Опубликовать статью

Информационное партнерство

Инфоресурсы

Контакты

«

Vol. 23, Art. 36 (pp. 633-647)    |    2022       

»

Prospects for the use of forecasting methods in combustiology (literature review)

1Movchan K.N., 2Deriy E.K., 1Povaliy A.A., 1Ishakov R.B.

1St. Petersburg State Budgetary Health Institution «Medical Information and Analytical Center», St. Petersburg, Russia
2Saint-Petersburg I. I. Dzhanelidze Research Institute of Emergency Medicine, Saint Petersburg, Russia

Brief summary

A review of data from literature sources devoted to research on the problems of introducing statistical analysis methods, machine learning and neural networks into the practical activities of specialists in burn centers is presented. The main areas of scientific research on thermal injury continue to be: the accuracy of determining the area and depth of thermal lesions [1], the prognosis of the course and outcome of burn disease, as well as optimizing the volume and quality of intensive care, the choice of surgical treatment tactics [2]. The emphasis in these aspects of scientific and practical activities is shifting from obtaining basic data during a physical classical examination to targeted mathematical calculations using information and analytical systems - IAS [3,4]. Against the backdrop of the rapid pace of technological progress, the need to apply the latest IT technologies in the development of software and applications that simplify the daily activities of practicing surgeons is beyond doubt. The use of artificial intelligence techniques helps to reduce the likelihood of errors and overdiagnosis when carrying out medical care for patients with burn injuries [5]. The results of multifactorial studies to identify new opportunities for the use of computer technologies in combustiology allow us to confidently judge the high quality of predicting the effectiveness of the treatment of victims of thermal injury and objectively assess the likelihood of its complicated course, which predetermines the prospects for the development of this area of scientific knowledge in combustiology [1,6,7] .


Key words

burns, artificial intelligence, machine learning, prediction, outcome

Reference list

1. Matveenko A.V. Optimalnie modeli prognozirovaniya ishoda ojogov // Vestnik Rossiiskoi Voenno-medicinskoi akademii. - 2020. - T. 22. - 2. - C. 235-240. doi: 10.17816/brmma50079.


2. Zavorotnii O.O., Zinovev E.V., Kostyakov D.V. Vozmojnosti prognozirovaniya letalnogo ishoda tyajeloobojjennih na osnove metodov regressionnogo analiza. Vestnik hiryrgii imeni I.I. Grekova. 2020;179(5):21-29. https://doi.org/10.24884/0042-4625-2020-179-5-21-29


3. Zinovev E.V., Vagner D.O., Chyharev A.E. Ocenka effektivnosti empiricheskih i raschetnih sposobov opredeleniya obema krovopoteri pri hiryrgicheskom lechenii postradavshih ot ojogov. Mediko-biologicheskie i socialno-psihologicheskie problemi bezopasnosti v chrezvichainih sityaciyah. 2022;(1):89-94. https://doi.org/10.25016/2541-7487-2022-0-1-89-94


4. Lam N. N., Hung N. T., Duc N. M. Prognosis value of revised Baux score among burn patients in developing country // International Journal of Burns and Trauma. - 2021. - T. 11. - 3. - S. 197.


5. Estahbanati H.K., Bouduhi N. Role of artificial neural networks in prediction of survival of burn patients - a new approach. Burns. - 2002. - Vol. 28. - P. 579-586.


6. I.R. Galatzer-Levy, S. Ma, A. Statnikov, R. Yehuda, A.Y. Shalev. Utilization of machine learning for prediction of post-traumatic stress: a re-examination of cortisol in the prediction and pathways to non-remitting PTSD. Transl Psychiatry. 2017;(3):1-15


7. Lee, S., Lukan, J., Boyko, T. et al. A deep learning model for burn depth classification using ultrasound imaging //Journal of the Mechanical Behavior of Biomedical Materials. - 2022. - T. 125. - P. 104930.


8. Synodinou, D., Savoie-White, F. H., Sangone A., et al. Health utilities in burn injury survivors: A systematic review //Burns. - 2021. - Vol. 48. - P. 13-22.


9. Khani M. E. et al. Supervised machine learning for automatic classification of in vivo scald and contact burn injuries using the terahertz Portable Handheld Spectral Reflection (PHASR) Scanner //Scientific Reports. - 2022. - T. 12. - 1. - S. 1-12.


