Application of AI and IoT in Clinical Medicine: Summary and Challenges

Abstract

The application of artificial intelligence (AI) technology in the medical field has experienced a long history of development. In turn, some long-standing points and challenges in the medical field have also prompted diverse research teams to continue to explore AI in depth. With the development of advanced technologies such as the Internet of Things (IoT), cloud computing, big data, and 5G mobile networks, AI technology has been more widely adopted in the medical field. In addition, the in-depth integration of AI and IoT technology enables the gradual improvement of medical diagnosis and treatment capabilities so as to provide services to the public in a more effective way. In this work, we examine the technical basis of IoT, cloud computing, big data analysis and machine learning involved in clinical medicine, combined with concepts of specific algorithms such as activity recognition, behavior recognition, anomaly detection, assistant decision-making system, to describe the scenario-based applications of remote diagnosis and treatment collaboration, neonatal intensive care unit, cardiology intensive care unit, emergency first aid, venous thromboembolism, monitoring nursing, image-assisted diagnosis, etc. We also systematically summarize the application of AI and IoT in clinical medicine, analyze the main challenges thereof, and comment on the trends and future developments in this field.

Keywords

artificial intelligence / Internet of Things / big data / cloud computing / clinical medicine

References

[1] GHWA/WHO. A Universal Truth: No Health Without a Workforce

[2] WHO. State of the World’s Nursing Report 2020

[3] KrukME, GageAD, JosephNT, et al.. Mortality due to low-quality health systems in the universal health coverage era: A systematic analysis of amenable deaths in 137 countries. Lancet, 2018, 392(10160): 2146-2147

[4] World Population Prospects 2019: Highlights[B]. ONU. United Nations. 2019

[5] Healthy Aging Team. The Top 10 Most Common Chronic Conditions in Older Adults.National council on ageing. Available from: https://dailycaring.com/prevent-and-manage-the-10-most-common-chronic-diseases-in-older-adults/

[6] JaulE, BarronJ. Age-Related Diseases and Clinical and Public Health Implications for the 85 Years Old and Over Population. Front Public Health, 2017, 5: 335-335

[7] van den BusscheH, KollerD, KolonkoT, et al.. Which chronic diseases and disease combinations are specific to multimorbidity in the elderly? Results of a claims data based cross-sectional study in Germany. BMC Public Health, 2011, 11: 101

[8] MofizulIM, ValderasJM, LaurannY, et al.. Multimorbidity and Comorbidity of Chronic Diseases among the Senior Australians: Prevalence and Patterns. Plos One, 2014, 9(1): e83783

[9] ZhaoC, LipingW, ZhuQ, et al.. Prevalence and correlates of chronic diseases in an elderly population: A community-based survey in Haikou. Plos One, 2018, 13(6): e0199006

[10] Burroughs A. What Is a Tele-ICU and How Does It Work? Available from https://healthtechmagazine.net/article/2020/09/what-tele-icu-and-how-does-it-work

[11] FullerT, FoxB, LakeD, et al.. Improving real-time vital signs documentation. Nurs Manage, 2018, 49(1): 28-33

[12] Martine L. Measuring patient and clinical effectiveness. Microsoft Industry Blogs - United Kingdom Available from: https://cloudblogs.microsoft.com/industry-blog/en-gb/health/2020/07/03/measuring-patient-and-clinical-effectiveness/

[13] PrajapatiB, ParikhS, PatelJAn Intelligent Real Time IoT Based System (IRTBS) for Monitoring ICU Patien, 2017, Cham, Springer

[14] HkaF, SwkB, EpC, et al.. The role of fifth-generation mobile technology in prehospital emergency care: An opportunity to support paramedics. Health Policy Technol, 2020, 9(1): 109-114

[15] TangX. The role of artificial intelligence in medical imaging research. BJR Open, 2019, 2(1): 20190031

