Classification of epidemiological forecasts and application of gradient boosting in preventive medicine
Federal Government State Establishment Main Center for State Sanitary and Epidemiological Surveillance (Special Purpose) of The Russian Federation Defense Ministry
Federal State Budjet Institution Saint_Peterburg Scientific-Research Institute for physical culture
Brief summary
The article proposes a new justified classification of epidemiological forecasts of acute respiratory infections. An overview of machine learning methods is presented. Examples of the use of the gradient boosting method in the field of clinical medicine for the purpose of predicting somatic morbidity are shown. The relevance of the use of gradient boosting in predicting the incidence of infectious diseases and respiratory diseases is highlighted. The development and implementation of the forecast of acute respiratory infections in organized teams of the Armed Forces of the Russian Federation with a preliminary definition of predictors is proposed.
Key words
machine learning, gradient boosting, retrospective epidemiological analysis, orecasting, prognosis of morbidity, acute respiratory infection, organized collectives, and the Armed Forces of the Russian Federation.
4. Golybkov, A.V. Primenenie iskysstvennih neironnih setei v profilakticheskoi i klinicheskoi medicine (naychnii obzor) / A.V. Golybkov, M.P. Gavrilova // Profilakticheskaya i klinicheskaya medicina. 2020. 4 (77). S. 30-39. DOI: 10.47843/2074-9120_2020_4_30.
5. Gorshenin, A.K. Gibridnie modeli ekstremalnogo gradientnogo bystinga dlya vosstanovleniya propyshennih znachenii v dannih ob osadkah / A.K. Gorshenin, O.P. Martinov // Inform. i ee primen. 2019, T. 13. Vip. 3. S. 34-40. DOI: 10.14357/19922264190306
15. Kitova, O.V. Metod mashin opornih vektorov dlya prognozirovaniya pokazatelei investicii / O.V. Kitova, I.B. Kolmakov, I.A. Penkov // Ekonomika, Statistika i Informatika. - 2016. - 4. - S. 27-30.
16. Kondratev, M.A. Metodi prognozirovaniya i modeli rasprostraneniya zabolevanii. / M.A. Kondratev. // Komputernie issledovaniya i modelirovanie. 2013. T. 5. 5. S. 863-882.
17. Melnichenko, P.I. Retrospektivnii epidemiologicheskii analiz i prognozirovanie zabolevaemosti lichnogo sostava Vooryjennih sil Rossiiskoi Federacii: metod. ykazaniya / P.I. Melnichenko [i dr.]. M.: Voenizdat, 2006. 143 s.
18. Nastavlenie po Globalnoi sisteme obrabotki dannih i prognozirovaniya. Dopolnenie IV k Tehnicheskomy reglamenty VMO. VMO- 485. Jeneva, Shveĭcariya. 2017. 123 s.
19. O sostoyanii sanitarno-epidemiologicheskogo blagopolychiya naseleniya v Rossiiskoi Federacii v 2012 gody: Gosydarstvennii doklad. M.: Federalnaya slyjba po nadzory v sfere zashiti prav potrebitelei i blagopolychiya cheloveka, 2013. 176 s. - URL: https://www.rospotrebnadzor.ru/upload/iblock/7cd/gosudarstvennyy-doklad-o-sostoyanii-sanitarno_epidemiologicheskogo-blagopoluchiya-naseleniya-v-rossiyskoy-federatsii-v-2012-godu.pdf/ (data obrasheniya: 15.04.2021)