10. Alekseev, A.A. Osnovnie statisticheskie pokazateli raboti medicinskih organizacii Rossii po okazaniu specializirovannoi medicinskoi pomoshi postradavshim ot ojogov v 2021 gody / A. A. Alekseev // Zasedanie profilnoi komissii po kombystiologii Minzdrava Rossii sovmestno s Plenymom Obsherossiiskoi obshestvennoi organizacii «Obedinenie kombystiologov «Mir bez ojogov» 2022. Rejim dostypa: http://combustiolog.ru/news_site/zasedaniya-profil-noj-komissii-po-kombustiologii.


11. Huang S. et al. A systematic review of machine learning and automation in burn wound evaluation: a promising but developing frontier //Burns. - 2021. - T. 47. - 8. - S. 1691-1704.


12. Pham C., Collier Z., Gillenwater J. Changing the way we think about burn size estimation //Journal of Burn Care & Research. - 2019. - T. 40. - 1. - S. 1-11.


13. Fransén J. et al. A proof-of-concept study on mortality prediction with machine learning algorithms using burn intensive care data //Scars, burns & healing. - 2022. - T. 8. - P. 20595131211066585.


14. Chauhan J., Goyal P. BPBSAM: body part-specific burn severity assessment model //Burns. - 2020. - T. 46. - 6. - S. 1407-1423.


15. Zavorotnii O. O., Zinovev E. V., Kostyakov D. V. Vozmojnosti povisheniya effektivnosti prognozirovaniya letalnogo ishoda y tyajeloobojjennih s ispolzovaniem metodov logisticheskoi regressii //Jyrnal Neotlojnaya hiryrgiya im. II Djanelidze. - 2021. - S1. - S. 23-24.


16. Colohan S. M. Predicting prognosis in thermal burns with associated inhalational injury: a systematic review of prognostic factors in adult burn victims //Journal of burn care & research. - 2010. - T. 31. - 4. - S. 529-539.


17. Hussain A., Choukairi F., Dunn K. Predicting survival in thermal injury: a systematic review of methodology of composite prediction models //Burns. - 2013. - T. 39. - 5. - S. 835-850.


18. Hussain Z. et al. Recent developments and advanced strategies for promoting burn wound healing //Journal of Drug Delivery Science and Technology. - 2022. - P. 103092.


19. Sheppard N. N. et al. Prognostic scoring systems in burns: a review //Burns. - 2011. - T. 37. - 8. - S. 1288-1295.


20. Bull J.P., Squire J.R. A study of mortality in a burns unit // Ann. Surgery.?1949.?Vol. 130, 2.P. 160-173.


21. Moyer C. A., Dupertuis S. M. The Treatment of Burns //Plastic and Reconstructive Surgery. - 1957. - T. 19. - 5. - S. 432.


22. Ryan, C. M. Functional outcomes following burn injury / C. M. Ryan, I. Parry, R. Richard // Journal of Burn Care and Research. - 2017. - Vol. 38, I. 3. - P. 614-617.


23. Matveenko A. V., Plotnikov S. A., Shindyapin S. V. Model prognoza ishoda ojogovoi travmi na osnove probit-analiza //Vestnik hiryrgii imeni II Grekova. - 2006. - T. 165. - 4. - S. 50-53.


24. Matveenko A. V. Prognozirovanie ishoda termicheskih ojogov //Vestnik hiryrgii imeni II Grekova. - 2009. - T. 168. - 6. - S. 101-104.


25. Vazina I.R., Zydina T.I., Vazin V.A., Ovsyannikov I.M. Prognozirovanie ishodov i kriticheskih periodov ojogovoi bolezni // 5-ya Naych.-prakt. konf. Po probleme termicheskih porajenii: Tezisi dokl. - Gorkii: NIITO, 1986 S. 106-109.


26. Covington D. S., Wainwright D. J., Parks D. H. Prognostic indicators in the elderly patient with burns //The Journal of burn care & rehabilitation. - 1996. - T. 17. - 3. - S. 222-230.


27. Wassermann D., Coste O., Schlotterer M. et al. Prognostic indicators in burned patients: study on a cohort of 847 patients: Abstracts 5th Congress Europian burn Association. - Brighton., 1993. - P. 4.


28. Shlik I.V., Shirokov D.M. Diagnostika, ocenka tyajesti, prognozirovanie ishoda i lechenie termoingalyacionnoi travmi y obojjennih: Metod. rekom. SPb.: GNII SP im. I.I.Djanelidze, 2001.16 s.


29. Vico P., Papillon J. Factors involved in burn mortality: a multivariate statistical approach based on discriminant analysis //Burns. - 1992. - T. 18. - 3. - S. 212-215.


