COVID-19 Sürecindeki Yapay Zeka, Dijital Sağlık Tanı ve Tedavisindeki Gelişmeler

Abstract

21. yüzyılda nesnelerin interneti teknolojisinin ilerlemesi ile yapay zeka kavramı daha geniş bir alana yayılmıştır. Yapay zeka ile doğadaki varlıkla-rın akıllı davranışları yapay olarak üretilmektedir. Yapay zeka teknolojileri olarak; uzman sistemler, bulanık mantık, makine öğrenmesi, yapay sinir ağları kullanılır. Yapay zeka, tıp alanında tanı ve sürecin tanımlanmasında kullanılır.Yapay zeka ile birlikte yapay zeka (AR), sanal zeka (VR), hologram, gi-yilebilir teknoloji gibi kavramlar önem kazanmıştır. Bu kavramların önem kazanmasının yanında sağlıkta büyük veride yaşanan sorunlar da vardır. Bu çalışmada nesnelerin interneti ve sağlık alanında AR, VR gibi teknolojilerin kullanımı, büyük veri kavramının sağlık alanında kullanım avantajları ve dezavantajları, yapay zeka ve yapay zekanın bazı hastalıkların tanısında ve teşhisinde kullanılması ve gelecekte sağlık alanındaki teknolojik gelişimler ve öngörüler anlatılmıştır. Sağlık alanındaki gelişmeler ile ilişkili olarak pandemi döneminden örnekler verilmiştir. COVID-19 tespiti için yapılan yapay zeka tabanlı sistemler ile dijital çağa uyum sağladığmız görülmüştür. Sonuçlar bize gelecekte yapay zekanın gelişmesiyle birlikte yeni ilaçların keşfinin hızlı bir şekilde olacağı, oluşabilecek hastalıkların tanı ve teda-visinin daha önceden tespit edilebileceği, hasta kontrollerinin daha hızlı ve daha sık gerçekleştirilebileceği, sağlık personel yükünün hafifleyeceği, küresel sorunların çözümlerinin çok daha hızlı bir şekilde bulunabileceğini göstermiştir.

Keywords

• COVID-19
• Teletıp
• Yapay zeka
• Sağlık
• Büyük veri

Advances in Artificial Intelligence and Digitalization in Health

Abstract

With the advancement of Internet of Things (IoTs) technology in the 21st century, the concept of artificial intelligence (AI) has taken a wider place. Intelligent behaviors of livings are produced artificially with AI. Expert systems, fuzzy logic, machine learning, artificial neural networks are used as AI technologies. AI is used in the healthcare field to diagnose and define the process.Along with AI, concepts such as Augmented Reality (AR), Virtual Re-ality (VR), hologram, wearable technology have gained importance. Besi-des the importance of these concepts, there are also major problems related to big data in medicine. In this study, IoTs and the use of technologies such as AR and VR, the advantages and disadvantages of using big data in the to big data in medicine. In this study, IoTs and the use of technologies such as AR and VR, the advantages and disad-vantages of using big data in the field of healthcare, the use of artificial intelligence and artificial intelligence in the di-agnosis of some diseases, and future technological develop-ments and predictions in the field of healthcare are explained. Examples from the pandemic period are given in relation to developments in the field of healthcare. It has been observed that we have adapted to the digital age with AI-based systems for the detection of COVID-19. The results have shown that with the development of AI in the future, the discovery of new drugs will be rapid, the diagnosis and treatment of the diseases that may occur can be detected earlier, patient cont-rols can be performed faster and more often, the burden on health staff will be reduced, and solutions to global problems can be found much faster.

