Machine learning approach in the STARK international study: gradient boosting outperforms logistic regression to predict post- ERCP pancreatitis (CROSBI ID 706093)
Prilog sa skupa u časopisu | sažetak izlaganja sa skupa | međunarodna recenzija
Podaci o odgovornosti
Archibugi, Livia ; Ciarfaglia, G ; Cárdenas-Jaén, Karina ; Poropat, Goran ; Korpela, Taija ; Maisonneuve, Patrick ; Aparicio Tormo, JR ; Casella y Casellas, JA ; Arcidiacono, Paolo Giorgio ; Mariani, A ; Štimac, Davor ; Hauser, Goran ; Udd, M ; Kylänpää, L ; Rainio, M ; Di Giulio, E ; Vanella, G ; Löhr, Matthias ; Valente, Roberto ; Arnelo, U ; Fagerstrom, N ; de Pretis, Nicolo ; Gabbrielli, A ; Brozzi, L ; Capurso, Gabriele ; de-Madaria, Enrique
engleski
Machine learning approach in the STARK international study: gradient boosting outperforms logistic regression to predict post- ERCP pancreatitis
Introduction: Post-Endoscopic Retrograde Cholangiopancreatography (ERCP) pancreatitis (PEP) is ERCP most frequent complication. Predicting PEP risk can be determinant in reducing its incidence and managing patients appropriately, however, studies conducted so far identified single risk factors with standard statistical approaches, with limited accuracy. Aims & Methods: The aim was to build and evaluate performances of machine learning models to predict PEP probability and identify relevant features. The “STARK project” is an international, multicenter, prospective cohort study focused on PEP-associated factors. Data were randomly split in training (80%) and test set (20%). Models used to predict PEP probability were: gradient boosting (GB) and logistic regression (LR). On the training set, a 10-split random cross-validation (CV) was applied to optimize parameters to obtain the best mean Area Under the Receiver Operating Characteristics Curve (AUC of ROC). Afterwards, the model was re-trained on the whole training set with the best parameters and then applied on the test set. Results: 1, 150 patients were included. 70 (6.1%) patients developed PEP. GB model AUC in CV was 0.7±0.076 (95% CI 0.64-0.76), LR model 0.585±0.068 (95% CI 0.53-0.63) (p-value=0.012). AUC in test for GB model was 0.671. Most relevant variables for PEP prediction were: total bilirubin, age, body mass index, procedure time, alcohol units/day, previous sphincterotomy, biliary cannulation attempts and use of Ringer’s solution. Conclusion: This is the first study applying machine learning techniques for PEP prediction, with GB significantly outperforming LR model. Relevant variables were mostly pre-procedural except for procedure time, biliary cannulation attempts and Ringer’s solution use.
Machine learning, pancreatitis, ERCP
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
Podaci o prilogu
790-790.
2020.
nije evidentirano
objavljeno
10.1177/2050640620927345
Podaci o matičnoj publikaciji
United European Gastroenterology Journal
2050-6406
2050-6414
Podaci o skupu
28th United European Gastroenterology Week
poster
11.10.2020-13.10.2020
online
Povezanost rada
Kliničke medicinske znanosti