20. O sostoyanii sanitarno-epidemiologicheskogo blagopolychiya naseleniya v Rossiiskoi Federacii v 2013 gody: Gosydarstvennii doklad. M.: Federalnaya slyjba po nadzory v sfere zashiti prav potrebitelei i blagopolychiya cheloveka, 2014. 191 s. - URL: https://www.rospotrebnadzor.ru/upload/iblock/3b8/gd_2013_dlya-sayta.pdf/ (data obrasheniya: 15.04.2021)
21. O sostoyanii sanitarno-epidemiologicheskogo blagopolychiya naseleniya v Rossiiskoi Federacii v 2014 gody: Gosydarstvennii doklad. M.: Federalnaya slyjba po nadzory v sfere zashiti prav potrebitelei i blagopolychiya cheloveka, 2015. 206 s. - URL: https://www.rospotrebnadzor.ru/upload/iblock/22c/gd_2014_seb_dlya-sayta.pdf/ (data obrasheniya: 15.04.2021)
22. O sostoyanii sanitarno-epidemiologicheskogo blagopolychiya naseleniya v Rossiiskoi Federacii v 2015 gody: Gosydarstvennii doklad. ? M.: Federalnaya slyjba po nadzory v sfere zashiti prav potrebitelei i blagopolychiya cheloveka, 2016. 200 s. - URL: https://www.rospotrebnadzor.ru/upload/iblock/486/gd_2015_ds.pdf/ (data obrasheniya: 15.04.2021)
23. O sostoyanii sanitarno-epidemiologicheskogo blagopolychiya naseleniya v Rossiiskoi Federacii v 2016 gody: Gosydarstvennii doklad. M.: Federalnaya slyjba po nadzory v sfere zashiti prav potrebitelei i blagopolychiya cheloveka, 2017. 220 s. - URL: https://www.rospotrebnadzor.ru/upload/iblock/0b3/gosudarstvennyy-doklad-2016.pdf/ (data obrasheniya: 15.04.2021)
24. O sostoyanii sanitarno-epidemiologicheskogo blagopolychiya naseleniya v Rossiiskoi Federacii v 2017 gody: Gosydarstvennii doklad. M.: Federalnaya slyjba po nadzory v sfere zashiti prav potrebitelei i blagopolychiya cheloveka, 2018. 268 s. - URL: https://www.rospotrebnadzor.ru/upload/iblock/d9d/gd_2017_seb.pdf/ (data obrasheniya: 15.04.2021)
25. O sostoyanii sanitarno-epidemiologicheskogo blagopolychiya naseleniya v Rossiiskoi Federacii v 2018 gody: Gosydarstvennii doklad. M.: Federalnaya slyjba po nadzory v sfere zashiti prav potrebitelei i blagopolychiya cheloveka, 2019. 254 s. - URL: https://www.rospotrebnadzor.ru/upload/iblock/798/gosudarstvennyy-doklad-o-sostoyanii-sanitarno_epidemiologicheskogo-blagopoluchiya-naseleniya-v-rossiyskoy-federatsii-v-2018-godu.pdf/ (data obrasheniya: 15.04.2021)
33. Tysaeva, A.R. Primenenie korrelyacionno-regressionnogo metoda v ocenke yrovnya zabolevaemosti Kyrskoi oblasti. / A.R. Tysaeva, A.V. Gavrilova. // Molodoi ychenii. 2017. 4 (138). S. 541-544. URL: https://moluch.ru/archive/138/38666/ (data obrasheniya: 02.05.2021).
34. Frolov, A.I. Analiz algoritma gradientnogo bystinga dlya celei prognozirovaniya / A.I. Frolov // Almanah naychnih rabot molodih ychenih Yniversiteta ITMO. XLVIII naychnaya i ychebno-metodicheskaya konferenciya Yniversiteta ITMO / Izdatelstvo: FGAOY VO «Nacionalnii issledovatelskii yniversitet ITMO» Sankt-Peterbyrg, 2019. S. 285-288.
35. Shylgin, S.G. Otbor peremennih dlya analiza i prognozirovaniya nestabilnosti s pomoshu modelei gradientnogo bystinga / S.G. Shylgin // Sistemnii monitoring globalnih i regionalnih riskov. Socialno-politicheskaya i ekonomicheskaya destabilizaciya: analiz stranovih i regionalnih sityacii v mir-sistemnom aspekte / Izdatelstvo «Ychitel» Volgograd, 2018. T. 9. S. 115?153.
