. 2022 May 12;12(1):7827.

doi: 10.1038/s41598-022-11517-w.

Early prediction of acute necrotizing pancreatitis by artificial intelligence: a prospective cohort-analysis of 2387 cases

Szabolcs Kiss^{1

2

3}, József Pintér⁴, Roland Molontay^{4

5}, Marcell Nagy⁴, Nelli Farkas^{2

6}, Zoltán Sipos², Péter Fehérvári^{2

7}, László Pecze², Mária Földi^{1

2

3}, Áron Vincze⁸, Tamás Takács⁹, László Czakó⁹, Ferenc Izbéki¹⁰, Adrienn Halász^{1

10}, Eszter Boros¹⁰, József Hamvas¹¹, Márta Varga¹², Artautas Mickevicius¹³, Nándor Faluhelyi¹⁴, Orsolya Farkas¹⁴, Szilárd Váncsa^{2

15}, Rita Nagy^{2

3

15}, Stefania Bunduc^{15

16}, Péter Jenő Hegyi^{15

17}, Katalin Márta^{15

17}, Katalin Borka^{15

18}, Attila Doros^{15

19}, Nóra Hosszúfalusi^{15

20}, László Zubek^{15

21}, Bálint Erőss^{15

17}, Zsolt Molnár^{15

21

22}, Andrea Párniczky^{2

3}, Péter Hegyi^#^{2

15

17}, Andrea Szentesi^#^{23

24}; Hungarian Pancreatic Study Group

Collaborators, Affiliations

Collaborators

Hungarian Pancreatic Study Group:
Szabolcs Kiss, Nelli Farkas, Zoltán Sipos, Péter Fehérvári, László Pecze, Mária Földi, Áron Vincze, Tamás Takács, László Czakó, Ferenc Izbéki, Adrienn Halász, Eszter Boros, József Hamvas, Márta Varga, Artautas Mickevicius, Nándor Faluhelyi, Orsolya Farkas, Szilárd Váncsa, Rita Nagy, Stefania Bunduc, Péter Jenő Hegyi, Katalin Márta, Katalin Borka, Attila Doros, Nóra Hosszúfalusi, László Zubek, Bálint Erőss, Zsolt Molnár, Andrea Párniczky, Péter Hegyi, Andrea Szentesi, Judit Bajor, Szilárd Gódi, Patrícia Sarlós, József Czimmer, Imre Szabó, Gabriella Pár, Anita Illés, Roland Hágendorn, Balázs Csaba Németh, Balázs Kui, Dóra Illés, László Gajdán, Veronika Dunás-Varga, Roland Fejes, Mária Papp, Zsuzsanna Vitális, János Novák, Imola Török, Melania Macarie, Elena Ramírez-Maldonado, Ville Sallinen, Shamil Galeev, Barnabás Bod, Ali Tüzün Ince, Dániel Pécsi, Péter Varjú, Márk Félix Juhász, Klementina Ocskay, Alexandra Mikó, Zsolt Szakács

