EASY-APP: An artificial intelligence model and application for early and easy prediction of severity in acute pancreatitis.

Autor: Kui B; Department of Medicine, University of Szeged, Szeged, Hungary.; Centre for Translational Medicine, Department of Medicine, University of Szeged, Szeged, Hungary., Pintér J; Department of Stochastics, Institute of Mathematics, Budapest University of Technology and Economics, Budapest, Hungary., Molontay R; Department of Stochastics, Institute of Mathematics, Budapest University of Technology and Economics, Budapest, Hungary.; MTA-BME Stochastics Research Group, Budapest, Hungary., Nagy M; Department of Stochastics, Institute of Mathematics, Budapest University of Technology and Economics, Budapest, Hungary., Farkas N; Institute for Translational Medicine, Szentágothai Research Centre, Medical School, University of Pécs, Pécs, Hungary.; Institute of Bioanalysis, Medical School, University of Pécs, Pécs, Hungary., Gede N; Institute for Translational Medicine, Szentágothai Research Centre, Medical School, University of Pécs, Pécs, Hungary., Vincze Á; Division of Gastroenterology, First Department of Medicine, University of Pécs, Medical School, Pécs, Hungary., Bajor J; Division of Gastroenterology, First Department of Medicine, University of Pécs, Medical School, Pécs, Hungary., Gódi S; Division of Gastroenterology, First Department of Medicine, University of Pécs, Medical School, Pécs, Hungary., Czimmer J; Division of Gastroenterology, First Department of Medicine, University of Pécs, Medical School, Pécs, Hungary., Szabó I; Division of Gastroenterology, First Department of Medicine, University of Pécs, Medical School, Pécs, Hungary., Illés A; Division of Gastroenterology, First Department of Medicine, University of Pécs, Medical School, Pécs, Hungary., Sarlós P; Division of Gastroenterology, First Department of Medicine, University of Pécs, Medical School, Pécs, Hungary., Hágendorn R; Division of Gastroenterology, First Department of Medicine, University of Pécs, Medical School, Pécs, Hungary., Pár G; Division of Gastroenterology, First Department of Medicine, University of Pécs, Medical School, Pécs, Hungary., Papp M; Department of Gastroenterology, Institute of Internal Medicine, Faculty of Medicine, University of Debrecen, Debrecen, Hungary., Vitális Z; Department of Gastroenterology, Institute of Internal Medicine, Faculty of Medicine, University of Debrecen, Debrecen, Hungary., Kovács G; Department of Gastroenterology, Institute of Internal Medicine, Faculty of Medicine, University of Debrecen, Debrecen, Hungary., Fehér E; Department of Gastroenterology, Institute of Internal Medicine, Faculty of Medicine, University of Debrecen, Debrecen, Hungary., Földi I; Department of Gastroenterology, Institute of Internal Medicine, Faculty of Medicine, University of Debrecen, Debrecen, Hungary., Izbéki F; Szent György Teaching Hospital of County Fejér, Székesfehérvár, Hungary., Gajdán L; Szent György Teaching Hospital of County Fejér, Székesfehérvár, Hungary., Fejes R; Szent György Teaching Hospital of County Fejér, Székesfehérvár, Hungary., Németh BC; Department of Medicine, University of Szeged, Szeged, Hungary.; Centre for Translational Medicine, Department of Medicine, University of Szeged, Szeged, Hungary., Török I; County Emergency Clinical Hospital of Târgu Mures-Gastroenterology Clinic and University of Medicine, Pharmacy, Sciences and Technology 'George Emil Palade', Targu Mures, Romania., Farkas H; County Emergency Clinical Hospital of Târgu Mures-Gastroenterology Clinic and University of Medicine, Pharmacy, Sciences and Technology 'George Emil Palade', Targu Mures, Romania., Mickevicius A; Vilnius University Hospital Santaros Clinics, Vilnius, Lithuania., Sallinen V; Department of Transplantation and Liver Surgery, Helsinki University Hospital and University of Helsinki, Helsinki, Finland., Galeev S; Saint Luke Clinical Hospital, St. Petersburg, Russia., Ramírez-Maldonado E; Department of General Surgery, Consorci Sanitari del Garraf, Sant Pere de Ribes, Spain., Párniczky A; Institute for Translational Medicine, Szentágothai Research Centre, Medical School, University of Pécs, Pécs, Hungary.; Heim Pál National Pediatric Institute, Budapest, Hungary., Erőss B; Institute for Translational Medicine, Szentágothai Research Centre, Medical School, University of Pécs, Pécs, Hungary.; Division of Pancreatic Diseases, Heart and Vascular Centre, Semmelweis University, Budapest, Hungary.; Centre for Translational Medicine, Semmelweis University, Budapest, Hungary., Hegyi PJ; Institute for Translational Medicine, Szentágothai Research Centre, Medical School, University of Pécs, Pécs, Hungary.; Division of Pancreatic Diseases, Heart and Vascular Centre, Semmelweis University, Budapest, Hungary., Márta K; Division of Pancreatic Diseases, Heart and Vascular