Preview

Annaly khirurgicheskoy gepatologii = Annals of HPB Surgery

Advanced search

Using an artificial neural network to predict biliary fistula after pancreaticoduodenal resection

https://doi.org/10.16931/1/1995-5464.2024-3-108-115

Abstract

Aim. To determine the risk factors of biliary fistula after pancreaticoduodenal resection.

Materials and methods. 128 pancreaticoduodenal resections were performed in the period of 2018–2023. Biliary fistula was predicted using a neural network and logistic regression. Prediction accuracy was evaluated by ROC analysis (Receiver Operator Characteristics). The DeLong test was used to compare ROC curves.

Results. Biliary fistula developed in 16 patients (12.5%). Univariate analysis showed that risk factors of biliary fistula included the patient's age >70 years, Charlson comorbidity index >7 points, diabetes mellitus, postsurgical anemia, common bile duct diameter <5 mm, and pancreatic fistula. In multivariate analysis, diabetes mellitus, common bile duct diameter <5 mm, and anemia after pancreaticoduodenal resection increased the risk of biliary fistula. A prognostic multivariate model of biliary fistula development, constructed using an artificial neural network demonstrated higher sensitivity (87.5%) and specificity (95.5%) compared to the logistic regression model (68.8% and 90.2%; p = 0.03).

Conclusion. The use of neural networks in predictive analysis of pancreaticoduodenal resection results can increase the efficiency of biliary fistula prediction.

About the Authors

V. A. Suvorov
Volgograd State Medical University
Russian Federation

Vladimir A. Suvorov – Cand. of Sci. (Med.), Assistant, Department of Oncology

1, Pavshikh Bortsov Sq., Volgograd, 400131



S. I. Panin
Volgograd State Medical University
Russian Federation

Stanislav I. Panin – Doct. of Sci. (Med.), Professor, Head of the Department of General Surgery

1, Pavshikh Bortsov Sq., Volgograd, 400131



N. V. Kovalenko
Volgograd State Medical University
Russian Federation

Nadezhda V. Kovalenko – Cand. of Sci. (Med.), Associate Professor, Head of the Department of Oncology, Hematology and Transplantology of the Continued Medical and Pharmaceutical Education Institute

1, Pavshikh Bortsov Sq., Volgograd, 400131



V. V. Zhavoronkova
Volgograd State Medical University
Russian Federation

Victoriya V. Zhavoronkova – Cand. of Sci. (Med.), Associate Professor, Head of the Department of Oncology

1, Pavshikh Bortsov Sq., Volgograd, 400131



M. P. Postolov
Volgograd State Medical University
Russian Federation

Mikhail P. Postolov – Cand. of Sci. (Med.), Assistant, Department of Oncology

1, Pavshikh Bortsov Sq., Volgograd, 400131



D. V. Linchenko
Volgograd State Medical University
Russian Federation

Diana V. Linchenko – Cand. of Sci. (Med.), Associate Professor, Department of General Surgery

1, Pavshikh Bortsov Sq., Volgograd, 400131



A. V. Panova
Volgograd State Medical University
Russian Federation

Alina V. Panova – Clinical Resident, Department of Oncology

1, Pavshikh Bortsov Sq., Volgograd, 400131



A. S. Voronina
Volgograd State Medical University
Russian Federation

Alyona S. Voronina – 5th year student, Faculty of General Medicine

1, Pavshikh Bortsov Sq., Volgograd, 400131



References

1. Vetshev P.S., Chzhao A.V., Ionkin D.A., Stepanova Yu.A., Zhavoronkova O.I., Kulezneva Yu.V., Melekhina O.V., Panchenkov D.N., Astakhov D.A., Ivanov Yu.V., Bruslik S.V., Sviridova T.I. Minimally invasive technologies for ablation of pancreatic malignancies. Annaly khirurgicheskoy gepatologii = Annals of HPB surgery. 2019; 24 (3): 87–98. (In Russian) http://doi.org/10.16931/1995-5464.2019387-98

2. Shabunin A.V., Bedin V.V., Tavobilov M.M., Karpov A.A., Karalkin A.V., Vasilenko E.I., Abramov K.A., Lantsynova A.V. Determination of the optimal reconstruction for pancreaticoduodenal resection based on modified scintigraphy of gastrointestinal motility. Annaly khirurgicheskoy gepatologii = Annals of HPB surgery. 2023; 28 (3): 48–55. (In Russian) https://doi.org/10.16931/1995-5464.2023-3-48-55.http://doi.org/

3. Gorin DS, Kriger AG, Galkin GV, Kalinin DV, Glotov AV, Kaldarov AR, Galchina YuS, Berelavichus SV. Predicting of pancreatic fistula after pancreatoduodenectomy. Pirogov Russian Journal of Surgery = Khirurgiya. Zurnal im. N.I. Pirogova. 2020;7:61-67. (In Russ.). https://doi.org/10.17116/hirurgia202007161

4. Patyutko Yu.I., Kotelnikov A.G.*, Polyakov A.N., Podluzhnyi D.V. Evolution of surgery for pancreatic head and periampullary cancer. Annaly khirurgicheskoy gepatologii = Annals of HPB surgery. 2019; 24 (3): 45–53. (In Russian). http://doi.org/10.16931/1995-5464.2019345-53

5. Kabanov M.Yu., Glushkov N.I., Semencov K.V., Koshelev T.E., Savchenkov D.K., Sizonenko N.A., Goloshchapova I.M. Modern approaches to the prevention and treatment of postoperative complications in pancreatic head cancer. Bulletin of Pirogov National Medical & Surgical center. 18 (2), 128-133. https://doi.org/10.25881/20728255_2023_18_2_128