Affiliations

¹ Doctoral School of Clinical Medicine, Faculty of Medicine, University of Szeged, Szeged, 6720, Hungary.
² Institute for Translational Medicine, Szentágothai Research Centre, Medical School, University of Pécs, Szigeti út 12., II. Emelet, Pécs, 7624, Hungary.
³ Heim Pál National Pediatric Institute, Üllői út 86, Budapest, 1089, Hungary.
⁴ Human and Social Data Science Lab, Budapest University of Technology and Economics, Műegyetem rkp. 3, Budapest, 1111, Hungary.
⁵ Stochastics Research Group, Hungarian Academy of Sciences, Budapest University of Technology and Economics, Egry József u. 1, Budapest, 1111, Hungary.
⁶ Institute of Bioanalysis, Medical School, University of Pécs, Honvéd u. 1, Pécs, 7624, Hungary.
⁷ Department of Biomathematics and Informatics, University of Veterinary Medicine, István u. 2, Budapest, 1078, Hungary.
⁸ Division of Gastroenterology, First Department of Medicine, Medical School, University of Pécs, Ifjúság út 13, Pécs, 7624, Hungary.
⁹ Department of Medicine, University of Szeged, Kálvária sgt. 57, Szeged, 6725, Hungary.
¹⁰ Department of Internal Medicine, Szent György Teaching Hospital of County Fejér, Seregélyesi út 3, Székesfehérvár, 8000, Hungary.
¹¹ Bajcsy-Zsilinszky Hospital, Maglódi út 89-91, Budapest, 1106, Hungary.
¹² Department of Gastroenterology, BMKK Dr Rethy Pal Hospital, Gyulai út 18, Békéscsaba, 5600, Hungary.
¹³ Vilnius University Hospital Santaros Clinics, Clinics of Abdominal Surgery, Nephrourology and Gastroenterology, Faculty of Medicine, Vilnius University, Santariškių g. 2, 08410, Vilnius, Lithuania.
¹⁴ Department of Medical Imaging, Medical School, University of Pécs, Ifjúság út 13, Pécs, 7624, Hungary.
¹⁵ Centre for Translational Medicine, Semmelweis University, Üllői út 26, Budapest, 1085, Hungary.
¹⁶ Doctoral School, Carol Davila University of Medicine and Pharmacy, Bulevardul Eroii Sanitari 8, 050474, Bucharest, Romania.
¹⁷ Division of Pancreatic Diseases, Heart and Vascular Center, Semmelweis University, Baross u. 23, Budapest, 1082, Hungary.
¹⁸ 2nd Department of Pathology, Semmelweis University, Üllői út 93, Budapest, 1091, Hungary.
¹⁹ Department of Transplantation and Surgery, Semmelweis University, Baross u. 23, Budapest, 1082, Hungary.
²⁰ Department of Internal Medicine and Hematology, Semmelweis University, Szentkirályi u. 46, Budapest, 1088, Hungary.
²¹ Department of Anaesthesiology and Intensive Therapy, Semmelweis University, Üllői út 78, Budapest, 1082, Hungary.
²² Department of Anaesthesiology and Intensive Therapy, Poznan University of Medical Sciences, ul. św. Marii Magdaleny 14, 61861, Poznan, Wielkopolska, Poland.
²³ Doctoral School of Clinical Medicine, Faculty of Medicine, University of Szeged, Szeged, 6720, Hungary. szentesiai@gmail.com.
²⁴ Institute for Translational Medicine, Szentágothai Research Centre, Medical School, University of Pécs, Szigeti út 12., II. Emelet, Pécs, 7624, Hungary. szentesiai@gmail.com.

^# Contributed equally.

PMID: 35552440
PMCID: PMC9098474
DOI: 10.1038/s41598-022-11517-w

Early prediction of acute necrotizing pancreatitis by artificial intelligence: a prospective cohort-analysis of 2387 cases

Szabolcs Kiss et al. Sci Rep. 2022.

. 2022 May 12;12(1):7827.

doi: 10.1038/s41598-022-11517-w.

Authors

Collaborators

Hungarian Pancreatic Study Group:
Szabolcs Kiss, Nelli Farkas, Zoltán Sipos, Péter Fehérvári, László Pecze, Mária Földi, Áron Vincze, Tamás Takács, László Czakó, Ferenc Izbéki, Adrienn Halász, Eszter Boros, József Hamvas, Márta Varga, Artautas Mickevicius, Nándor Faluhelyi, Orsolya Farkas, Szilárd Váncsa, Rita Nagy, Stefania Bunduc, Péter Jenő Hegyi, Katalin Márta, Katalin Borka, Attila Doros, Nóra Hosszúfalusi, László Zubek, Bálint Erőss, Zsolt Molnár, Andrea Párniczky, Péter Hegyi, Andrea Szentesi, Judit Bajor, Szilárd Gódi, Patrícia Sarlós, József Czimmer, Imre Szabó, Gabriella Pár, Anita Illés, Roland Hágendorn, Balázs Csaba Németh, Balázs Kui, Dóra Illés, László Gajdán, Veronika Dunás-Varga, Roland Fejes, Mária Papp, Zsuzsanna Vitális, János Novák, Imola Török, Melania Macarie, Elena Ramírez-Maldonado, Ville Sallinen, Shamil Galeev, Barnabás Bod, Ali Tüzün Ince, Dániel Pécsi, Péter Varjú, Márk Félix Juhász, Klementina Ocskay, Alexandra Mikó, Zsolt Szakács

