COVID-19 tanısında biyokimyasal testlerin makine öğrenimi destekli kullanımı

Büyük veri analizleri ile kendi kendine öğrenen sistemler geliştirebilen makine öğrenimi yaklaşımı günümüzde birçok alanda olduğu gibi laboratuvar tıbbında da kullanıma girmiştir. Gerçek zamanlı ters transkripsiyon polimeraz zincir reaksiyonu (rRT PCR) testi, COVID 19 tanısında altın standart metot olmasına rağmen, hassas preanalitik evre, uzun turn around time ve sürekli sarf ihtiyacı gibi birçok dezavantaja sahiptir. Günlük hayatımızın bir parçası olan makine öğrenim algoritmaları COVID 19 pandemisinde mevcut tanı yöntemlerine alternatif maliyetsiz bir metot olarak denenmiştir. Bu konuda yapılan çalışmalara bakıldığında rutin biyokimya testleri ile oluşturulan makine öğrenim modelleri tanıyla beraber hızlı dışlama, prognoz, klinik ilişkili testlerin karşılaştırılması gibi birçok farklı açıdan başarılı bir performans göstermiştir. Biyokimyasal testlerin yaygın klinik kullanımı ve tıbbi laboratuvarların rutininde yer alan otoanalizörler ve laboratuvar bilgi sistemlerinin uygun yazılım altyapıları göz önüne alındığında ve bunlara artan sağlık maliyetleri ve mevcut yöntemlerin dezavantajları eklendiğinde makine öğrenimi biyokimya laboratuvarı ilişkisinin gelecekte de gelişmeye açık popüler bir konu olmaya devam edeceği öngörülmektedir. Bu derlemede COVID 19 tanısında kullanılan yöntemler özetlenmiş, makine öğrenim modellerinin temel prensipleri anlatılmış ve biyokimya testleri ile makine öğrenim modellerinin kullanımlarına örnek verilmiştir.

USAGE OF BIOCHEMICAL TESTS BASED ON MACHINE LEARNING IN THE DIAGNOSIS OF COVID-19

Machine learning approach, which can develop self learning systems with big data analysis, has been used in laboratory medicine as in many fields today. Although the real time reverse transcription polymerase chain reaction (rRTPCR) test is the gold standard method in the diagnosis of COVID 19, it has many disadvantages such as sensitive preanalytical phase, long turn around time and continuous need for consumables. Machine learning algorithms, which are now a part of daily life, have been tried as a cost free alternative method to existing diagnostic methods in the COVID 19 pandemic. When looking at the studies on this subject, machine learning models created with routine biochemistry tests have shown a successful performance in many different aspects such as rapid exclusion with diagnosis, prognosis, comparison of clinically relevant tests. Considering the widespread clinical use of biochemical tests and auto analyzers in the routine medical laboratories and the appropriate software infrastructures of laboratory information systems along with the increased healthcare costs and the disadvantages of existing methods, it is predicted that the relationship between machine learning and biochemistry laboratory will continue to be a popular topic favorable to development in the future. In this review, the methods used in the diagnosis of COVID 19 are summarized, the basic principles of machine learning models are explained and examples of the use of biochemistry tests and machine learning models are given.

PDF

___

1. T.C. Sağlık Bakanlığı Halk Sağlığı Genel Müdürlüğü (2020) COVID 19 (SARS CoV 2 ENFEKSİYONU) Genel Bilgiler, Epidemiyoloji ve Tanı. [Erişim tarihi: 24 Ocak 2021] Erişim adresi: https://covid19.saglik.gov.tr/TR 66337/genel bilgilerepidemiyoloji ve tani.html.
2. WHO Coronavirus (COVID 19) Dashboard. [Erişim tarihi: 23 Mart 2021] Erişim adresi: https://covid19.who.int.
3. Dikmen A, Kına M, Özkan S, İlhan M. COVID 19 Epidemiyolojisi: Pandemiden Ne Öğrendik? J Biotechnol and Strategic Health Res. 2020;1(COVID 19 Özel Sayı):S29 36.