6. Rayn V.Yu. Biliary Fistula after Pancreaticoduodenectomy. Novosti Khirurgii. 2022; 30 (1): 95-101. https://doi.org/10.16931/1995-5464.2023-3-48-55

7. Kozlov I.A., Baydarova M.D., Shevchenko T.V., Ikramov R.Z., Zharikov Yu.O. Duodenum-preserving total pancreatic head resection. Early postoperative outcomes. Annaly khirurgicheskoy gepatologii = Annals of HPB Surgery. 2020;25(4):107-117. (In Russ.) https://doi.org/10.16931/1995-5464.20204107-117

8. Suvorov V.A., Panin S.I., Kovalenko N.V., Zhavoronkova V.V., Postolov M.P., Tolstopyatov S.E., Bublikov A.E., Panova A.V., Popova V.O. Prediction of pancreatic fistula after pancreatoduodenectomy using machine learning. Siberian Journal of Oncology. 2023; 22(6): 25–34. https://doi.org/10.21294/1814-4861-2023-22-6-25-34

9. Birgin E, Tesfazgi W, Knoth M, Wilhelm TJ, Post S, Rückert F. Evaluation of the new isgls definitions of typical posthepatectomy complications. Scand J Surg. 2019 Jun;108(2):130-36. http://doi.org/10.1177/1457496918798202

10. El Nakeeb A, El Sorogy M, Hamed H, Said R, Elrefai M, Ezzat H, Askar W, Elsabbagh AM. Biliary leakage following pancreaticoduodenectomy: Prevalence, risk factors and management. Hepatobiliary Pancreat Dis Int. 2019 Feb;18(1):67-72. https://doi.org/10.1016/j.hbpd.2018.10.005

11. Perri G, Bortolato C, Marchegiani G, Holmberg M, Romandini E, Sturesson C, Bassi C, Sparrelid E, Ghorbani P, Salvia R. Pure biliary leak vs. pancreatic fistula associated: non-identical twins following pancreatoduodenectomy. HPB (Oxford). 2022 Sep;24(9):1474-1481. https://doi.org/10.1016/j.hpb.2022.03.001

12. Andrianello S, Marchegiani G, Malleo G, Pollini T, Bonamini D, Salvia R, Bassi C, Landoni L. Biliary fistula after pancreaticoduodenectomy: data from 1618 consecutive pancreaticoduodenectomies. HPB (Oxford). 2017 Mar;19(3):264-269. https://doi.org/10.1016/j.hpb.2016.11.011

13. Maatman TK, Loncharich AJ, Flick KF, Simpson RE, Ceppa EP, Nakeeb A, Nguyen TK, Schmidt CM, Zyromski NJ, House MG. Transient Biliary Fistula After Pancreatoduodenectomy Increases Risk of Biliary Anastomotic Stricture. J Gastrointest Surg. 2021 Jan;25(1):169-177. https://doi.org/10.1007/s11605-020-04727-y

14. Farooqui W, Penninga L, Burgdorf SK, Storkholm JH, Hansen CP. Biliary Leakage Following Pancreatoduodenectomy: Experience from a High-Volume Center. J Pancreat Cancer. 2021 Dec 24;7(1):80-85. https://doi.org/10.1089/pancan.2021.0014

15. Wang R, Jiang P, Chen Q, Liu S, Jia F, Liu Y. Pancreatic fistula and biliary fistula after laparoscopic pancreatoduodenectomy: 500 patients at a single institution. J Minim Access Surg. 2023 Jan-Mar;19(1):28-34. https://doi.org/10.4103/jmas.jmas_336_21

16. Melnikov P.V., Dovedov V.N., Kanner D.Yu., Chernikovskiy I.L. Artificial intelligence in surgical practice. Tazovaya Khirurgiua I Oncologiya = Pelvic Surgery and Oncology. 2020;10(3-4):60-64 (In Russ.). https://doi.org/10.17650/2686-9594-2020-10-3-4-60-64.

17. Golubkov A.V., Gavrilova M.P. Application of artifi cial neural networks in preventive and clinical medicine (review). Preventive and clinical medicine. 2020.4 (77):30–39 (in Russian) https://doi.org/10.47843/2074-9120_2020_4_30

18. Ingwersen EW, Stam WT, Meijs BJV, Roor J, Besselink MG, Groot Koerkamp B, de Hingh IHJT, van Santvoort HC, Stommel MWJ, Daams F; Dutch Pancreatic Cancer Group. Machine learning versus logistic regression for the prediction of complications after pancreatoduodenectomy. Surgery. 2023 Sep;174(3):435-440. doi: 10.1016/j.surg.2023.03.012.

19. Yoon SJ, Kwon W, Lee OJ, Jung JH, Shin YC, Lim CS, Kim H, Jang JY, Shin SH, Heo JS, Han IW. External validation of risk prediction platforms for pancreatic fistula after pancreatoduodenectomy using nomograms and artificial intelligence. Ann Surg Treat Res. 2022; 102(3):147-152. https://doi.org/10.4174/astr.2022.102.3.147.

20. Singh G. Artificial intelligence in colorectal cancer: a review. Siberian journal of oncology. 2023;22(3):99-107. https://doi.org/10.21294/1814-4861-2023-22-3-99-107

21.


Supplementary files

Review

For citations:


Suvorov V.A., Panin S.I., Kovalenko N.V., Zhavoronkova V.V., Postolov M.P., Linchenko D.V., Panova A.V., Voronina A.S. Using an artificial neural network to predict biliary fistula after pancreaticoduodenal resection. Annaly khirurgicheskoy gepatologii = Annals of HPB Surgery. 2024;29(3):108-115. (In Russ.) https://doi.org/10.16931/1/1995-5464.2024-3-108-115

Views: 209


Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.


ISSN 1995-5464 (Print)
ISSN 2408-9524 (Online)