Affiliations

¹ Doctoral School of Clinical Medicine, Faculty of Medicine, University of Szeged, Szeged, 6720, Hungary.
² Institute for Translational Medicine, Szentágothai Research Centre, Medical School, University of Pécs, Szigeti út 12., II. Emelet, Pécs, 7624, Hungary.
³ Heim Pál National Pediatric Institute, Üllői út 86, Budapest, 1089, Hungary.
⁴ Human and Social Data Science Lab, Budapest University of Technology and Economics, Műegyetem rkp. 3, Budapest, 1111, Hungary.
⁵ Stochastics Research Group, Hungarian Academy of Sciences, Budapest University of Technology and Economics, Egry József u. 1, Budapest, 1111, Hungary.
⁶ Institute of Bioanalysis, Medical School, University of Pécs, Honvéd u. 1, Pécs, 7624, Hungary.
⁷ Department of Biomathematics and Informatics, University of Veterinary Medicine, István u. 2, Budapest, 1078, Hungary.
⁸ Division of Gastroenterology, First Department of Medicine, Medical School, University of Pécs, Ifjúság út 13, Pécs, 7624, Hungary.
⁹ Department of Medicine, University of Szeged, Kálvária sgt. 57, Szeged, 6725, Hungary.
¹⁰ Department of Internal Medicine, Szent György Teaching Hospital of County Fejér, Seregélyesi út 3, Székesfehérvár, 8000, Hungary.
¹¹ Bajcsy-Zsilinszky Hospital, Maglódi út 89-91, Budapest, 1106, Hungary.
¹² Department of Gastroenterology, BMKK Dr Rethy Pal Hospital, Gyulai út 18, Békéscsaba, 5600, Hungary.
¹³ Vilnius University Hospital Santaros Clinics, Clinics of Abdominal Surgery, Nephrourology and Gastroenterology, Faculty of Medicine, Vilnius University, Santariškių g. 2, 08410, Vilnius, Lithuania.
¹⁴ Department of Medical Imaging, Medical School, University of Pécs, Ifjúság út 13, Pécs, 7624, Hungary.
¹⁵ Centre for Translational Medicine, Semmelweis University, Üllői út 26, Budapest, 1085, Hungary.
¹⁶ Doctoral School, Carol Davila University of Medicine and Pharmacy, Bulevardul Eroii Sanitari 8, 050474, Bucharest, Romania.
¹⁷ Division of Pancreatic Diseases, Heart and Vascular Center, Semmelweis University, Baross u. 23, Budapest, 1082, Hungary.
¹⁸ 2nd Department of Pathology, Semmelweis University, Üllői út 93, Budapest, 1091, Hungary.
¹⁹ Department of Transplantation and Surgery, Semmelweis University, Baross u. 23, Budapest, 1082, Hungary.
²⁰ Department of Internal Medicine and Hematology, Semmelweis University, Szentkirályi u. 46, Budapest, 1088, Hungary.
²¹ Department of Anaesthesiology and Intensive Therapy, Semmelweis University, Üllői út 78, Budapest, 1082, Hungary.
²² Department of Anaesthesiology and Intensive Therapy, Poznan University of Medical Sciences, ul. św. Marii Magdaleny 14, 61861, Poznan, Wielkopolska, Poland.
²³ Doctoral School of Clinical Medicine, Faculty of Medicine, University of Szeged, Szeged, 6720, Hungary. szentesiai@gmail.com.
²⁴ Institute for Translational Medicine, Szentágothai Research Centre, Medical School, University of Pécs, Szigeti út 12., II. Emelet, Pécs, 7624, Hungary. szentesiai@gmail.com.