Keywords

• COVID-19
• Telemedicine
• Artificial intelligence
• Health
• Big data

References

1. 1. Mantovani F, Castelnuovo G, Gaggioli A. Virtual reality training for health-care professionals. Cyberpsychol Behav. 6(4):389-95. 2003. doi: 10.1089/109493103322278772.
2. 2. Orlosky J, Itoh Y, Ranchet M. Emulation of Physician Tasks in Eye-Tracked Virtual Reality for Remote Diagnosis of Neuro-degenerative Disease in IEEE Transactions on Visualization and Computer Graphics, 2017. vol. 23, no. 4, pp. 1302-1311. doi:10.1109/TVCG.2017.2657018.
3. 3. Zhu E, Hadadgar A, Masiello I and Zary N. Augmented reality in healthcare education: an integrative review. PeerJ, 2, e469. 2014. doi:10.7717/peerj.469
4. 4. Hainke C and Pfeiffer T. Adapting virtual trainings of applied skills to cognitive processes in medical and health care educa-tion within the DiViDaG project. DELFI 2020 – Die 18. Fa-chtagung Bildungstechnologien der Gesellschaft für Informatik e.V. 2020
5. 5. Gündüz MZ and Daş R. Nesnelerin interneti: Gelişimi, bileşen-leri ve uygulama alanları. Pamukkale University Journal of En-gineering Sciences, 24(2), 327-335, 2018. doi:10.5505/pajes. 2017.89106
6. 6. Wilson S and Laing R. Wearable Technology: Present and Future. Conference: 91st World Conference of The Textile Institute At: Leeds, UK, July 2018. Available from: https://www.research-gate.net/publication/327542210_Wearable_Technology_Pre-sent_and_Future
7. 7. Northwestern. Monitoring COVID-19 from hospital to home: First wearable device continuously tracks key symptoms [In-ternet] May 2020 [cited 2020 August 25] Available from: https://news.northwestern.edu/stories/2020/04/monito-ring-covid-19-from-hospital-to-home-first-wearable-devi-ce-continuously-tracks-key-symptoms
8. 8. Köse G. ve Kurutkan MN. Sağlık Hizmetlerinde Nesnelerin İn-terneti Uygulamalarının Bibliyometrik Analizi . Avrupa Bilim ve Teknoloji Dergisi , (27) , 412-432 . 2021. doi: 10.31590/ejo-sat.86800

