ISSN 2415-3060 (print), ISSN 2522-4972 (online)
  • 18 of 45
Up
УЖМБС 2018, 3(3): 93–100
https://doi.org/10.26693/jmbs03.03.093
Clinical Medicine

Model of the Course Prognosis and the Results of a Severe Isolated Craniocerebral Trauma

Masalitin I. M. 1, Kochina M. L. 2, Firsov O. G. 3
Abstract

One of the types of injuries (30-50% of all traumatic injuries) that are most commonly encountered today is the craniocerebral trauma (CСT), which ranks first in the structure of neurosurgical pathology. CCT is the main cause of death and disability in people under the age of 45 and outweighs tumor and vascular diseases. As a rule, the injured are young people of working age. Almost one third of injured remain disabled. In addition, CCT occupies one of the leading places in the mortality structure, ranging from 40% to 55% of all traumatic injuries. One of the most important tasks that must be solved when organizing and conducting treatment of CCT is the prognosis of the course and outcome of CCT. In this case, the important role is played by the patients’ indicators used for prognosis. The current methods of individual prognosis of the course and outcome of CCT, in most cases, require additional surveys, built on the basis of a large number of clinical, neurological and laboratory indicators. If the prognosis is based on new or additional indices that are not standard and are not included in the protocol for managing a patient with CCT, then its use will be complicated, because it requires special equipment, additional financing of the medical diagnostic process by public funds or relatives of the injured. The most valuable prognosis is the one which is based on the traditional indicators defined in each patient with CCT during hospitalization according to the diagnosis and treatment standard. The purpose of the study is to develop a model for predicting the course and outcome of a severe isolated craniocerebral trauma using fuzzy logic. The results of a standard survey of 155 patients with severe isolated CCT were used for synthesis of the experimental model. 126 patients out of all were favorable and 29 with the fatal outcome of the disease. As a result of many years of research, it was found out that the result of CCT significantly affects the nature of brain damage and the localization of the pathological substrate. Accordingly, the patients were divided into groups with the most similar traumatic brain damage. The grouping of patients was performed according to the parameters of localization of the injury point (frontal lobe, temporal fate, anterolateral fossa, occipital lobe) using the fuzzy clustering method and the fuzzy c-median algorithm. Preliminary data analysis showed that some patients had multiple brain lesions, the number of possible combinations was equal to sixteen. The use of the clustering method allowed dividing patients into subgroups with the most similar characteristics of brain damage. Patients with a Glasgow coma score of less than 5 or more than 13 were excluded from the study group. In the first case, all patients had a CCT fatal result; in the second case it was favorable. For the construction of models for the course prognosis and the results of CCT with using fuzzy logic, the most informative were: localization of the pathological substrate, Glasgow coma scale score and DRS scale, indicators of vital functions (heart rate and respiratory movements). The developed prognosis model is based on a two-stage algorithm. At the first stage, patients are divided into clusters according to the pathological substrate localization parameters. At the second stage, the results of CCT are predicted using the model results of the disease developed separately for each cluster, indicators of scales and vital functions.