^# Contributed equally.

PMID: 35552440
PMCID: PMC9098474
DOI: 10.1038/s41598-022-11517-w

Abstract

Pancreatic necrosis is a consistent prognostic factor in acute pancreatitis (AP). However, the clinical scores currently in use are either too complicated or require data that are unavailable on admission or lack sufficient predictive value. We therefore aimed to develop a tool to aid in necrosis prediction. The XGBoost machine learning algorithm processed data from 2387 patients with AP. The confidence of the model was estimated by a bootstrapping method and interpreted via the 10th and the 90th percentiles of the prediction scores. Shapley Additive exPlanations (SHAP) values were calculated to quantify the contribution of each variable provided. Finally, the model was implemented as an online application using the Streamlit Python-based framework. The XGBoost classifier provided an AUC value of 0.757. Glucose, C-reactive protein, alkaline phosphatase, gender and total white blood cell count have the most impact on prediction based on the SHAP values. The relationship between the size of the training dataset and model performance shows that prediction performance can be improved. This study combines necrosis prediction and artificial intelligence. The predictive potential of this model is comparable to the current clinical scoring systems and has several advantages over them.

PubMed Disclaimer

Conflict of interest statement

The authors declare no competing interests.

Figures

**Figure 1**
Flowchart representing the process of developing the model.

**Figure 2**
Association between necrosis development and other complications in acute pancreatitis.

**Figure 3**
Receiver operating characteristic (ROC) curve for the XGBoost model.

**Figure 4**
The relationship between the size of the data set and the model performance. The blue dot represents the area under the ROC curve value and the vertical lines show the corresponding confidence intervals.

**Figure 5**
The predicted necrosis probabilities with the corresponding 50% (between the 25th and 50th percentiles) and 80% confidence (between the 10th and 90th percentiles).

**Figure 6**
(A) The features with the highest impact on model output based on the SHAP values. The higher the predictor is on the list, the bigger the impact on model output. Each patient is represented by a dot. The x-axis represents the extent of the impact on prediction. The color of the dot shows the feature value (e.g. the red color implies higher values). (B) An example of prediction and its textual interpretation. The lower picture highlights the effect of individual predictors and the final necrosis probability provided by the model.