9. 9. Atalay M ve Çelik E. Büyük Veri Analizinde Yapay Zekâ Ve Ma-kine Öğrenmesi Uygulamalari - Artificial Intelligence and Mac-hine Learning Applications in Big Data Analysis. Mehmet Akif Ersoy Üniversitesi Sosyal Bilimler Enstitüsü Dergisi, 9(22), 155-172. 2017. doi: 10.20875 makusobed.309727
10. 10. Habl C, Renner AT, Bobek J. Study on Big Data in Public He-alth, Telemedicine and Healthcare Final Report . 2016.
11. 11. Gupta B, Kumar A, and Dwivedi RK. Big Data and Its Applica-tions–A Review, 2018 International Conference on Advances in Computing, Communication Control and Networking (ICACC-CN) ,pp. 146-149., IEEE.
12. 12. Estava A, Kuprel B, Novoa RA. Dermatologist level classificati-on of skin cancer with deep neural networks. 2017. doi:10.1038/nature21056.
13. 13. Gargeya R and Leng T. Automated identification of diabetic re-tinopathy using deep learning. Ophthalmology, 2017. 124(7), 962-969. doi:10.1016/j.ophtha.2017.02.008.
14. 14. Esteva A, Kuprel B, Novoa RA, et al. Dermatologist-level clas-sification of skin cancer with deep neural networks. Nature 542, 115–118. 2017. doi: 10.1038/nature21056.
15. 15. Hannun AY, Rajpurkar P, Haghpanahi M. Cardiologist-level arr-hythmia detection and classification in ambulatory electrocardi-ograms using a deep neural network. Nat Med 25, 65–69. 2019. doi: 10.1038/s41591-018-0268-3.
16. 16. Zhang J, Gajjala S, Agrawal P. Fully automated echocardiog-ram interpretation in clinical practice: feasibility and diagnostic accuracy. Circulation, 2018. 138(16), 1623-1635. doi: 10.1161/CIRCULATIONAHA.118.034338.
17. 17. Oikonomou EK, Williams MC, Kotanidis CP. A novel machine learning-derived radio transcriptomic signature of perivascular fat improves cardiac risk prediction using coronary CT angiog-raphy. European heart journal, 2019. 40(43), 3529-3543. doi: 10.1093/eurheartj/ehz592.
18. 18 Aronson S and Rehm H. Building the foundation for genomics precision medicine. Nature, 2015. 526, 336–342 doi: 10.1038/nature15816.
19. 19 Rysavy M. Evidence-based medicine: a science of uncertainty and an art of probability. AMA Journal of Ethics, 2013. 15(1), 4-8. doi: 10.1001/virtualmentor.2013.15.1.fred1-1301.
20. 20. Büyükkalaycı G and Karaca HM. Pazarlama 4.0: Nesnelerin İn-terneti. Üçüncü Sektör Sosyal Ekonomi Dergisi, 2019. 54(1), 463-477. doi: 10.15659/3.sektor-sosyal-ekonomi. 19.03.1105
21. 21. Büyükgöze S ve Dereli E. Dijital Sağlık Uygulamalarında Yapay Zeka. VI. Uluslararası Bilimsel ve Mesleki Çalışmalar Kongresi-Fen ve Sağlık, 07-10, 2019.
22. 22. Park S and Jayaraman S. Enhancing the Quality of Life th-rough Wearable Technology. IEEE Engineering in Medici-ne and Biology Magazine, 22(3), 2003. 41-48. doi: 10.1109 MEMB.2003.1213625
23. 23. Mordor Intelligence. (2019). Akıllı giyilebilir teknoloji ürünleri pazarı - büyüme, Trendler, and tahminler.
24. 24. GCF Global. Giyilebilir teknoloji ürünlerinin artı ve eksileri. [Internet] 2019 [cited 2020 January] Available from: https://edu.gcfglobal.org/en/wearables/pros-and-cons-of-wearable-te-chnology/1
25. 25. Designboom. C-mask, a smart face mask that can translate and transcribe for you [Internet] July 2020 [cited 2021 Janu-ary] Available from: https://www.designboom.com/design/do-nut-robits-c-mask-internet-connected-07-07-2020/
26. 26. Altındiş S ve Kıran M. Sağlık Hizmetlerinde Büyük Veri. Aca-demic Review of Economics and Administrative Sciences, 2018. 11(2), 257-271. doi: 10.25287/ohuiibf.366227
27. 27. Sevli O. Göğüs Kanseri Teşhisinde Farklı Makine Öğrenme-si Tekniklerinin Performans Karşılaştırması. Avrupa Bilim ve Teknoloji Dergisi, 2019. (16), 176-185. doi: https://doi.org/10.31590/ejosat.553549
28. 28. Wang D, Qian Z, Vukicevic M. 3D Printing, Computational Modeling, and Artificial Intelligence for Structural Heart Di-sease. JACC: Cardiovascular Imaging. 2020. doi:10.1016/j.jcmg.2019.12.022
29. 29. Borrego P, González EL, Sousa P. The role of deep learning-ba-sed artificial intelligence diagnostic system in detecting pediatric pneumonia with Chest x-ray in the clinical practice. European Congress of Radiology, 2020. doi:10.26044/ecr2020/C-10039.