Keywords: craniocerebral trauma, model of prognosis, fuzzy logic

Full text: PDF (Ukr) 336K

References
  1. Dzyak LA, Zozulya OA. Poetapnaya model prognoza iskhodov tyazheloy cherepno-mozgovoy travmy. Meditsina neotlozhnykh sostoyaniy. 2016; 4: 79-83. [Russian]
  2. Elskiy VN, Zyablitsev SV, Pishchulina SV, Kishenya MS, Kolesnikova SV. Ispolzovanie matematicheskikh metodov modelirovaniya v issledovanii patogeneza travmaticheskoy bolezni. Patologiya. 2008; 5 (3): 35. [Russian]
  3. Elskiy VN, Zyablitsev SV. Modelirovanie cherepno-mozgovoy travmy. Donetsk: Izd-vo «Novyy mir», 2008. 140 s. [Russian]
  4. Zhitinkina NV. Tyazhelaya cherepno-mozgovaya travma u detey (optimizatsiya intensivnoy terapii, prognozirovanie iskhodov): avtoref. dis. … kand. med. nauk, Abstr. PhDr. (Med.). Ekaterinburg; 2006. 17 s. [Russian]
  5. Zozulya OO. Prognostichni kriteriyi perebigu ta vikhodiv tyazhkoyi cherepno-mozkovoyi travmi (kliniko-biokhimichne doslidzhennya): avtoref. dis. … kand. med. nauk, Abstr. PhDr. (Med.). Kharkiv; 2005. 21 s. [Ukrainian]
  6. Klimash AV. Sovershenstvovanie sistemy diagnostiki, lecheniya i prognozirovaniya iskhodov u bolnykh s tyazheloy cherepno-mozgovoy travmoy (kliniko-eksperimentalnoe issledovanie): avtoref. dis. … doktora med. nauk, Abstr. Dr. Sci. (Med.). Sankt-Peterburg; 2011. 44 s. [Russian]
  7. Klinicheskaya nevrologiya s osnovami mediko-sotsialnoy ekspertizy. [ruk-vo dlya vrachey]. Ed AYu Ma¬karov. SPb, 1998. 602 s. [Russian]
  8. Pedachenko EG, Semisalov SYa, Elskiy VN, Kardash AM. Klinicheskaya epidemiologiya cherepno-mozgovoy travmy. Donetsk: Apeks, 2002. 156 s. [Russian]
  9. Konovalov AN, Likhterman LB, Potapov AA, i dr. Klinicheskoe rukovodstvo po cherepno-mozgovoy trav¬me. M: Antidor, 2002. Vol 1: 550 s. [Russian]
  10. Kobzar AI. Prikladnaya matematicheskaya statistika. Moskva: Fizmatlit, 2006. 816 s. [Russian]
  11. Kuzminov SU. Prognozirovanie iskhoda khirurgicheskogo lecheniya tyazheloy izolirovannoy i sochetannoy cherepno-mozgovoy travmy: avtoref. dis. … kand. med. nauk, Abstr. PhDr. (Med.). Ryazan; 2003. 17 s. [Russian]
  12. Leonenkov AV. Nechetkoe modelirovanie v srede MATLAB i fuzzyTECH./BKhV-Peterburg. SPb; 2005. 736 s. [Russian]
  13. Lekhan VM, Guk AP. Osoblivosti epidemiologiyi cherepno-mozkovoyi travmi v Ukrayini. Ukrayina. Zdorov'ya natsiyi. 2010; 2 (14): 7-14. [Ukrainian]
  14. Likhterman LB, Kornienko VN, Potapov AA. Cherepno-mozgovaya travma: prognoz techeniya i iskhodov. M: Kniga, 1992. 320 s. [Russian]
  15. Runion RP. Spravochnik po neparametricheskoy statistike: sovremennyy podkhod. Per. s angl. EZ Demidenko. Moskva: Finansy i statistika, 1982. 198 s. [Russian]
  16. Semenov AV. Dogospitalnaya diagnostika i prognozirovanie iskhodov sochetannoy cherepno-mozgovoy travmy. Neyrokhirurgiya. 2007; 56-9. [Russian]
  17. Semisalov SYa. Matematicheskoe modelirovanie razvitiya ostrogo cherepno-mozgovogo travmatizma gorodskogo naseleniya s pomoshchyu iskusstvennogo neyrosetevogo programmirovaniya. Ukrayinskiy neyrokhirurgichniy zhurnal. 2001; 4: 108-11. [Russian]
  18. Sumin SA. Neotlozhnye sostoyaniya. M: Izd-vo MIA, 2010. 960 s. [Russian]
  19. Troshin LI, Balash VA, Balash OS. Statisticheskiy analiz nechislovoy informatsii. Moskovskiy gosudarstvennyy universitet ekonomiki, statistiki i informatiki. Moskva; 2001. 67 s. [Russian]
  20. Cherepno-mozgovaya travma [digital resource]. Available from: http://ilive.com.ua/health/cherepno-mozgovayatravma_108127i15958.html [Russian]
  21. Potapov AA, Roshal LM, Likhterman LB, Krav¬chuk AD. Cherepno-mozgovaya travma: problemy i perspektivy. Voprosy neyrokhirurgii. 2009; 2: 3-8. [Russian]
  22. Shtovba SD. Proektirovanie nechetkikh sistem sredstvami MATLAB./Goryachaya liniya –Telekom. M; 2007. 288 s. [Russian]
  23. Khobzey NK, Pedachenko EG, Golik VA, Guk AP, i dr. Epidemiologiya invalidnosti vsledstvii cherepno-mozgovoy travmy v Ukraine. Ukrayina. Zdorov’ya natsiyi. 2011; 3 (19): 30-4. [Russian]
  24. Maas AI, Marmarou A, Murray GD, Teasdale SG, Steyerberg EW. Prognosis and clinical trial design in traumatic brain injury: the IMPACT study. J Neurotrauma. 2007 Feb; 24 (2): 232-8. https://www.ncbi.nlm.nih.gov/pubmed/17375987. https://doi.org/10.1089/neu.2006.0024
  25. Olesen J, Baker M, Freud T, di Luca M, Mendlewicz J, Ragan I, Westphal M. Consensus document on European brain research. J Neurol Neurosurg Psychiatry. 2006; 77 (suppl 1): i1-i49. https://www.ncbi.nlm.nih.gov/pmc/articles/3284269
  26. Andlin-Sobocki P, Jonsson B, Wittchen H-U, Olesen J. Costs of disorders of the brain in Europe. Europ J Neurol. 2005; 12 (suppl 1): 1-27. https://www.ncbi.nlm.nih.gov/pubmed/15877774. https://doi.org/10.1111/j.1468-1331.2005.01202.x
  27. Fuzzy Logic Toolbox [digital resource]. Available from: http://atoms.scilab.org/toolboxes/sciFLT/0.4.7
  28. Guler I, Gokcil Z, Gulbandilar E. Evaluation of traumatic brain injuries using artificsal neural networks. Expert Systems with Applications. 2009; 36 (7): 10424-7. https://doi.org/10.1016/j.eswa.2009.01.036
  29. Guler I, Tunca A, Gulbandilar E. Detection of traumatic brain injuries using fuzzy logic algorithm. Expert Systems with Applications. 2008; 34 (2): 1312-7. https://doi.org/10.1016/j.eswa.2006.12.009
  30. Lippert-Grüner M, Maegele M, Haverkamp H, Klug N, Wedekind Ch. Health - related quality of life during the first year after severe brain trauma with and without polytrauma. Brain Inj. 2007; 21 (5): 451-5. https://doi.org/10.1080/02699050701343961
  31. Nasser R, Jallo J. International Neurotrauma. Neurotrauma and Critical Care. 2007: 1- 6.
  32. Open source software for numerical computation [digital resource]. Available from: http://www.scilab.org/