Centre, Semmelweis University, Budapest, Hungary.; Centre for Translational Medicine, Semmelweis University, Budapest, Hungary., Váncsa S; Institute for Translational Medicine, Szentágothai Research Centre, Medical School, University of Pécs, Pécs, Hungary.; Division of Pancreatic Diseases, Heart and Vascular Centre, Semmelweis University, Budapest, Hungary.; Centre for Translational Medicine, Semmelweis University, Budapest, Hungary., Sutton R; Institute of Systems, Molecular and Integrative Biology, University of Liverpool and Liverpool University Hospitals NHS Foundation Trust, Liverpool, England, UK., Szatmary P; Institute of Systems, Molecular and Integrative Biology, University of Liverpool and Liverpool University Hospitals NHS Foundation Trust, Liverpool, England, UK., Latawiec D; Institute of Systems, Molecular and Integrative Biology, University of Liverpool and Liverpool University Hospitals NHS Foundation Trust, Liverpool, England, UK., Halloran C; Institute of Systems, Molecular and Integrative Biology, University of Liverpool and Liverpool University Hospitals NHS Foundation Trust, Liverpool, England, UK., de-Madaria E; Gastroenterology Department, Alicante University General Hospital, ISABIAL, Alicante, Spain., Pando E; Department of Hepato-Pancreato-Biliary and Transplant Surgery, Hospital Universitari Vall d'Hebron, Universitat Autònoma de Barcelona, Barcelona, Spain., Alberti P; Department of Hepato-Pancreato-Biliary and Transplant Surgery, Hospital Universitari Vall d'Hebron, Universitat Autònoma de Barcelona, Barcelona, Spain., Gómez-Jurado MJ; Department of Hepato-Pancreato-Biliary and Transplant Surgery, Hospital Universitari Vall d'Hebron, Universitat Autònoma de Barcelona, Barcelona, Spain., Tantau A; The 4th Medical Clinic, Iuliu Hatieganu' University of Medicine and Pharmacy, Cluj-Napoca, Romania.; Gastroenterology and Hepatology Medical Center, Cluj-Napoca, Romania., Szentesi A; Centre for Translational Medicine, Department of Medicine, University of Szeged, Szeged, Hungary.; Institute for Translational Medicine, Szentágothai Research Centre, Medical School, University of Pécs, Pécs, Hungary., Hegyi P; Institute for Translational Medicine, Szentágothai Research Centre, Medical School, University of Pécs, Pécs, Hungary.; Division of Pancreatic Diseases, Heart and Vascular Centre, Semmelweis University, Budapest, Hungary.; Centre for Translational Medicine, Semmelweis University, Budapest, Hungary.
Jazyk: angličtina
Zdroj: Clinical and translational medicine [Clin Transl Med] 2022 Jun; Vol. 12 (6), pp. e842.
DOI: 10.1002/ctm2.842
Abstrakt: Background: Acute pancreatitis (AP) is a potentially severe or even fatal inflammation of the pancreas. Early identification of patients at high risk for developing a severe course of the disease is crucial for preventing organ failure and death. Most of the former predictive scores require many parameters or at least 24 h to predict the severity; therefore, the early therapeutic window is often missed.
Methods: The early achievable severity index (EASY) is a multicentre, multinational, prospective and observational study (ISRCTN10525246). The predictions were made using machine learning models. We used the scikit-learn, xgboost and catboost Python packages for modelling. We evaluated our models using fourfold cross-validation, and the receiver operating characteristic (ROC) curve, the area under the ROC curve (AUC), and accuracy metrics were calculated on the union of the test sets of the cross-validation. The most critical factors and their contribution to the prediction were identified using a modern tool of explainable artificial intelligence called SHapley Additive exPlanations (SHAP).
Results: The prediction model was based on an international cohort of 1184 patients and a validation cohort of 3543 patients. The best performing model was an XGBoost classifier with an average AUC score of 0.81 ± 0.033 and an accuracy of 89.1%, and the model improved with experience. The six most influential features were the respiratory rate, body temperature, abdominal muscular reflex, gender, age and glucose level. Using the XGBoost machine learning algorithm for prediction, the SHAP values for the explanation and the bootstrapping method to estimate confidence, we developed a free and easy-to-use web application in the Streamlit Python-based framework (http://easy-app.org/).
Conclusions: The EASY prediction score is a practical tool for identifying patients at high risk for severe AP within hours of hospital admission. The web application is available for clinicians and contributes to the improvement of the model.
(© 2022 The Authors. Clinical and Translational Medicine published by John Wiley & Sons Australia, Ltd on behalf of Shanghai Institute of Clinical Bioinformatics.)
Databáze: MEDLINE
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje