Analysis of Prognostic Factors for Mortality in Patients With Gastrointestinal Bleeding: Application of Machine Learning Tools
https://doi.org/10.35401/2541-9897-2024-9-4-68-76
Abstract
Introduction: Treatment of upper gastrointestinal bleeding (UGIB) is a complex challenge due to the wide range of causes and factors affecting hospitalization outcomes.
Objective: To study the impact of various factors on 30-day hospital outcomes using machine learning (ML) tools.
Materials and methods: We compiled a retrospective data set that includes clinical, laboratory, and imaging data of 101 patients. The database was divided into 2 groups by UGIB etiology: ulcer and variceal bleedings. Both etiological groups were processed using ML tools in 2 steps: imputation by the MICE (multiple imputation by chained equations) model and factor importance analysis using the Random Forest model.
Results: Analysis revealed that the most prognostically valuable parameters in both groups were well-known mortality predictors and emerging predictive factors, such as creatinine, blood pressure, activated partial thromboplastin time, level of consciousness, urea, lactate, comorbidity status, procalcitonin, ferritin, and total protein.
Conclusions: The application of advanced tools confirmed the significance of popular and validated mortality predictors and contributed to the development of predictors, both explored and unexplored ones.
About the Authors
A. O. IsmatiUzbekistan
Amir O. Ismati - Basic Doctoral Student, Assistant Professor at the Department of Surgical Diseases, Samarkand State Medical University.
Samarkand
V. D. Anosov
Russian Federation
Viktor D. Anosov - Cand. Sci. (Med.), Deputy Chief Physician for Surgical Care, O.M. Filatov City Clinical Hospital No. 15.
Moscow
S. E. Mamarajabov
Uzbekistan
Sobirjon E. Mamarajabov - Dr. Sci. (Med.), Dean of the Faculty of International Education, Head of the Department of Surgical Diseases, Samarkand State Medical University.
Amir Temur ko’chasi, 18, Samarkand, 140100
References
1. Kamboj AK, Hoversten P, Leggett CL. Upper gastrointestinal bleeding: etiologies and management. Mayo Clin Proc. 2019;94(4):697–703. PMID: 30947833. https://doi.org/10.1016/j.mayocp.2019.01.022
2. Antunes C, Tian C, Copelin II EL. Upper gastrointestinal bleeding. In: StatPearls. StatPearls Publishing; 2024. PMID: 29262121.
3. Elsebaey MA, Elashry H, Elbedewy TA, et al. Predictors of in-hospital mortality in a cohort of elderly Egyptian patients with acute upper gastrointestinal bleeding. Medicine (Baltimore). 2018;97(16):e0403. PMID: 29668596. PMCID: PMC5916675. https://doi.org/10.1097/MD.0000000000010403
4. Zeng F, Du L, Ling L. Lactate level as a predictor of outcomes in patients with acute upper gastrointestinal bleeding: a systematic review and meta-analysis. Exp Ther Med. 2024;27(3):113. PMID: 38361514. PMCID: PMC10867736. https://doi.org/10.3892/etm.2024.12401
5. Ungureanu BS, Gheonea DI, Florescu DN, et al. Predicting mortality in patients with nonvariceal upper gastrointestinal bleeding using machine-learning. Front Med (Lausanne). 2023;10:1134835. PMID: 36873879. PMCID: PMC9982090. https://doi.org/10.3389/fmed.2023.1134835
6. Udriștoiu AL, Cazacu IM, Gruionu LG, et al. Real-time computer-aided diagnosis of focal pancreatic masses from endoscopic ultrasound imaging based on a hybrid convolutional and long short-term memory neural network model. PLoS One. 2021;16(6):e0251701. PMID: 34181680. PMCID: PMC8238220. https://doi.org/10.1371/journal.pone.0251701
7. Abbas OM, Khalifa KAE, Makhlouf MM, Osman NF, Abdel Razek WM, Atta AS. Influence of esophageal variceal bleeding on iron status in chronic hepatitis C patients. Eur J Gastroenterol Hepatol. 2020;32(5):616–622. PMID: 31567713. https://doi.org/10.1097/MEG.0000000000001547
8. Oikonomou T, Goulis I, Soulaidopoulos S, et al. High serum ferritin is associated with worse outcome of patients with decompensated cirrhosis. Ann Gastroenterol. 2017;30(2):217–224. PMID: 28243043. PMCID: PMC5320035. https://doi.org/10.20524/aog.2016.0112
9. Yue W, Liu Y, Jiang W, Huang J, Liu J. Prealbumin and D-dimer as prognostic indicators for rebleeding in patients with nonvariceal upper gastrointestinal bleeding. Dig Dis Sci. 2021;66(6):1949– 1956. PMID: 32583220. https://doi.org/10.1007/s10620-020-06420-1
10. Zhuang Y, Xia S, Chen J, et al. Construction of a prediction model for rebleeding in patients with acute upper gastrointestinal bleeding. Eur J Med Res. 2023;28(1):351. PMID: 37715244. PMCID: PMC10502990. https://doi.org/10.1186/s40001-023-01349-3
11. Shingina A, Barkun AN, Razzaghi A, Martel M, Bardou M, Gralnek I; RUGBE Investigators. Systematic review: the presenting international normalised ratio (INR) as a predictor of outcome in patients with upper nonvariceal gastrointestinal bleeding. Aliment Pharmacol Ther. 2011;33(9):1010–1018. PMID: 21385193. https://doi.org/10.1111/j.1365-2036.2011.04618.x
12. Rady HI, Emil A, Samy K, Baher S. Prediction of stress related gastrointestinal bleeding in critically iii children using PRISM III score. Journal of Anesthesia & Critical Care: Open Access. 2014;1(4):00023. https://doi.org/10.15406/jaccoa.2014.01.00023
13. Gulen M, Satar S, Tas A, Avci A, Nazik H, Toptas Firat B. Lactate level predicts mortality in patients with upper gastrointestinal bleeding. Gastroenterol Res Pract. 2019;2019:5048078. PMID: 31781189. PMCID: PMC6855015. https://doi.org/10.1155/2019/5048078
14. Zidan MHS, Zaghloul SG, Seleem WM, Ahmed HS, Gad AI. Bacteremia as a risk factor for variceal upper gastrointestinal tract bleeding in cirrhotic patients: a hospital-based study. Egyptian Liver Journal. 2021;11(1):8. https://doi.org/10.1186/s43066-021-00078-8
15. Tatlıparmak AC, Dikme Ö, Dikme Ö, Topaçoğlu H. Cancer, platelet distribution width, and total protein levels as predictors of rebleeding in upper gastrointestinal bleeding. PeerJ. 2022;10:e14061. PMID: 36128193. PMCID: PMC9482764. https://doi.org/10.7717/peerj.14061
16. Tomizawa M, Shinozaki F, Hasegawa R, et al. Laboratory test variables useful for distinguishing upper from lower gastrointestinal bleeding. World J Gastroenterol. 2015;21(20):6246–6251. PMID: 26034359. PMCID: PMC4445101. https://doi.org/10.3748/wjg.v21.i20.6246
Review
For citations:
Ismati A.O., Anosov V.D., Mamarajabov S.E. Analysis of Prognostic Factors for Mortality in Patients With Gastrointestinal Bleeding: Application of Machine Learning Tools. Innovative Medicine of Kuban. 2024;(4):68-76. (In Russ.) https://doi.org/10.35401/2541-9897-2024-9-4-68-76