[16] ChamberlinJ, KocherMR, WaltzJ, et al.. Automated detection of lung nodules and coronary artery calcium using artificial intelligence on low-dose CT scans for lung cancer screening: accuracy and prognostic value. BMC Med, 2021, 19(1): 55

[17] WangXN, DaiL, LiST, et al.. Automatic Grading System for Diabetic Retinopathy Diagnosis Using Deep Learning Artificial Intelligence Software. Curr Eye Res, 2020, 45: 1550-1555

[18] DeyD, SlomkaPJ, LeesonP, et al.. Artificial Intelligence in Cardiovascular Imaging. J Am Coll Cardiol, 2019, 73(11): 1317-1335

[19] Alkhatib H, Faraboschi P, Frachtenberg E, et al. IEEE CS 2022 Report. IEEE Computer Society, 2014:25–27

[20] KosmatosEA, TselikasND, BoucouvalasAC. Integrating RFIDs and Smart Objects into a Unified-Internet of Things Architecture. Adv Internet Things, 2011, 1(1): 5-12

[21] MadakamS, RamaswamyR, TripathiS. Internet of Things (IoT): A Literature Review. J Comp Commun, 2015, 3(3): 164-173

[22] GubbiJ, BuyyaR, MarusicS, et al.. Internet of Things (IoT): A Vision, Architectural Elements, and Future Directions. Future Gener Comp Syst, 2013, 29(7): 1645-1660

[23] HaiderF. Cellular architecture and key technologies for 5G wireless communication networks. J Chongqing Univ Posts Telecommun, 2014, 52(2): 122-130

[24] JoyiaGJ, LiaqatRM, FarooqA, et al.. Internet of medical things (IOMT): Applications, benefits and future challenges in healthcare domain. J Commun, 2017, 12(4): 240-247

[25] HingmireM, BagjilewaleM, DakholeM. What is Cloud Computing. Springer Verlag Ny, 2017, 17(1): 3-20

[26] SultanN. Making use of cloud computing for healthcare provision: Opportunities and challenges. Int J Inform Manage, 2014, 34(2): 177-184

[27] WangL, von LaszewskiG, YoungeA, et al.. Cloud Computing: a Perspective Study. New Generat Comput, 2010, 28(2): 137-146

[28] AhujaSP, SindhuM, JesusZ. A Survey of the State of Cloud Computing in Healthcare. Network Commun Technol, 2012, 1(2): 12-19

[29] MarjaniM, NasaruddinF, GaniA, et al.. Big IoT Data Analytics: Architecture, Opportunities, and Open Research Challenges. IEEE Access, 2017, 5(99): 5247-5261

[30] KufrinR. Decision trees on parallel processors. Machine Intelligence Pattern Recognition, 1997, 20: 279-306

[31] GondyLA, ThomasC, BayesN. Programs for machine learning. Advances in Neural Inform Proc Syst, 1993, 79(2): 937-944

[32] JudithE, JamesM. Artificial neural networks. Cancer, 2001, 91(S8): 1615-1635

[33] KrallingerM, LeitnerF, VazquezM, et al.. Text Mining. Compr Biomed Phys, 2014, 6: 51-66 10 Supplement

[34] Quan XX, Yang J F, Luo Z. Models in digital business and economic forecasting based on big data IoT data visualization technology. Pers Ubiquit Comput, 2021 (https://doi.org/10.1007/s00779-021-01603-7)

[35] Hua X, Aldrich MC, Chen Q, et al. Validating drug repurposing signals using electronic health records: a case study of metformin associated with reduced cancer mortality. J Am Med Inform Assoc, 2015(1):179–191

[36] DashS, ShakyawarSK, SharmaM, et al.. Big data in healthcare: management, analysis and future prospects. J Big Data, 2019, 6(1): 54

[37] Bhardwaj R, Nambiar AR, Dutta D. A Study of Machine Learning in Healthcare. 2017 IEEE 41st Annual Computer Software and Applications Conference (COMPSAC). July 4–7, 2017, Turin, Italy