30. 30. Dawes TJ, de Marvao A, Shi W. Machine learning of three-di-mensional right ventricular motion enables outcome prediction in pulmonary hypertension: a cardiac MR imaging study. Radi-ology, 2017. 283(2), 381-390. doi: 10.1148/radiol.2016161315.
31. 31. Mathotaarachchi S, Pascoal TA, Shin M, et al. Identifying in-cipient dementia individuals using machine learning and amy-loid imaging. Neurobiology of aging, 2017. 59, pp: 80-90. doi: 10.1016/j.neurobiolaging.2017.06.027.
32. 32. Long E, Lin H, Liu Z. An artificial intelligence platform for the multihospital collaborative management of congenital ca-taracts. Nat Biomed Eng, 2017. 1(2), 1-8 . doi:10.1038/s41551-016-0024
33. 33. VerMilyea M, Hall JMM, Diakiw SM. Development of an ar-tificial intelligence-based assessment model for prediction of embryo viability using static images captured by optical light microscopy during IVF. Human Reproduction, 2020. 35(4), 770-784. doi: 10.1093/humrep/deaa013.
34. 34.Yang M, Liu C, Wang X. An Explainable Artificial Intelligence Predictor for Early Detection of Sepsis. Critical care medicine, 2020. doi:10.1097/CCM.0000000000004550
35. 35. Shademan A, Decker RS, Opfermann JD. Supervised autono-mous robotic soft tissue surgery. Science translational medici-ne, 2016. 8(337), 337ra64-337ra64. doi:10.1126/scitranslmed.aad9398.4
36. 36. Toğaçar M, Ergen B, Cömert Z. COVID-19 detection using deep learning models to exploit Social Mimic Optimization and stru-ctured chest X-ray images using fuzzy color and stacking ap-proaches. Comput Biol Med. 2020;121:103805. doi:10.1016/j.compbiomed.2020.103805
37. 37. Wedmid A, Llukani E and Lee DI. Future perspectives in robotic surgery. BJU International, 108(6b), 1028-1036. 2011 Sep;108(6 Pt 2):1028-36. Sep doi:10.1111/j.1464-410X.2011.10458.x
38. 38. Davenport T and Kalakota R. The potential for artificial intel-ligence in healthcare. Future healthcare journal, 2019. 6(2), 94. Doi: org/10.7861/futurehosp.6-2-94.
39. 39. Eckert M, Volmerg J, and Friedrich C. Systematic Review of Augmented Reality in Healthcare (Preprint). 2018. Doi: 10.2196/preprints.10967.
40. 40. Brown MS, Ashley B and Koh A. Wearable technology for ch-ronic wound monitoring: current dressings, advancements, and future prospects. Frontiers in bioengineering and biotechnology, 2018. 6, 47. doi: 10.3389/fbioe.2018.00047.
41. 41.Esteva A, Kuprel B, Novoa RA. Dermatologist-level classificati-on of skin cancer with deep neural networks. Nature 542, 2017. 115–118. doi:10.1038/nature21056.
42. 42. Dawes TJ, de Marvao A, Shi W. Machine learning of three-di-mensional right ventricular motion enables outcome prediction in pulmonary hypertension: a cardiac MR imaging study. Radi-ology, 2017. 283(2), 381-390. doi: 10.1148/radiol.2016161315.
43. 43. Gökrem L ve Bozuklu M. Nesnelerin İnterneti: Yapılan Çalış-malar ve Ülkemizdeki Mevcut Durum. Gaziosmanpaşa Bilim-sel Araştırma Dergisi , (13) , 47-68 . Retrieved 2016. Available from: https://dergipark.org.tr/en/pub/gbad/issue/29709/319647
44. 44. Borrego P, Gonzalez EL, Sousa P. The role of deep learning-ba-sed artificial intelligence diagnostic system in detecting pe-diatric pneumonia with Chest x-ray in the clinical practice. European Congress of Radiology 2020. 2020. doi:10.26044/ecr2020/C-10039
45. 45. Wang B, Jin S, Yan Q. AI-assisted CT imaging analysis for CO-VID-19 screening: Building and deploying a medical AI sys-tem. Applied soft computing, 98, 106897. 2021. Available from: https://doi.org/10.1016/j.asoc.2020.106897
46. 46. Wehbe RM, Sheng J, Dutta S. DeepCOVID-XR: An Artificial Intelligence Algorithm to Detect COVID-19 on Chest Radiog-raphs Trained and Tested on a Large U.S. Clinical Data Set. Radiology. 2021. Apr;299(1):E167-E176. doi: 10.1148/radi-ol.2020203511. Epub 2020 Nov 24. PMID: 33231531; PMCID: PMC7993244.
47. 47. Bhattacharya S, Maddikunta PKR, Pham QV. Deep learning and medical image processing for coronavirus (COVID-19) pande-mic: A survey. Sustain Cities Soc. 2021. Feb;65:102589. doi: 10.1016/j.scs.2020.102589