EASY-APP : An artificial intelligence model and application for early and easy prediction of severity in acute pancreatitis
Kui, Balázs (University of Szeged)
Pintér, József (Budapest University of Technology and Economics)
Molontay, Roland (MTA-BME Stochastics Research Group)
Nagy, Marcell (Budapest University of Technology and Economics)
Farkas, Nelli (University of Pécs)
Gede, Noémi (University of Pécs)
Vincze, Áron (University of Pécs)
Bajor, Judit (University of Pécs)
Gódi, Szilárd (University of Pécs)
Czimmer, József (University of Pécs)
Szabó, Imre (University of Pécs)
Illés, Anita (University of Pécs)
Sarlós, Patrícia (University of Pécs)
Hágendorn, Roland (University of Pécs)
Pár, Gabriella (University of Pécs)
Papp, Mária (University of Debrecen)
Vitalis, Zsuzsanna (University of Debrecen)
Kovács, György (University of Debrecen)
Fehér, Eszter (University of Debrecen)
Földi, Ildikó (University of Debrecen)
Izbéki, Ferenc (Szent György Teaching Hospital of County Fejér)
Gajdán, László (Szent György Teaching Hospital of County Fejér)
Fejes, Roland (Szent György Teaching Hospital of County Fejér)
Németh, Balázs Csaba (University of Szeged)
Török, Imola (University of Medicine, Pharmacy, Sciences and Technology 'George Emil Palade')
Farkas, Hunor (University of Medicine, Pharmacy, Sciences and Technology 'George Emil Palade')
Mickevicius, Artautas (Vilnius University Hospital Santariskiu Clinics (Vilnius, Lituània))
Sallinen, Ville (Helsinki University Hospital)
Galeev, Shamil (Saint Luke Clinical Hospital)
Ramírez-Maldonado, Elena (Consorci Sanitari del Garraf)
Párniczky, Andrea (Heim Pál National Pediatric Institute)
Erőss, Bálint (Semmelweis University)
Hegyi, Péter Jenő (Semmelweis University)
Márta, Katalin (Semmelweis University)
Váncsa, Szilárd (Semmelweis University)
Sutton, Robert (Liverpool University Hospitals NHS Foundation Trust)
Szatmary, Peter (Liverpool University Hospitals NHS Foundation Trust)
Latawiec, Diane (Liverpool University Hospitals NHS Foundation Trust)
Halloran, Chris (Liverpool University Hospitals NHS Foundation Trust)
de-Madaria, Enrique (Hospital General Universitari Dr. Balmis)
Pando, Elizabeth (Hospital Universitari Vall d'Hebron)
Alberti Delgado, Piero Arturo (Hospital Universitari Vall d'Hebron)
Gómez-Jurado, Maria José (Hospital Universitari Vall d'Hebron)
Tantau, Alina (Gastroenterology and Hepatology Medical Center)
Szentesi, Andrea (University of Pécs)
Hegyi, Péter (Semmelweis University)
Universitat Autònoma de Barcelona

Fecha:	2022
Resumen:	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. 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). 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/). 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.
Derechos:	Aquest document està subjecte a una llicència d'ús Creative Commons. Es permet la reproducció total o parcial, la distribució, la comunicació pública de l'obra i la creació d'obres derivades, fins i tot amb finalitats comercials, sempre i quan es reconegui l'autoria de l'obra original.
Lengua:	Anglès
Documento:	Article ; recerca ; Versió publicada
Materia:	Acute pancreatitis ; Artificial intelligence ; Severity prediction
Publicado en:	Clinical and Translational Medicine, Vol. 12 (june 2022) , ISSN 2001-1326

DOI: 10.1002/ctm2.842
PMID: 35653504

15 p, 1.6 MB

El registro aparece en las colecciones:
Artículos > Artículos de investigación
Artículos > Artículos publicados