4. World Health Organization. (2020). Laboratory testing for coronavirus disease 2019 (COVID 19) in suspected human cases: interim guidance, 2 March 2020. World Health Organization. [Erişim tarihi: 24 Ocak 2021] Erişim adresi: https://apps.who.int/iris/handle/10665/331329.
5. Coronavirus Testing Basics. [Erişim tarihi: 24 Ocak 2021] Erişim adresi: https://www.fda.gov/media/140161/download.
6. Vandenberg O, Martiny D, Rochas O, van Belkum A, Kozlakidis Z. Considerations for diagnostic COVID 19 tests. Nat Rev Microbiol. 2021;19:171 83..
7. Wikramaratna PS, Paton RS, Ghafari M, Lourenço J. Estimating the false negative test probability of SARSCoV 2 by RT PCR. Euro Surveill. 2020;25(50):2000568. doi:10.1101/2020.04.05.20053355.
8. Winichakoon P, Chaiwarith R, Liwsrisakun C, Salee P, Goona A, Limsukon A et al. Negative Nasopharyngeal and Oropharyngeal Swabs Do Not Rule Out COVID 19. J Clin Microbiol. 2020;58(5):e00297 20. doi: 10.1128/JCM.00297 20.
9. Chavez S, Long B, Koyfman A, Liang SY. Coronavirus Disease (COVID 19): A primer for emergency physicians. Am J Emerg Med. 2020:S0735 6757(20)30178 9.
10. Larremore DB, Wilder B, Lester E, Shehata S, Burke JM, Hay JA et al. Test sensitivity is secondary to frequency and turnaround time for COVID 19 screening. Sci Adv. 2021;7(1):eabd5393. doi: 10.1126/sciadv.abd5393.
11. Li Z, Yi Y, Luo X, Xiong N, Liu Y, Li S et al. Development and clinical application of a rapid IgMIgG combined antibody test for SARS CoV 2 infection diagnosis. J Med Virol. 2020;92(9):1518 24.
12. Russell SJ, Norvig P. (2010). Artificial Intelligence: A Modern Approach (Third ed.). Prentice Hall. [Internet]. [Erişim tarihi: 13 Şubat 2021] Erişim adresi: https://www.cin.ufpe.br/~tfl2/artificial intelligencemodern approach.9780131038059.25368.pdf.
13. Alpaydin E. (2010). Introduction to Machine Learning. MIT Press. p. 9. [Internet]. [Erişim tarihi: 13.02.2021] Erişim adresi: https://www.cmpe.boun.edu.tr/~ethem/i2ml2e/.
14. Cabitza F, Banfi G. Machine learning in laboratory medicine: waiting for the flood?. Clin Chem Lab Med. 2018;56(4):516 24.
15. Rohr UP, Binder C, Dieterle T, Giusti F, Messina C, Toerien E et al. The Value of In Vitro Diagnostic Testing in Medical Practice: A Status Report. PLoS One. 2016;11(3):e0149856. https://doi.org/10.1371/journal.pone.0149856 Erişim adresi: https://journals.plos.org/plosone/article?id=10.1371/jo urnal.pone.0149856
16. Lin C, Karlson EW, Canhao H, Miller TA, Dligach D, Chen PJ et al. Automatic prediction of rheumatoid arthritis disease activity from the electronic medical records. PLoS One. 2013;8(8):e69932. doi.org/10.1371/journal.pone.0069932 Erişim adresi: https://journals.plos.org/plosone/article?id=10.1371/jo urnal.pone.0069932
17. Nelson DW, Rudehill A, MacCallum RM, Holst A, Wanecek M, Weitzberg E et al. Multivariate outcome prediction in traumatic brain injury with focus on laboratory values. J Neurotrauma. 2012;29(17):2613 24.
18. Liu KE, Lo CL, Hu YH. Improvement of adequate use of warfarin for the elderly using decision tree based approaches. Methods Inf Med. 2014;53(1):47 53.