[38] AbramsonN, BravermanDJ, SebestyenGS. Pattern Recognition and Machine Learning. Public Am Statist Assoc, 2006, 103(4): 886-887

[39] Avci A, Bosch S, Marin-Perianu M, et al. Activity Recognition Using Inertial Sensing for Healthcare, Wellbeing and Sports Applications: A Survey. ARCS’10 - 23th International Conference on Architecture of Computing Systens 2010, Workshop Proceedings, February 22–23, 2010, Hannover, Germany. VDE, 2010

[40] Ijjina EP, Mohan CK. Hybrid deep neural network model for human action recognition. Appl Soft Comput, 2016:936–952

[41] GoodfellowI, BengioY, CourvilleADeep learning, 2016, Cambridge, MIT Press: 367-415

[42] LiuX, YangXDMulti-stream with deep convolutional neural networks for human action recognition in videos, 2018, Cham, Springer International Publishing: 251-262

[43] WangLL, GeLZ, LiRF, et al.. Three-stream CNNs for action recognition. Pattern Recog Lett, 2017, 92: 33-40

[44] TranD, BourdevL, FergusR, et al.Learning Spatiotemporal Features with 3D Convolutional Networks, 2015, Santiago, Chile, IEEE: 4489-4497

[45] QiuZ, YaoT, MeiTLearning Spatio-Temporal Representation with Pseudo-3D Residual Networks, 2017, Venice, IEEE: 5533-5541

[46] ZhouY, SunX, ZhaZJ, et al.MiCT: Mixed 3D/2D Convolutional Tube for Human Action Recognition, 2018, Salt Lake City, UT, IEEE: 449-458

[47] NgYH, HausknechtM, VijayanarasimhanS, et al.Beyond short snippets: Deep networks for video classification, 2015, Boston, MA, USA, IEEE: 4694-4702

[48] DuW, WangY, YuQRPAN: An End-to-End Recurrent Pose-Attention Network for Action Recognition in Videos, 2017, Venice, IEEE: 3725-3734

[49] RenZH, XuHY, FengSL, et al.. Sequence labeling Chinese word segmentation method based on LSTM networks. Comput Appl Res, 2017, 34(5): 1321-1324

[50] WsyA, SyhB. A process-mining framework for the detection of healthcare fraud and abuse. Exp Syst Appl, 2006, 31(1): 56-68

[51] AlabdulkarimA, Al-RodhaanM, Al-DhelaanTA. A Privacy-Preserving Algorithm for Clinical Decision-Support Systems Using Random Forest. Comput Mater Contin, 2019, 58(3): 585-601

[52] Tama BA, Lim S. A Comparative Performance Evaluation of Classification Algorithms for Clinical Decision Support Systems. Mathematics, 2020(8):1814

[53] PatilK, MohammadS. Big data privacy: A technological perspective and review. SSRN Electr J, 2017, 4(11): 159-162

[54] AbouelmehdiK, Beni-HessaneA, KhaloufiH. Big healthcare data: preserving security and privacy. J Big Data, 2018, 5(1): 1

[55] ZhangDW, LiX, JiangLX. New medical hotspot: remote collaborative diagnosis and treatment. Sci Technol Rev, 2017, 35(10): 26-31

[56] KulkarniA, SatheS. Healthcare applications of the Internet of Things: A Review. Int J Comput Sci Inform Technol, 2014, 5(5): 6229-6232

[57] Lu D, Tao L, The application of IOT in medical system. 2011 IEEE International Symposium on IT in Medicine and Education, December 9–11, 2011, Guangzhou, China, 272–275

[58] ZhouWH, XiaoTT. Digital future of neonatal critical care medicine. Chin J Pediat (Chinese), 2021, 59(4): 261-263