30. Carlson R.G., Finley R.K., Miller S.F. et al. Fluid retention the first 48 hours as an indicator of burn survival // J. Trauma.1986. Vol. 26, 9.P. 840-843.


31. Zavorotnii, O. O., Zinovev, E. V., Volkov, V. G. i dr. Sravnitelnaya ocenka metodov prognozirovaniya letalnogo ishoda tyajeloobojjennih //Innovacionnaya medicina Kybani. - 2022. - 1. - S. 12-18.


32. Wei W., Yang X. Comparison of diagnosis accuracy between a backpropagation artificial neural network model and linear regression in digestive disease patients: An empirical research //Computational and Mathematical Methods in Medicine. - 2021. - T. 2021.


33. Korotkih D.M., Lyah U.E., Gyryanov V.G., Fistal N.N. Is polzo vanie neirosetevogo modelirovaniya dlya prognozirovaniya techeniya i ishoda ojogovoi bolezni // Kombystiologiya..? Prilojenie k Nijegorodsk. med. jyrn.2004.S. 53-54.


34. Hassanipour S. et al. Comparison of artificial neural network and logistic regression models for prediction of outcomes in trauma patients: A systematic review and meta-analysis //Injury. - 2019. - T. 50. - 2. - S. 244-250.


35. Shapovalov S. G., Pleshkov A. S. Takticheskie podhodi v hiryrgicheskom lechenii postradavshih s glybokimi kriticheskimi ojogami //Jyrnal Neotlojnaya hiryrgiya im. II Djanelidze. - 2021. - S1. - S. 73-74.


36. Haller H. L., Dirnberger J., Giretzlehner M. et al. ?Understanding burns?: research project BurnCase 3D?overcome the limits of existing methods in burns documentation //Burns. - 2009. - T. 35. - 3. - S. 311-317.


37. Yoo K. T., Woo G. W., Jang T. Y. et al. Comparison between the Lund-Browder chart and the BurnCase 3D for consistency in estimating total body surface area burned //WikiJournal of Medicine. - 2020. - T. 7. - 1. - S. 1-8.


38. Serrano C., Boloix-Tortosa, R., Gómez-Cía, T., Acha, B. Features identification for automatic burn classification //Burns. - 2015. - T. 41. - 8. - S. 1883-1890.


39. Cirillo M. D., Mirdell R., Sjöberg F. et al. Time-independent prediction of burn depth using deep convolutional neural networks //Journal of Burn Care & Research. - 2019. - T. 40. - 6. - S. 857-863.


40. Acha B., Serrano C., Fondón I. et al. Burn depth analysis using multidimensional scaling applied to psychophysical experiment data //IEEE Transactions on Medical Imaging. - 2013. - T. 32. - 6. - S. 1111-1120.


41. Rowland R. A., Ponticorvo A., Baldado M. L. et al. Burn wound classification model using spatial frequency-domain imaging and machine learning //Journal of biomedical optics. - 2019. - T. 24. - 5. - P. 056007.


42. Giretzlehner M., Dirnberger J., Owen R. et al. The determination of total burn surface area: how much difference? //Burns. - 2013. - T. 39. - 6. - S. 1107-1113.


43. Koppenol D. C., Vermolen F. J., Koppenol-Gonzalez G. V. et al. A mathematical model for the simulation of the contraction of burns //Journal of Mathematical Biology. - 2017. - T. 75. - 1. - S. 1-31.


44. Kashf D. W. A., Okasha A. N., Sahyoun N. A. et al. ANN for Predicting DNA Lung Cancer //Lung cancer. - 2018. - T. 2. - 10. - S. 6-13.


45. Hu B., Yin G., Sun X. Identification of specific role of SNX family in gastric cancer prognosis evaluation //Scientific Reports. - 2022. - T. 12. - 1. - S. 1-15.


46. Kraushkin P. V. Vozmojnosti iskysstvennogo intellekta v diagnostike onkologicheskih zabolevanii koji //Kosmetika i medicina. - 2018. - 3. - S. 90-99.


47. Abubakar A., Ugail H., Bukar A. M. Can machine learning be used to discriminate between burns and pressure ulcer? //Proceedings of SAI intelligent systems conference. - Springer, Cham, 2019. - S. 870-880.


48. Rostami B. et al. Multiclass Burn Wound Image Classification Using Deep Convolutional Neural Networks //arXiv preprint arXiv:2103.01361. - 2021.


49. Anisuzzaman D. M. et al. Wound Severity Classification using Deep Neural Network //arXiv preprint arXiv:2204.07942. - 2022.