19. Razavian N, Blecker S, Schmidt AM, Smith McLallen A, Nigam S, Sontag D. Population Level Prediction of Type 2 Diabetes From Claims Data and Analysis of Risk Factors. Big Data. 2015;3(4):277 87.
20. Cao Y, Cheng M, Hu C. UrineCART, a machine learning method for establishment of review rules based on UF 1000i flow cytometry and dipstick or reflectance photometer. Clin Chem Lab Med. 2012;50(12):2155 61.
21. Goldstein BA, Navar AM, Carter RE. Moving beyond regression techniques in cardiovascular risk prediction: applying machine learning to address analytic challenges. Eur Heart J. 2017;38(23):1805 14.
22. Diri B, Varlı AS. Visualization and analysis of classifiers performance in multi class medical data. Expert Systems with Applications. 2008;1(34):628 34.
23. Guan WJ, Ni ZY, Hu Y, Liang WH, Ou CQ, He JX, et al. Clinical characteristics of coronavirus disease 2019 in China. N Engl J Med. 2020;382:1708–20.
24. Joshi RP, Pejaver V, Hammarlund NE, Sung H, Lee SK, Furmanchuk A et al. A predictive tool for identification of SARS CoV 2 PCR negative emergency department patients using routine test results. J Clin Virol. 2020;129:104502.
25. Yang HS, Hou Y, Vasovic LV, Steel P, Chadburn A, Racine Brzostek SE et al. Routine Laboratory Blood Tests Predict SARS CoV 2 Infection Using Machine Learning. Clin Chem. 2020;66(11):1396 404.
26. Mei X, Lee HC, Diao K, Huang M, Lin B, Liu C et al. Artificial intelligence enabled rapid diagnosis of COVID 19 patients. Preprint. medRxiv. 2020;2020.04.12.20062661. doi: 10.1101/2020.04.12.20062661. Erişim adresi: https://www.nature.com/articles/s41591 020 0931 3
27. Meng Z, Wang M, Song H, Guo S, Zhou Y, Li W et al. Development and utilization of an intelligent application for aiding COVID 19 diagnosis. medRxiv. 2020;2020.03.18.20035816. doi:10.1101/2020.03.18.20035816 Erişim adresi: https://www.medrxiv.org/content/10.1101/2020.03.18. 20035816v1
28. Gong J, Ou J, Qiu X, Jie Y, Chen Y, Yuan L et al. A Tool for Early Prediction of Severe Coronavirus Disease 2019 (COVID 19): A Multicenter Study Using the Risk Nomogram in Wuhan and Guangdong, China. Clin Infect Dis. 2020;71(15):833 40.
29. Sun L, Song F, Shi N, Liu F, Li S, Li P et al. Combination of four clinical indicators predicts the severe/critical symptom of patients infected COVID 19. J Clin Virol. 2020;128:104431.
30. Yu H, Shao J, Guo Y, Xiang Y, Sun C, Yuan Y. Datadriven discovery of clinical routes for severity detection in COVID 19 pediatric cases. medRxiv. 2020;2020.03.09.20032219. DOI: 10.1101/2020.03.09.20032219. Erişim adresi: https://www.medrxiv.org/content/10.1101/2020.03.18. 20035816v1.full
31. Yadaw AS, Li YC, Bose S, Iyengar R, Bunyavanich S, Pandey G. Clinical features of COVID 19 mortality: development and validation of a clinical prediction model. Lancet Digit Health. 2020;2(10):e516 e525.
32. Cabitza F, Campagner A, Ferrari D, Di Resta C, Ceriotti D, Sabetta E et al. Development, evaluation, and validation of machine learning models for COVID 19 detection based on routine blood tests. Clin Chem Lab Med. 2020;59(2):421 31.
33. Samuel AL. Some Studies in Machine Learning Using the Game of Checkers. IBM Journal of Research and Development. 1959;44:206–226.
