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

Journal: Scientific reports
Published Date: May 12, 2022

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.

Authors

  • Szabolcs Kiss
    Doctoral School of Clinical Medicine, Faculty of Medicine, University of Szeged, Szeged, 6720, Hungary.
  • József Pintér
    Human and Social Data Science Lab, Budapest University of Technology and Economics, Műegyetem rkp. 3, Budapest, 1111, Hungary.
  • Roland Molontay
    Human and Social Data Science Lab, Budapest University of Technology and Economics, Műegyetem rkp. 3, Budapest, 1111, Hungary.
  • Marcell Nagy
    Human and Social Data Science Lab, Budapest University of Technology and Economics, Műegyetem rkp. 3, Budapest, 1111, Hungary.
  • Nelli Farkas
    Institute for Translational Medicine, Szentágothai Research Centre, Medical School, University of Pécs, Szigeti út 12., II. Emelet, Pécs, 7624, Hungary.
  • Zoltán Sipos
    Institute for Translational Medicine, Szentágothai Research Centre, Medical School, University of Pécs, Szigeti út 12., II. Emelet, Pécs, 7624, Hungary.
  • Péter Fehérvári
    Institute for Translational Medicine, Szentágothai Research Centre, Medical School, University of Pécs, Szigeti út 12., II. Emelet, Pécs, 7624, Hungary.
  • László Pecze
    Institute for Translational Medicine, Szentágothai Research Centre, Medical School, University of Pécs, Szigeti út 12., II. Emelet, Pécs, 7624, Hungary.
  • Mária Földi
    Doctoral School of Clinical Medicine, Faculty of Medicine, University of Szeged, Szeged, 6720, Hungary.
  • Áron Vincze
    Division of Gastroenterology, First Department of Medicine, Medical School, University of Pécs, Ifjúság út 13, Pécs, 7624, Hungary.
  • Tamás Takács
    Department of Medicine, University of Szeged, Kálvária sgt. 57, Szeged, 6725, Hungary.
  • László Czakó
    Department of Medicine, University of Szeged, Kálvária sgt. 57, Szeged, 6725, Hungary.
  • Ferenc Izbéki
    Department of Internal Medicine, Szent György Teaching Hospital of County Fejér, Seregélyesi út 3, Székesfehérvár, 8000, Hungary.
  • Adrienn Halász
    Doctoral School of Clinical Medicine, Faculty of Medicine, University of Szeged, Szeged, 6720, Hungary.
  • Eszter Boros
    Department of Internal Medicine, Szent György Teaching Hospital of County Fejér, Seregélyesi út 3, Székesfehérvár, 8000, Hungary.
  • József Hamvas
    Bajcsy-Zsilinszky Hospital, Maglódi út 89-91, Budapest, 1106, Hungary.
  • Márta Varga
    Department of Gastroenterology, BMKK Dr Rethy Pal Hospital, Gyulai út 18, Békéscsaba, 5600, Hungary.
  • Artautas Mickevicius
    Vilnius University Hospital Santaros Clinics, Clinics of Abdominal Surgery, Nephrourology and Gastroenterology, Faculty of Medicine, Vilnius University, Santariškių g. 2, 08410, Vilnius, Lithuania.
  • Nándor Faluhelyi
    Department of Medical Imaging, Medical School, University of Pécs, Ifjúság út 13, Pécs, 7624, Hungary.
  • Orsolya Farkas
    Department of Medical Imaging, Medical School, University of Pécs, Ifjúság út 13, Pécs, 7624, Hungary.
  • Szilárd Váncsa
    Institute for Translational Medicine, Szentágothai Research Centre, Medical School, University of Pécs, Szigeti út 12., II. Emelet, Pécs, 7624, Hungary.
  • Rita Nagy
    Institute for Translational Medicine, Szentágothai Research Centre, Medical School, University of Pécs, Szigeti út 12., II. Emelet, Pécs, 7624, Hungary.
  • Stefania Bunduc
    Centre for Translational Medicine, Semmelweis University, Üllői út 26, Budapest, 1085, Hungary.
  • Péter Jenő Hegyi
    Centre for Translational Medicine, Semmelweis University, Üllői út 26, Budapest, 1085, Hungary.
  • Katalin Márta
    Centre for Translational Medicine, Semmelweis University, Üllői út 26, Budapest, 1085, Hungary.
  • Katalin Borka
    Centre for Translational Medicine, Semmelweis University, Üllői út 26, Budapest, 1085, Hungary.
  • Attila Doros
    Centre for Translational Medicine, Semmelweis University, Üllői út 26, Budapest, 1085, Hungary.
  • Nóra Hosszúfalusi
    Centre for Translational Medicine, Semmelweis University, Üllői út 26, Budapest, 1085, Hungary.
  • László Zubek
    Centre for Translational Medicine, Semmelweis University, Üllői út 26, Budapest, 1085, Hungary.
  • Bálint Erőss
    Centre for Translational Medicine, Semmelweis University, Üllői út 26, Budapest, 1085, Hungary.
  • Zsolt Molnár
    Institute of Ecology and Botany, MTA Centre for Ecological Research, Hungarian Academy of Sciences, Alkotmány u. 2-4, H-2163, Vácrátót, Hungary. molnar.zsolt@okologia.mta.hu.
  • Andrea Párniczky
    Institute for Translational Medicine, Szentágothai Research Centre, Medical School, University of Pécs, Szigeti út 12., II. Emelet, Pécs, 7624, Hungary.
  • Péter Hegyi
    Centre for Translational Medicine, Semmelweis University, Budapest, Hungary.
  • Andrea Szentesi
    Doctoral School of Clinical Medicine, Faculty of Medicine, University of Szeged, Szeged, 6720, Hungary. szentesiai@gmail.com.

Keywords

External Resources

Popular Topics
Recent Journals