Akut Pankreatitte Prognoz ve Mortalite Tahmini için Yapay Zeka Destekli Skorlama Sistemi

Yıl 2026, Cilt: 7 Sayı: 1, 70 - 80, 31.01.2026

İbrahim Çaltekin , Ali Aygun , Adem Köksal , Mehmet Seyfettin Sarıbaş , Hilal Altaş , Mehmet Ali Ata , Mesut Tomakin , Furkan Elmas

https://doi.org/10.47482/acmr.1672726

Öz

Amaç: Bu çalışmada, akut pankreatitli (AP) hastalarda hastalık şiddetini ve hastane içi mortaliteyi öngörmede yeni bir yapay zeka tabanlı skorlama sistemi olan Pankreatit Yapay Zeka (PanAI) skorunun prognostik değerini değerlendirmeyi amaçladık.
Yöntemler: Çalışmaya 01.01.2023-01.01.2024 tarihleri arasında AP tanısıyla acil servise başvuran 76 hasta dahil edildi. Hastaların klinik ve laboratuvar verileri retrospektif olarak analiz edildi. PanAI skoru, Ranson skoru, 48. saat Ranson skoru ve Balthazar CTSI skorları hesaplandı ve bunların hastalık şiddeti ve hastane içi mortalite ile ilişkileri değerlendirildi. Model performansı ROC analizi ile karşılaştırıldı.
Bulgular: Çalışmaya dahil edilen hastaların yaş ortalaması 61.95±17.40 idi ve hastaların %44.2'si ağır AP grubunda sınıflandırıldı. Hastane içi mortalite oranı %13.2 idi. PanAI skoru, şiddetli AP ve hastane içi mortaliteyi öngörmede diğer skorlardan daha doğruydu (AUC=0.911). Lojistik regresyon analizinde, PanAI skoru şiddetli AP ve mortalitenin bağımsız bir belirleyicisi olarak bulundu (p<0.001).
Sonuç: PanAI skoru, AP hastalarında hastalık şiddeti ve mortalite riskini öngörmede güçlü bir prognostik gösterge olarak öne çıkmaktadır. Geleneksel skorlama sistemlerine kıyasla daha yüksek doğruluğu nedeniyle, klinik karar vermede önemli bir araç olabilir.

Anahtar Kelimeler

Akut Pankreatit , Mortalite , Risk Sınıflandırması , Şiddet Değerlendirmesi , PanAI Skoru

Artificial Intelligence Assisted Scoring System for Prognosis and Mortality Prediction in Acute Pancreatitis

Öz

Background: In this study, we aimed to evaluate the prognostic value of the Pancreatitis Artificial Intelligence (PanAI) score, a new AI-based scoring system, in predicting disease severity and in-hospital mortality in patients with acute pancreatitis (AP).
Methods: The study included 76 patients admitted to the emergency department with a diagnosis of AP between 01.01.2023 - 01.01.2024. Clinical and laboratory data of the patients were analyzed retrospectively. PanAI score, Ranson score, 48th hour Ranson score and Balthazar Computed Tomography Severity Index (CTSI) scores were calculated and their relationships with disease severity and in-hospital mortality were evaluated. Model performance was compared by ROC analysis.
Results: The mean age of the patients included in the study was 61.95±17.40 years and 44.2% of the patients were classified in the severe AP group. In-hospital mortality rate was 13.2%. The PanAI score was more accurate than other scores in predicting severe AP and in-hospital mortality (AUC=0.911). In logistic regression analysis, PanAI score was found to be an independent predictor of severe AP and mortality (p<0.001).
Conclusion: The PanAI score stands out as a strong prognostic indicator in predicting disease severity and mortality risk in AP patients. Due to its higher accuracy compared to traditional scoring systems, it can be an important tool in clinical decision-making.

Anahtar Kelimeler

Acute Pancreatitis , Mortality , Risk Classification , Severity Assessment , PanAI Score

Etik Beyan

This study was approved by Ordu University Clinical Research Ethics Committee. Decision No: 2024/59.

Destekleyen Kurum

This research received no external funding.

Teşekkür

The PanAI scoring system presented in this study was developed with the support of the Claude 3.7 Sonnet artificial intelligence model, which was utilized for scoring algorithm generation. The authors also used DeepL as a language assistance tool during the English editing process. We would like to thank Alesta Translation for their assistance in the language review of the manuscript. All authors have read and approved the final version of the article.