36. Yanchevskaya, E.U. Matematicheskoe modelirovanie i prognozirovanie v epidemiologii infekcionnih zabolevaniĭ / E.U. Yanchevskaya, O.A. Mesnyankina // Vestnik Rossiiskogo yniversiteta dryjbi narodov. Seriya: Medicina. 2019. T. 23. 3 S. 328-334. DOI: 10.22363/2313-0245-2019-23-3-328-334.
37. Aler R., Galvan I. M., Ruiz-Arias J. A., Gueymard C. A. Improving the separation of direct and diffuse solar ra- diation components using machine learning by gradient boosting // Sol. Energy, 2017. Vol. 150. P. 558-569.
38. Blaser R., Fryzlewicz P. Random Rotation Ensembles // Journal of Machine Learning Research 17 / 2016. c. 1-26.
39. Chatzis, S.P., Siakoulis V., Petropoulos A., Stavroulakis E., Vlachogiannakis N. Forecasting stock market crisis events using deep and statistical machine learning techniques // Expert Syst. Appl., 2018. Vol. 112. P. 353-371.
40. Chen, T., and Guestrin, C. (2016). «XgBoost: A Scalable Tree Boosting System» in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785-794. doi: 10.1145/2939672.2939785
41. Friedman, J.H. Greedy function approximation: a gradient boosting machine. The Annals of Statistics 2001; 29(5): 1189-1232 URL: https://doi.org/10.1214/aos/1013203451/ (data obrasheniya: 15.03.2021)
42. Harrell FE. Regression modeling strategies: With applications to linear models, logistic regression, and survival analysis. Springer, New York; 2001
43. Henzel, J. Gradient Boosting Application in Forecasting of Performance Indicators Values for Measuring the Efficiency of Promotions in FMCG Retail / J. Henzel, M. Sikora // arXiv:2006.04945v1 [cs.CY] 30 May 2020
44. Hosmer, D.W., Lemeshow, S. Applied Logistic Regression. New York:Wiley 1989.
45. Mustapha, I. B., and F. Saeed. Bioactive molecule prediction using extreme gradient boosting. Molecules 2016. 21(8):983.
46. Natekin A., Knoll A. Gradient boosting machines, a tutorial. Front Neurorobot 2013; 7: 21, https://doi.org/10.3389/ fnbot.2013.00021.
47. Paulo Celio Di Cellio Dias, Melissa Forti, Marc Witarsa // A comparison of Gradient Boosting with Logistic Regression in Practical Cases. - URL: https://www.sas.com/content/dam/SAS/support/en/sas-global-forum-proceedings/2018/1857-2018.pdf/ (data obrasheniya: 19.04.2021)
48. Prokhorenkova, L., Gusev G., Vorobev A., Dorogush A.V., Gulin A. CatBoost: Unbiased boosting with categorical features. 2018. Adv. Neur. In. 31:6638-6648
49. Shalev-Shwartz S, Ben-David S. Understanding Machine Learning: From Theory to Algorithms. New York: Cambridge University Press; 2014. 410 p.
50. Hastie, T., Tibshirani R., Friedman J. The Elements of Statistical Learning: Prediction, Inference and Data Mining (Second Edition). Springer Verlag, New York, 2009.
51. Torres-Barran, A., Alonso A., Dorronsoro J. R. Regression tree ensembles for wind energy and solar radiation predic- tion // Neurocomputing, 2018. Vol. 326. P. 151-160.
52. Xia, Y., Liu C., Li Y., Liu N. A boosted decision tree approach using Bayesian hyper-parameter optimization for credit scoring // Expert Syst. Appl., 2017. Vol. 78. P. 225-241.
53. Zhang, D. A data-driven design for fault detection of wind turbines using random forests and XGboost / D. Zhang [et al.] // IEEE Access, 2018. Vol. 6. P. 21020-21031.
54. Zhang, Z. Predictive analytics with gradient boosting in clinical medicine / Z. Zhang [et al.] // Ann Transl Med 2019;7(7):152. doi: 10.21037/atm.2019.03.29.