دورية أكاديمية
Early prediction of acute necrotizing pancreatitis by artificial intelligence : a prospective cohort-analysis of 2387 cases
| العنوان: | Early prediction of acute necrotizing pancreatitis by artificial intelligence : a prospective cohort-analysis of 2387 cases |
|---|---|
| المؤلفون: | Kiss Szabolcs, Pintér József, Molontay Roland, Nagy Marcell, Borbásné Farkas Kornélia, Sipos Zoltán, Fehérvári Péter, Földi Mária, Vincze Áron, Takács Tamás, Czakó László, Faluhelyi Nándor, Farkas Orsolya, Váncsa Szilárd, Hegyi Péter Jenő, Márta Katalin, Erőss Bálint Mihály, Molnár Zsolt, Párniczky Andrea, Hegyi Péter, Szentesi Andrea Ildikó, Kollaborációs szervezet Hungarian Pancreatic Study Group |
| سنة النشر: | 2022 |
| المجموعة: | University of Szeged: SZTE Repository of Publications / SZTE Publicatio Repozitórium |
| مصطلحات موضوعية: | 03.02.18. Endokrinológia és anyagcserebetegségek (benne cukorbetegség, hormonok) |
| الوصف: | 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. |
| نوع الوثيقة: | article in journal/newspaper |
| وصف الملف: | text |
| اللغة: | English |
| العلاقة: | http://publicatio.bibl.u-szeged.hu/24366/1/KissszSciRep2022.pdfTest; Kiss Szabolcs; Pintér József; Molontay Roland; Nagy Marcell; Borbásné Farkas Kornélia; Sipos Zoltán; Fehérvári Péter; Földi Mária; Vincze Áron; Takács Tamás; Czakó László; Faluhelyi Nándor; Farkas Orsolya; Váncsa Szilárd; Hegyi Péter Jenő; Márta Katalin; Erőss Bálint Mihály; Molnár Zsolt; Párniczky Andrea; Hegyi Péter; Szentesi Andrea Ildikó; Kollaborációs szervezet Hungarian Pancreatic Study Group: Early prediction of acute necrotizing pancreatitis by artificial intelligence : a prospective cohort-analysis of 2387 cases. SCIENTIFIC REPORTS, 12 (1). Terjedelem: 11 p.-Azonosító: 7827. ISSN 2045-2322 (2022) |
| DOI: | 10.1038/s41598-022-11517-w |
| الإتاحة: | https://doi.org/10.1038/s41598-022-11517-wTest http://publicatio.bibl.u-szeged.hu/24366Test/ http://publicatio.bibl.u-szeged.hu/24366/1/KissszSciRep2022.pdfTest |
| حقوق: | info:eu-repo/semantics/openAccess |
| رقم الانضمام: | edsbas.68B9498A |
| قاعدة البيانات: | BASE |
| DOI: | 10.1038/s41598-022-11517-w |
|---|