Kaynakça

• Xiao AY, Tan ML, Wu LM, Asrani VM, Windsor JA, Yadav D, et al. Global incidence and mortality of pancreatic diseases: a systematic review, meta-analysis, and meta-regression of population-based cohort studies. Lancet Gastroenterol Hepatol. 2016;1(1):45–55. doi:10.1016/S2468-1253(16)30004-8.
• Cohen SM, Kent TS. Etiology, diagnosis, and modern management of chronic pancreatitis: a systematic review. JAMA Surg. 2023;158(6):652–61. doi:10.1001/jamasurg.2023.0367.
• Szatmary P, Grammatikopoulos T, Cai W, Huang W, Mukherjee R, Halloran C, et al. Acute pancreatitis: diagnosis and treatment. Drugs. 2022;82(12):1251–76. doi:10.1007/s40265-022-01766-4.
• Zerem E, Kurtcehajic A, Kunosić S, Malkočević DZ, Zerem O. Current trends in acute pancreatitis: diagnostic and therapeutic challenges. World J Gastroenterol. 2023;29(18):2747–63. doi:10.3748/wjg.v29.i18.2747.
• Cho JH, Kim TN, Chung HH, Kim KH. Comparison of scoring systems in predicting the severity of acute pancreatitis. World J Gastroenterol. 2015;21(8):2387–94. doi:10.3748/wjg.v21.i8.2387.
• Bradley EL III. A clinically based classification system for acute pancreatitis. Arch Surg. 1993;128(5):586–90. doi:10.1001/archsurg.1993.01420170122019.
• Banks PA, Bollen TL, Dervenis C, Gooszen HG, Johnson CD, Sarr MG, et al. Classification of acute pancreatitis–2012: revision of the Atlanta classification and definitions by international consensus. Gut. 2013;62(1):102–11. doi:10.1136/gutjnl-2012-302779.
• Ranson JH, Rifkind KM, Roses DF, Fink SD, Eng K, Localio SA. Objective early identification of severe acute pancreatitis. Am J Gastroenterol. 1974;61(6):443–51.
• Larvin M, McMahon MJ. APACHE-II score for assessment and monitoring of acute pancreatitis. Lancet. 1989;2(8656):201–5. doi:10.1016/s0140-6736(89)90381-4.
• Balthazar EJ, Robinson DL, Megibow AJ, Ranson JH. Acute pancreatitis: value of CT in establishing prognosis. Radiology. 1990;174(2):331–6. doi:10.1148/radiology.174.2.2296641.
• Papachristou GI, Muddana V, Yadav D, O’Connell M, Sanders MK, Slivka A, et al. Comparison of BISAP, Ranson’s, APACHE-II, and CTSI scores in predicting organ failure, complications, and mortality in acute pancreatitis. Am J Gastroenterol. 2010;105(2):435–41. doi:10.1038/ajg.2009.622.
• Tran A, Fernando SM, Rochwerg B, Inaba K, Bertens KA, Engels PT, et al. Prognostic factors associated with development of infected necrosis in acute necrotizing or severe pancreatitis: a systematic review and meta-analysis. J Trauma Acute Care Surg. 2022;92(5):940–8. doi:10.1097/TA.0000000000003502.
• Ding L, Chen HY, Wang JY, Xiong HF, He WH, Xia L, et al. Severity of acute gastrointestinal injury grade is a good predictor of mortality in critically ill patients with acute pancreatitis. World J Gastroenterol. 2020;26(5):514–23. doi:10.3748/wjg.v26.i5.514.
• Li P, Shi L, Yan X, Wang L, Wan D, Zhang Z, et al. Albumin corrected anion gap and the risk of in-hospital mortality in patients with acute pancreatitis: a retrospective cohort study. J Inflamm Res. 2023;16:2415–22. doi:10.2147/JIR.S412860.
• Kiyak M, Tanoglu A. Comparison of the efficacy of Balthazar score and C-reactive protein-albumin ratio for determination of acute pancreatitis severity. Curr Health Sci J. 2022;48(1):81–7. doi:10.12865/CHSJ.48.01.12.
• Mumin A, Abdullah M, Amin A, Al Amin A, Shahriar Kabir AKM, Noor RA, et al. Role of C-reactive protein (CRP) and neutrophil lymphocyte ratio (NLR) in detecting severity & predicting outcome of acute pancreatitis patients. Dinkum J Med Innov. 2024;3(1):1–12.
