USING NEURAL NETWORK MODELING TO PREDICT THE COURSE OF ACUTE PANCREATITIS
https://doi.org/10.38181/2223-2427-2021-4-23-32
Abstract
The database of studies of 82 patients with acute pancreatitis are presented. Using neural network analysis, the most indicative parameters for predicting acute pancreatitis were revealed: indexes of Kalf-Kalif intoxication modified by Kostyuchenko and Khomich, Reis, Garkavi, the ratio of leukocytes to ESR, leukocyte index, general intoxication index; sonographic parameters – the size of the head of the pancreas, the diameter of the splenic vein, the presence of free fluid in the abdominal cavity; biochemical parameters – blood amylase concentration, urine diastase. When conducting clustering in a multidimensional feature space, a Kohonen neural network was created. All analyzed objects were effectively divided into 3 clusters. The most severe and prognostically unfavorable is cluster 1, which included data from 30 patients, with the maximum mortality rate and maximum hospital stay.
About the Authors
I. K. YelskyiUkraine
Ivan K. Yelskyi – assistant of the Surgery and Endoscopy Department
Ilyicha Avenue, 16, 83003, Donetsk, Donetsk People's Republic
A. A. Vasylyev
Ukraine
Alexander A. Vasylyev – PhD in Medicine, Head of the Department of Surgery and Endoscopy
Ilyicha Avenue, 16, 83003, Donetsk, Donetsk People's Republic
N. L. Smirnov
Ukraine
Nikolay L. Smirnov – PhD in Medicine, docent of the Surgery and Endoscopy Department
Ilyicha Avenue, 16, 83003, Donetsk, Donetsk People's Republic
References
1. Munigala S, Yadav D. Case-fatality from acute pancreatitis is decreasing but its population mortality shows little change. Pancreatology. 2016; 16(4): 542-550. http://doi.org/10.1016/j.pan.2016.04.008
2. Kurti F, Shpata V, Kuqo A, Duni A, Roshi E, Basho J. Incidence of acute pancreatitis in Albanian population. Mater Sociomed. 2015; 27(6): 376-369. http://doi.org/10.5455/msm.2015.27.376-379
3. El'skij I.K., Vasil'ev A.A., Smirnov N.L. Jeffektivnost' prognosticheskih shkal v stratifikacii ostrogo pankreatita. Obzor literatury. Hirurgicheskaja praktika. 2020; 3(43); 17-28. (In Russ.). https://doi.org/10.38181/2223-2427-2020-3-17-28
4. Karakayali FY. Surgical and interventional management of complications caused by acute pancreatitis. World J Gastroenterol. 2014; 20(37): 412-423. https://doi:10.3748/wjg.v20.i37.13412
5. Podluzhnyj V.I. Ostryj pankreatit: sovremennye predstavlenija ob jetiologii, patogeneze, diagnostike i lechenii. Fundamental'naja i klinicheskaja medicina. 2017; 2(4): 62-71. (In Russ.).
6. Kokosis G, Perez A, Pappas TN. Surgical management of necrotizing pancreatitis: an overview. World J Gastroenterol. 2014; 20(43): 16106-16112. https://doi:10.3748/wjg.v20.i43.16106
7. Borodin NA, Maltceva OV, Gibert BK, Zaitcev EJ. Modern approaches to treatment of destructive forms of pancreatitis, ways to reduce mortality. Medical Science and Education of the Ural. 2015; 2-1(82): 70-73. https://doi:10.23946/2500-0764-2017-2-4-62-71
8. Akimov A.A., Stjazhkina S.N., Valinurov A.A., Varenik E.Ju., Koroljov V.K., Matusevich A.E. Ostryj pankreatit v molodom vozraste. Mediko-farmacevticheskij zhurnal «Pul's». 2018; 20(4): 18-21. (In Russ.).
9. Stjazhkina SN, Protopopov VA, Darovskih AA, Akimov AA. Mortality from acute pancreatitis in Udmurt Republic for the period of 2012-2015. Journal of Scientific Articles Health and Education in the XXI Century. 2017; 19(9): 119-121.