**Figure 7**
The models build on the k predictors with the highest SHAP value.

See this image and copyright information in PMC

Cited by

Stmol: A component for building interactive molecular visualizations within streamlit web-applications.
Nápoles-Duarte JM, Biswas A, Parker MI, Palomares-Baez JP, Chávez-Rojo MA, Rodríguez-Valdez LM. Nápoles-Duarte JM, et al. Front Mol Biosci. 2022 Sep 23;9:990846. doi: 10.3389/fmolb.2022.990846. eCollection 2022. Front Mol Biosci. 2022. PMID: 36213112 Free PMC article.
Implementation and Updating of Clinical Prediction Models: A Systematic Review.
Saelmans A, Seinen T, Pera V, Markus AF, Fridgeirsson E, John LH, Schiphof-Godart L, Rijnbeek P, Reps J, Williams R. Saelmans A, et al. Mayo Clin Proc Digit Health. 2025 May 23;3(3):100228. doi: 10.1016/j.mcpdig.2025.100228. eCollection 2025 Sep. Mayo Clin Proc Digit Health. 2025. PMID: 40599890 Free PMC article. Review.
Predicting the risk of early intensive care unit admission for patients hospitalized with acute pancreatitis using supervised machine learning.
Ali H, Inayat F, Dhillon R, Patel P, Afzal A, Wilkinson C, Rehman AU, Anwar MS, Nawaz G, Chaudhry A, Awan JR, Afzal MS, Samanta J, Adler DG, Mohan BP. Ali H, et al. Proc (Bayl Univ Med Cent). 2024 Mar 21;37(3):437-447. doi: 10.1080/08998280.2024.2326371. eCollection 2024. Proc (Bayl Univ Med Cent). 2024. PMID: 38628340 Free PMC article.
Persistently High Procalcitonin and C-Reactive Protein Are Good Predictors of Infection in Acute Necrotizing Pancreatitis: A Systematic Review and Meta-Analysis.
Tarján D, Szalai E, Lipp M, Verbói M, Kói T, Erőss B, Teutsch B, Faluhelyi N, Hegyi P, Mikó A. Tarján D, et al. Int J Mol Sci. 2024 Jan 20;25(2):1273. doi: 10.3390/ijms25021273. Int J Mol Sci. 2024. PMID: 38279274 Free PMC article.
Machine learning improves prediction of severity and outcomes of acute pancreatitis: a prospective multi-center cohort study.
Li JN, Mu D, Zheng SC, Tian W, Wu ZY, Meng J, Wang RF, Zheng TL, Zhang YL, Windsor J, Lu GT, Wu D. Li JN, et al. Sci China Life Sci. 2023 Aug;66(8):1934-1937. doi: 10.1007/s11427-022-2333-8. Epub 2023 May 16. Sci China Life Sci. 2023. PMID: 37209250 No abstract available.

See all "Cited by" articles

References

1. Boxhoorn L, et al. Acute pancreatitis. Lancet (London, England) 2020;396:726–734. doi: 10.1016/s0140-6736(20)31310-6. - DOI - PubMed
1. Xiao AY, 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;1:45–55. doi: 10.1016/s2468-1253(16)30004-8. - DOI - PubMed
1. Berger Z, et al. Acute pancreatitis in Chile. A multicenter study on epidemiology, etiology and clinical outcome. Retrospective analysis of clinical files. Pancreatology. 2020;20:637–643. doi: 10.1016/j.pan.2020.04.016. - DOI - PubMed
1. Párniczky A, et al. Prospective, multicentre, nationwide clinical data from 600 cases of acute pancreatitis. PLoS ONE. 2016;11:e0165309. doi: 10.1371/journal.pone.0165309. - DOI - PMC - PubMed
1. Aranda-Narvaez JM, Gonzalez-Sanchez AJ, Montiel-Casado MC, Titos-Garcia A, Santoyo-Santoyo J. Acute necrotizing pancreatitis: Surgical indications and technical procedures. World J. Clin. Cases. 2014;2:840–845. doi: 10.12998/wjcc.v2.i12.840. - DOI - PMC - PubMed

Publication types

Actions

MeSH terms

Actions
Actions
Actions
Actions
Actions
Actions
Actions

LinkOut - more resources

Full Text Sources
Research Materials
- NCI CPTC Antibody Characterization Program

Save citation to file

Email citation

Add to Collections

Add to My Bibliography

Your saved search

Create a file for external citation management software

Your RSS Feed

Early prediction of acute necrotizing pancreatitis by artificial intelligence: a prospective cohort-analysis of 2387 cases

Collaborators

Affiliations

Early prediction of acute necrotizing pancreatitis by artificial intelligence: a prospective cohort-analysis of 2387 cases

Authors

Collaborators

Affiliations

Abstract

Conflict of interest statement

Figures

Similar articles

Cited by

References

Publication types

MeSH terms

LinkOut - more resources

Full Text Sources

Research Materials

Abstract

Conflict of interest statement

Figures

Similar articles

Cited by

References

Publication types

MeSH terms

Related information

LinkOut - more resources

Full Text Sources

Research Materials