• Wang C, Zhang J, Liu L, Qin W, Luo N. Early predictive value of presepsin for secondary sepsis and mortality in intensive care unit patients with severe acute pancreatitis. Shock. 2023;59(4):560–8. doi:10.1097/SHK.0000000000002088.
• Kırmızı S, Doğan S, Edizer A, Yeniyurt B, Kalafat UM. Does the percentage of immature granulocytes predict the severity and mortality of the disease in patients with acute pancreatitis presenting to the emergency department? Glob Emerg Crit Care. 2022;1(3):76–82.
• Omair U, Azmat U, Rakhshani AQ. Diagnostic accuracy of computed tomography scoring index in predicting mortality among suspected patients of acute pancreatitis. Int J Endors Health Sci Res. 2021;9(2):201–5.
• Silva Vaz P, Abrantes AM, Castelo Branco M, Gouveia A, Botelho MF, Tralhão JG. Multifactorial scores and biomarkers of prognosis of acute pancreatitis: applications to research and practice. Int J Mol Sci. 2020;21(1):338. doi:10.3390/ijms21010338.
• Wu BU, Johannes RS, Sun X, Tabak Y, Conwell DL, Banks PA. The early prediction of mortality in acute pancreatitis: a large population-based study. Gut. 2008;57(12):1698–703. doi:10.1136/gut.2008.152702.
• Lu CX, Zhou J, Feng YC, Meng SJ, Guo XL, Su WS, et al. Artificial intelligence models assisting physicians in quantifying pancreatic necrosis in acute pancreatitis. Quant Imaging Med Surg. 2025;15(1):135–48. doi:10.21037/qims-24-841.
• Hu JX, Zhao CF, Wang SL, Tu XY, Huang WB, Chen JN, et al. Acute pancreatitis: a review of diagnosis, severity prediction and prognosis assessment from imaging technology, scoring system and artificial intelligence. World J Gastroenterol. 2023;29(37):5268–91. doi:10.3748/wjg.v29.i37.5268.
• Anderson K, Shah I, Yakah W, Cartelle AL, Zuberi SA, McHenry N, et al. Prospective evaluation of an emergency department protocol to prevent hospitalization in mild acute pancreatitis: outcomes and predictors of discharge. Pancreatology. 2023;23(3):299–305. doi:10.1016/j.pan.2023.02.006.
• Kui B, Pintér J, Molontay R, Nagy M, Farkas N, Gede N, et al. EASYAPP: an artificial intelligence model and application for early and easy prediction of severity in acute pancreatitis. Clin Transl Med. 2022;12(6):e842. doi:10.1002/ctm2.842.
• Tarján D, Hegyi P. Acute pancreatitis severity prediction: it is time to use artificial intelligence. J Clin Med. 2022;12(1):290. doi:10.3390/jcm12010290.
• Kiss S, Pintér J, Molontay R, Nagy M, Farkas N, Sipos Z, et al. Early prediction of acute necrotizing pancreatitis by artificial intelligence: a prospective cohort-analysis of 2387 cases. Sci Rep. 2022;12(1):7827. doi:10.1038/s41598-022-11517-w.
• Keogan MT, Lo JY, Freed KS, Raptopoulos V, Blake S, Kamel IR, et al. Outcome analysis of patients with acute pancreatitis by using an artificial neural network. Acad Radiol. 2002;9(4):410–9. doi:10.1016/s1076-6332(03)80186-1.
• Pearce CB, Gunn SR, Ahmed A, Johnson CD. Machine learning can improve prediction of severity in acute pancreatitis using admission values of APACHE II score and C-reactive protein. Pancreatology. 2006;6(1–2):123–31. doi:10.1159/000090032.
• Andersson B, Andersson R, Ohlsson M, Nilsson J. Prediction of severe acute pancreatitis at admission to hospital using artificial neural networks. Pancreatology. 2011;11(3):328–35. doi:10.1159/000327903.