5 Eavesdropping attack 45 3.1.6 Malware attack 45 3.2 Related work 45 3.3 Cloud computing 47 3.3.1 Machine learning 47 3.3.2 Exploratory data analysis 48 3.4 Results 50 References 54 4 Classification methodologies inhealthcare 55 Adri Jovin John Joseph, Ferdin Joe John Joseph, Oswalt Manoj StanislausandDebashreet Das 4.1 Introduction 56 4.2 Classification algorithms 57 4.2.1 Statistical data 57 4.2.2 Discriminant analysis 58 4.2.3 Decision tree 58 4.2.4 K-nearest neighbor (KNN) 59 4.2.5 Logistic regression (LR) 59 4.2.6 Bayesian classifier 59 4.2.7 Support vector machine (SVM) 60 4.3 Parameter identification 60 4.3.1 Feature selection for classification 63 4.4 Real-time applications 66 4.4.1 Classification of patients based on medical record 66 4.4.2 Predictive analytics and diagnostic analytics based on medical records 67 4.4.3 Classification of diseases based onmedical imaging 67 4.4.4 Mixed reality-based automation to help aid aging society 68 4.4.5 Tiny ML-based classificationsystems for medical gadgets 69 4.4.6 Classification systems for insurance claim management 69 4.4.7 Case study: Inspectra from Perceptra 70 4.4.8 Deep learning forbeginners 71 References 72 5 Introducingdeep learning inmedical domain 75 Prithi Samuel,AnushaBamini, P. Nancy, S.Oswalt Manoj andMaruti Perumal 5.1 Introduction 76 5.1.1 DLin a nutshell 77 Contents vii 5.1.2 History of DLin the medical field 77 5.1.3 Benefits of DL inthe medical domain 79 5.1.4 Challenges and obstacles of DLin the medical domain 80 5.1.5 Opportunities of DLin the medical field 81 5.2 DLapplicationsin the medical domain 81 5.2.1 Drugdiscovery and medicine precision 81 5.2.2 Detection of diseases 82 5.2.3 Diagnosing patients 83 5.2.4 Healthcare administration 83 5.3 DLfor medical image analysis 84 5.3.1 Medical image detection 85 5.3.2 Medical image recognition 86 5.3.3 Medical image segmentation 87 5.3.4 Medical image registration 88 5.3.5 Disease diagnosis and quantification 89 5.4 Conclusion 89 References 90 6 Deep-stackedautoencoder for medical image classification 93 J. Anitha, S. Akila Agnes, S.Immanuel Alex Pandian and Malin Bruntha 6.1 Introduction 93 6.2 Autoencoder 96 6.2.1 Stacked AE 97 6.2.2 Sparse AE 97 6.2.3 Convolutional AE 100 6.2.4 Deep AE 101 6.3 Proposedmethod 101 6.3.1 Representationlearning usingAE 102 6.3.2 Softmax layer 102 6.3.3 Support vector machine 103 6.3.4 K-nearest neighbor 103 6.3.5 Fine-tuning 104 6.3.6 Sparsity and regularization in AE 104 6.4 Results and discussions 104 6.4.1 Datasets 104 6.4.2 Evaluation metrics 105 6.4.3 Analysis of the simple AE 106 6.4.4 Effect of sparsity in AE 109 6.4.5 Effect of squeezing bottleneck in AE 110 6.4.6 Performance of deep stacked encoder 111 6.5 Conclusion 113 References 113 viii Evolving predictive analytics in healthcare 7 Comparisonof machine learning anddeep learningalgorithmsfor prediction of coronary heart disease 117 Sajeev RamArumugam,E. Anna Devi, T.Abimala andOswalt Manoj 7.1 Introduction 118 7.1.1 Coronary heart disease (CHD) 118 7.1.2 ML and DL techniques 118 7.2 Related works 119 7.3 Materials and methods 121 7.3.1 Data preparation 121 7.3.2 Fixing the missing data issue 122 7.3.3 Data analysis 124 7.3.4 Feature selection 126 7.3.5 Balancing the dataset 127 7.3.6 Feature scaling 128 7.3.7 Methodology 129 7.3.8 Performance metrics 134 7.4 Results and discussion 135 7.5 Conclusion 140 References 140 8 Revolutionintechnology-enabled healthcare: Internetof Things 143 S.Sangeetha, DeepaShanmugham,S.Balamuruganand K. Maharaja 8.1 IoT and healthcare informationsystems 144 8.2 Remote health monitoring and telehealth 145 8.2.1 PharmaIoT 146 8.2.2 Mobile applicationsfor healthcare 147 8.2.3 Big data inhealthcare 147 8.2.4 Challenges in MIoT 148 8.3 Wearables and medical devices 148 8.3.1 Activity trackers 148 8.3.2 Vital sign measurement 149 8.3.3 Smart jacket 149 8.3.4 Wire-based wearable devices 150 8.4 IoT inchronic diseases 150 8.5 IoT inemergency medical care 153 8.6 IoT and pregnancy care 154 8.7 IoT ineyecare 155 8.7.1 Visual acuity tester 155 8.7.2 Mobile imaging 156 8.8 Benefits of IoT in the healthcare system 157 8.9 Challenges with IoT in healthcare 158 References 159 Contents ix 9 Smart healthcare monitoring framework usingIoTwithbigdata analytics 163 S. Usharani,P. Manju Bala, T.Ananth Kumar,R. Rajmohan, A. Balachandarand A.S. Adeola 9.1 Introduction 164 9.2 Related work 165 9.3 Overview of IoT and big data 165 9.4 Data sources for healthcare 166 9.4.1 Electronic health records (EHR)data 167 9.4.2 Medical images data 167 9.4.3 Experimental data mining 167 9.4.4 Interactive data 168 9.4.5 Genomic data 168 9.5 Big data’sevolution in IoT 168 9.6 Recent trends in big data analytics and IoT 169 9.6.1 Specialized medical envisioning 169 9.6.2 Telehealth 169 9.6.3 Portable gadgets and the IoT 170 9.6.4 Biological IoT 170 9.7 Big data challenges in healthcare 171 9.7.1 Challenges relating to budgetary and economic considerations 171 9.7.2 Challenges relating to expertise 171 9.8 IoT challenges in healthcare 172 9.8.1 IoT and portable gadgets 172 9.8.2 Modesof communication in wearable devices 173 9.8.3 Smart healthcare monitoring frameworks 174 9.8.4 SHMSprinciples in the IoT 175 9.8.5 Implementation of SHMSwith big data analytics 176 9.8.6 Proposedmodel 176 9.8.7 Case study 177 9.8.8 Performance evaluation of data analysis 177 9.9 Conclusion 180 References 181 10 Experimental analysis andinvestigation of dementia detection framework usingEHR-basedvariant LSTM model 185 P. Manju Bala, S. Usharani,R. Rajmohan, T.Ananth Kumar, A. Balachandarand S.ArunmozhiSelvi 10.1 Introduction 186 10.2 Related work 187 10.3 Materialsand methods 188 10.3.1 EHR datasets 188 10.3.2 ML models 189