34. Schwartz WB. Medicine and the computer. The promise and problems of change. N Engl J Med. 1970;283(23):1257 64.
35. Alvin R, Jeffrey D, Isaac K. Machine Learning in Medicine. N Engl J Med. 2019;380(14):1347 58.
36. Sun K, Chen J, Viboud C. Early epidemiological analysis of the coronavirus disease 2019 outbreak based on crowdsourced data: a population level observational study. Lancet Digital Health. 2020;2(4):e201 e208.
37. Husnayain A, Fuad A, Su EC Y. Applications of Google Search Trends for risk communication in infectious disease management: a case study of the COVID 19 outbreak in Taiwan. Int J Infect Dis. 2020;95:221 3.
38. Bung N, Krishnan SR, Bulusu G, Roy A. De novo design of new chemical entities (NCEs) for SARSCoV 2 using artificial intelligence. ChemRxiv. 2020. doi:10.26434/chemrxiv.11998347.v2. Erişim adresi: https://chemrxiv.org/articles/preprint/De_Novo_Desi gn_of_New_Chemical_Entities_NCEs_for_SARSCoV 2_Using_Artificial_Intelligence/11998347.
39. Enayatkhani M, Hasaniazad M, Faezi S, et al. Reverse vaccinology approach to design a novel multi epitope vaccine candidate against COVID 19: an in silico study. J Biomol Struct Dyn. 2020:1 16.
40. Yan L, Zhang HT, Goncalves J, Xiao Y, Wang M, Guo Y et al. An interpretable mortality prediction model for COVID 19 patients.J Mach Intell.2020;2:283 8.
41. Ikemura K, Bellin E, Yagi Y, Billet H, Saada M, Simone K et al. Using Automated Machine Learning to Predict the Mortality of Patients With COVID 19: Prediction Model Development Study. J Med Internet Res. 2021;23(2):e23458. doi:10.2196/23458. Erişim adresi: https://www.jmir.org/2021/2/e23458/
42. Statsenko Y, Al Zahmi F, Habuza T, Gorkom KN, Zaki N. Prediction of COVID 19 severity using laboratory findings on admission: informative values, thresholds, ML model performance. BMJ Open. 2021;11(2):e044500. doi:10.1136/bmjopen 2020 044500. Erişim adresi: https://bmjopen.bmj.com/content/11/2/e044500
43. Berenguer J, Borobia AM, Ryan P, Rodríguez Baño J, Bellón JM, Jarrín I et al. Development and validation of a prediction model for 30 day mortality in hospitalised patients with COVID 19: the COVID 19 SEIMC score. Thorax. 2021;thoraxjnl 2020 216001. doi:10.1136/thoraxjnl 2020 216001. Erişim adresi: https://thorax.bmj.com/content/early/2021/02/25/thor axjnl 2020 216001?rss=1
44. Brinati D, Campagner A, Ferrari D, Locatelli M, Banfi G, Cabitza F. Detection of COVID 19 Infection from Routine Blood Exams with Machine Learning: A Feasibility Study. J Med Syst. 2020;44(8):135.
45. Wynants L, Van Calster B, Collins GS, Riley RD, Heinze G, Schuit E et al. Prediction models for diagnosis and prognosis of covid 19 infection: systematic review and critical appraisal. BMJ. 2020;369:m1328. Doi:10.1136/bmj.m1328. Erişim adresi: https://www.bmj.com/content/369/bmj.m1328
46. Moons KG, Altman DG, Reitsma JB, Ioannidis JP, Macaskill P, Steyerberg EW et al. Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis (TRIPOD): explanation and elaboration. Ann Intern Med. 2015;162(1):W1 W73.
47. Cabitza F, Zeitoun JD. The proof of the pudding: in praise of a culture of real world validation for medical artificial intelligence. Ann Transl Med. 2019;7(8):161.
48. Lippi G, Mattiuzzi C, Sanchis Gomar F, Henry BM. Clinical and demographic characteristics of patients dying from COVID 19 in Italy vs China. J Med Virol. 2020;92(10):1759 60.