[59] BarkerDJ. Human growth and chronic disease: a memorial to Jim Tanner. Ann Hum Biol, 2012, 39(5): 335-341

[60] YangL, LiuX, LiZ, et al.. Genetic aetiology of early infant deaths in a neonatal intensive care unit. J Med Genet, 2020, 57: 169-177

[61] YangL, KongY, DongX, et al.. Clinical and genetic spectrum of a large cohort of children with epilepsy in China. Genet Med, 2019, 21(3): 564-571

[62] PavelAM, RennieJM, de VriesLS, et al.. A machine learning algorithm for neonatal seizure recognition: a multicentre, randomised, controlled trial. Lancet Child Adolesc Health, 2020, 4(10): 740-749

[63] Olga BL, Gao XM, Ehsan Y, et al. E-Healthcare: Remote Monitoring, Privacy, and Security. Microwave Symposium IEEE, December 12–14, 2014, Marrakech, Morocco

[64] MasinoAJ, HarrisMC, ForsythD, et al.. Machine learning models for early sepsis recognition in the neonatal intensive care unit using readily available electronic health record data. PLoS One, 2019, 14(2): e0212665

[65] Sanchez PintoLN, StroupEK, PendergrastT, et al.. Derivation and validation of novel phenotypes of multiple organ dysfunction syndrome in critically ill children. JAMA NetwOpen, 2020, 3(8): e209271

[66] KannathalN, AcharyaUR, LimCM, et al.. Classification of cardiac patient states using artificial neural network. Exp Clin Cardiol, 2003, 8(4): 206-211

[67] SengupataPP, HuangYM, BansalM, et al.. Cognitive machine-learning algorithm for cardiac imaging: a pilot study for differentiating constrictive pericarditis from restrictive cardiomyopathy. Cire Cardiovasc Imaging, 2016, 9(6): e004330

[68] SchoenrathF, MarkendorfS, BrauchlinAE, et al.. Robotassisted training early after cardiac surgery. J Card Surg, 2015, 30(7): 574-58

[69] Ottavinano M, Vera-Munoz C, Arredondo MT, et al. Innovative self management system for guided cardiac rehabilitation. Conference proceedings: Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society, August 30–September 3, 2011, Boston, USA, 2011:1559-1562

[70] ChenAY, LuTY, MaMH, et al.. Demand Forecast Using Data Analytics for the Preallocation of Ambulances. IEEE J Biomed Health Inform, 2016, 20(4): 1178-1187

[71] TsienCL, FraserHS, LongWJ, et al.. Using classification tree and logistic regression methods to diagnose myocardial infarction. Stud Health Technol Inform, 1998, 52(1): 493-497

[72] GreenM, BjrkJ, ForbergJ, et al.. Comparison between neural networks and multiple logistic regression to predict acute coronary syndrome in the emergency room. Artif Intell Med, 2006, 38(3): 305-318

[73] BentleyP, GanesalingamJ, Carlton JonesAL, et al.. Prediction of stroke thrombolysis outcome using CT brain machine learning. Neuroimage Clin, 2014, 4: 635-640

[74] ToltzisP, Soto-CamposG, SheltonC, et al.. Evidence Based Pediatric Outcome Predictors to Guide the Allocation of Critical Care Resources in a Mass Casualty Event. Pediatr Crit Care Med, 2015, 16(7): e207-e216

[75] FrancJM, IngrassiaPL, VerdeM, et al.. A simple graphical method for quantification of disaster management surge capacity using computer simulation and process-control tools. Prehosp Disaster Med, 2015, 30(1): 9-15

[76] ZhaiZ, KanQ, LiW, et al.. VTE risk profiles and prophylaxis in medical and surgical inpatients: The identification of Chinese hospitalized patients’ risk profile for venous thromboembolism(DissolVE-2)-a cross-sectional study. Chest, 2019, 155(1): 114