10. Setiawan VW, Pandol SJ, Porcel J, Wilkens LR, Le Marchand L, Pike MC, et al. Prospective Study of Alcohol Drinking, Smoking, and Pancreatitis: The Multiethnic Cohort. Pancreas. 2016; 45(6): 819-825. https://doi:10.1097/MPA.0000000000000657
11. Aleksandrovich Ju.S., Gordeev V.I. Ocenochnye i prognosticheskie shkaly v medicine kriticheskih sostojanij. SPb: Sotis; 2007. (In Russ.).
12. El'skij I.K., Shirshov I.V., Medvedev A.V. Osobennosti ocenki tjazhesti ostrogo nekroticheskogo pankreatita i ih prognosticheskoe znachenie. Vestnik neotlozhnoj i vosstanovitel'noj hirurgii. 2017; 2-3(2): 238-242. (In Russ.).
13. Kaplan M, Ates I, Oztas E, et al. A New Marker to Determine Prognosis of Acute Pancreatitis: PLR and NLR Combination. J Med Biochem. 2018; 37(1): 21-30. http://dx.doi.org/10.1515/jomb-2017-0039
14. Ljah Ju. E. Analiz rezul'tatov medikobiologicheskih issledovanij i klinicheskih ispytanij v specializirovannom statisticheskom pakete MEDSTAT. Vestnik gigieny i jepidemiologii. 2004; 8(1): 155-167. (In Russ.).
15. Speranskij I.I., Samojlenko G.E., Lobacheva M.V. Obshhij analiz krovi – vse li ego vozmozhnosti ischerpany? Integral'nye indeksy intoksikacii kak kriterii ocenki tjazhesti techenija jenndogennoj intoksikacii, ee oslozhnenij i jeffektivnosti provodimogo lechenija. Zdorov'e Ukrainy. 2009; 6(19): 51-57. (In Russ.).
16. Borovikov V. STATISTICA. Iskusstvo analiza dannyh na komp'jutere: Dlja professionalov. 2-e izd. SPb.: Piter; 2003. (In Russ.).
17. Lojd Je., Lederman U., Ajvazjan S.A., Tjurina Ju.N. Spravochnik po prikladnoj statistike. M.: Finansy i statistika; 1990. (In Russ.).
18. Lapach S.N. Statisticheskie metody v mediko-biologicheskih issledovanijah s ispol'zovaniem EXCEL. K.: MORION; 2002. (In Russ.).
19. Shhekotov V.V. Patogenez i klinicheskaja diagnostika sindroma jendogennoj intoksikacii. V kn.: Korjukina I.P. Laboratornaja diagnostika sindroma jendogennoj intoksikacii. Perm': PGMA; 2005: 4-17 (in Russ.)
20. Belozerov I.V. Ocenka jeffektivnosti predoperacionnogo podgotovitel'nogo jetapa u bol'nyh rakom obodochnoj kishki, oslozhnennogo ostroj neprohodimost'ju kishechnika. Harkіvs'ka hіrurgіchna shkola. 2010; 6(44): 6-10. (In Russ.).
21. Gallyamov E.A., Agapov M.A., Lutsevich O.E., Kakotkin V.V. Advanced technologies for treatment of infected pancreatic necrosis: differentiated approach. Annaly khirurgicheskoy gepatologii = Annals of HPB Surgery. 2020;25(1):69-78. (In Russ.) https://doi.org/10.16931/1995-5464.2020169-78
22. Levchenko K.F., Chernobaj G.N. Informativnost' standartnyh paraklinicheskih testov u pacientov s rakom molochnoj zhelezy. Vestnik NGU. Serija: Biologija, klinicheskaja medicina. 2010; 8(1): 15-154. (In Russ.).
23. ЛLjah Ju. E. Obosnovanie vybora optimal'nogo chisla klasterov dlja metoda samoorganizujushhihsja kart Kohonena. Klinicheskaja informatika i telemedicina. 2005; 2(1): 124. (In Russ.). http://dx.doi.org/10.5152/tjg.2017.25041
Review
For citations:
Yelskyi I.K., Vasylyev A.A., Smirnov N.L. USING NEURAL NETWORK MODELING TO PREDICT THE COURSE OF ACUTE PANCREATITIS. Surgical practice (Russia). 2021;(4):23-32. (In Russ.) https://doi.org/10.38181/2223-2427-2021-4-23-32