FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308348056> ?p ?o ?g. }

• W4308348056 endingPage "393" @default.
• W4308348056 startingPage "387" @default.
• W4308348056 abstract "Predicting Post-Endoscopic Retrograde Cholangiopancreatography (ERCP) pancreatitis (PEP) risk can be determinant in reducing its incidence and managing patients appropriately, however studies conducted thus far have identified single-risk factors with standard statistical approaches and limited accuracy.To build and evaluate performances of machine learning (ML) models to predict PEP probability and identify relevant features.A proof-of-concept study was performed on ML application on an international, multicenter, prospective cohort of ERCP patients. Data were split in training and test set, models used were gradient boosting (GB) and logistic regression (LR). A 10-split random cross-validation (CV) was applied on the training set to optimize parameters to obtain the best mean Area Under Curve (AUC). The model was re-trained on the whole training set with the best parameters and applied on test set. Shapley-Additive-exPlanation (SHAP) approach was applied to break down the model and clarify features impact.One thousand one hundred and fifty patients were included, 6.1% developed PEP. GB model outperformed LR with AUC in CV of 0.7 vs 0.585 (p-value=0.012). GB AUC in test was 0.671. Most relevant features for PEP prediction were: bilirubin, age, body mass index, procedure time, previous sphincterotomy, alcohol units/day, cannulation attempts, gender, gallstones, use of Ringer's solution and periprocedural NSAIDs.In PEP prediction, GB significantly outperformed LR model and identified new clinical features relevant for the risk, most being pre-procedural." @default.
• W4308348056 created "2022-11-11" @default.
• W4308348056 creator A5000830051 @default.
• W4308348056 creator A5009466676 @default.
• W4308348056 creator A5009488989 @default.
• W4308348056 creator A5013117107 @default.
• W4308348056 creator A5013662815 @default.
• W4308348056 creator A5015433245 @default.
• W4308348056 creator A5016633126 @default.
• W4308348056 creator A5017315328 @default.
• W4308348056 creator A5017811643 @default.
• W4308348056 creator A5022836234 @default.
• W4308348056 creator A5023956553 @default.
• W4308348056 creator A5024489661 @default.
• W4308348056 creator A5025825374 @default.
• W4308348056 creator A5054890023 @default.
• W4308348056 creator A5056160642 @default.
• W4308348056 creator A5065022735 @default.
• W4308348056 creator A5065520120 @default.
• W4308348056 creator A5065599900 @default.
• W4308348056 creator A5065644162 @default.
• W4308348056 creator A5067951642 @default.
• W4308348056 creator A5069023355 @default.
• W4308348056 creator A5069035265 @default.
• W4308348056 creator A5080333029 @default.
• W4308348056 creator A5082270662 @default.
• W4308348056 creator A5085191511 @default.
• W4308348056 creator A5088530341 @default.
• W4308348056 date "2023-03-01" @default.
• W4308348056 modified "2023-10-04" @default.
• W4308348056 title "Machine learning for the prediction of post-ERCP pancreatitis risk: A proof-of-concept study" @default.
• W4308348056 cites W1678356000 @default.
• W4308348056 cites W1830758076 @default.
• W4308348056 cites W2014891010 @default.
• W4308348056 cites W2045292320 @default.
• W4308348056 cites W2058073973 @default.
• W4308348056 cites W2067083645 @default.
• W4308348056 cites W2095333601 @default.
• W4308348056 cites W2135473463 @default.
• W4308348056 cites W2136033222 @default.
• W4308348056 cites W2145758369 @default.
• W4308348056 cites W2296985122 @default.
• W4308348056 cites W2512631225 @default.
• W4308348056 cites W2568237566 @default.
• W4308348056 cites W2577520851 @default.
• W4308348056 cites W2590921856 @default.
• W4308348056 cites W2609777439 @default.
• W4308348056 cites W2773955993 @default.
• W4308348056 cites W2789894922 @default.
• W4308348056 cites W2809700263 @default.
• W4308348056 cites W2888040362 @default.
• W4308348056 cites W2892741787 @default.
• W4308348056 cites W2897124762 @default.
• W4308348056 cites W2905598756 @default.
• W4308348056 cites W2912856104 @default.
• W4308348056 cites W2913997948 @default.
• W4308348056 cites W2954166898 @default.
• W4308348056 cites W2954691525 @default.
• W4308348056 cites W2966038383 @default.
• W4308348056 cites W2994864913 @default.
• W4308348056 cites W2996748935 @default.
• W4308348056 cites W2999615587 @default.
• W4308348056 cites W3137245688 @default.
• W4308348056 cites W4280616075 @default.
• W4308348056 cites W4281929909 @default.
• W4308348056 doi "https://doi.org/10.1016/j.dld.2022.10.005" @default.
• W4308348056 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36344369" @default.
• W4308348056 hasPublicationYear "2023" @default.
• W4308348056 type Work @default.
• W4308348056 citedByCount "2" @default.
• W4308348056 countsByYear W43083480562023 @default.
• W4308348056 crossrefType "journal-article" @default.
• W4308348056 hasAuthorship W4308348056A5000830051 @default.
• W4308348056 hasAuthorship W4308348056A5009466676 @default.
• W4308348056 hasAuthorship W4308348056A5009488989 @default.
• W4308348056 hasAuthorship W4308348056A5013117107 @default.
• W4308348056 hasAuthorship W4308348056A5013662815 @default.
• W4308348056 hasAuthorship W4308348056A5015433245 @default.
• W4308348056 hasAuthorship W4308348056A5016633126 @default.
• W4308348056 hasAuthorship W4308348056A5017315328 @default.
• W4308348056 hasAuthorship W4308348056A5017811643 @default.
• W4308348056 hasAuthorship W4308348056A5022836234 @default.
• W4308348056 hasAuthorship W4308348056A5023956553 @default.
• W4308348056 hasAuthorship W4308348056A5024489661 @default.
• W4308348056 hasAuthorship W4308348056A5025825374 @default.
• W4308348056 hasAuthorship W4308348056A5054890023 @default.
• W4308348056 hasAuthorship W4308348056A5056160642 @default.
• W4308348056 hasAuthorship W4308348056A5065022735 @default.
• W4308348056 hasAuthorship W4308348056A5065520120 @default.
• W4308348056 hasAuthorship W4308348056A5065599900 @default.
• W4308348056 hasAuthorship W4308348056A5065644162 @default.
• W4308348056 hasAuthorship W4308348056A5067951642 @default.
• W4308348056 hasAuthorship W4308348056A5069023355 @default.
• W4308348056 hasAuthorship W4308348056A5069035265 @default.
• W4308348056 hasAuthorship W4308348056A5080333029 @default.
• W4308348056 hasAuthorship W4308348056A5082270662 @default.
• W4308348056 hasAuthorship W4308348056A5085191511 @default.
• W4308348056 hasAuthorship W4308348056A5088530341 @default.

• next