[77] CohenAT, TapsonVF, BergmannJF, et al.. Venous thromboembolism risk and prophylaxis in the acute hospital care setting (ENDORSE study): a multinational cross-sectional study. Lancet, 2008, 371(9610): 387-394

[78] WangLJ, PangJ, WangD, et al.. FX. Design and construction of intelligent early warning system for venous thrombosis risk under big data technology. Chin Digit Med (Chinese), 2020, 15(9): 27-29

[79] MengY, LiXY, SuJF, et al.. Design and implementation of prevention and treatment system for venous thromboembolism (VTE). Chin Digit Med (Chinese), 2020, 15(12): 21-23

[80] Integrated Care Platform[DB/OL]. [2021-09-22] https://www.vitalerter.com/

[81] ECRI Institute. Top 10 health technology hazards for 2020[EB/OL]. (2019-12-20)[2020-01-01] http://www.ecri.org

[82] AACN. Practice alert: alarm management [EB/OL]. (2017-11-22). [2020-01-01] http://ccn.aacnjournals.org

[83] SiebigS, SiebenW, KollmannF, et al.. Users’opinions on intensive care unit alarms-a survey of German intensive care units. Anaesth Intensive Care, 2009, 37(1): 112-116

[84] GulshanV, PengL, CoramM, et al.. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. J Am Med Assoc, 2016, 316(22): 2402-2410

[85] EstevaA, KuprelB, NovoaRA, et al.. Dermatologistlevel classification of skin cancer with deep neural networks. Nature, 2017, 542: 115-118

[86] ZhangK, LiuXH, ShenJ, et al.. Clinically applicable AI system for accurate diagnosis, quantitative measurements, and prognosis of COVID-19 pneumonia using computed tomography. Cell, 2020, 181(6): 1423-1433

[87] Soualmi A, Alti A, Laouamer L. Medical Data Protection Using BlindWatermarking Technique. Enabl AI Appl Data Sci, 2020:557

[88] TuliS, TuliS, WanderG, et al.. Next Generation Technologies for Smart Healthcare: Challenges, Vision, Model, Trends and Future Directions. Intern Technol Let, 2020, 3: e145

[89] Ahamed F, Farid F. Applying Internet of Things and Machine-Learning for Personalized Healthcare: Issues and Challenges. 2018 International Conference on Machine Learning and Data Engineering (iCMLDE), IEEE Computer Society, December 03–07, 2018, Sydney, Australia

[90] Tuya Inc., Gartner Group. 2021 Global AIoT Developers Ecosystem White Paper. Tech Show Developers Conference, December 29, 2020, Hangzhou, China

[91] BanguiH, RakrakS, RaghayS, et al.. Moving to the Edge-Cloud-of-Things: Recent Advances and Future Research Directions. Electronics, 2018, 7(11): 309

[92] Alaybeyi S, Lheureux B. Survey Analysis: Artificial Intelligence Establishes a Foothold in IoT Projects. Gartner, Research, September 20, 2019. https://www.gartner.com/en/documents/3968034/survey-analysis-artificial-intelligence-establishes-a-fo

[93] ZhouZ, ShuaiYU, ChenX. Edge intelligence:a new nexus of edge computing and artificial intelligence. Big Data Res, 2019, 5(2): 53-63

[94] FerdinandAS, KelaherM, LaneCR, et al.. An implementation science approach to evaluating pathogen whole genome sequencing in public health. Genome Med, 2021, 13(1): 121

[95] European Centre for Disease PreventionControlMonitoring the use of whole-genome sequencing in infectious disease surveillance in Europe, 2018, Stockholm, ECDC

[96] QiuT, YangY, QiuJ, et al.. CE-BLAST makes it possible to compute antigenic similarity for newly emerging pathogens. Nat Commun, 2018, 9(1): 1772

[97] World Robotics 2020 Report [DB/OL]. [2020-09-24] https://ifr.org/news/record-2.7-million-robots-work-in-factories-around-the-globe