Related Experiment Video
Updated: Jun 16, 2025
Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
Published on: May 15, 2020
Development and validation of a machine learning-based, point-of-care risk calculator for post-ERCP pancreatitis and
Todd Brenner1, Albert Kuo2, Christina J Sperna Weiland3
1Division of Gastroenterology, Johns Hopkins Medical Institutions, Baltimore, Maryland, USA.
Insights
A new machine learning tool accurately predicts post-ERCP pancreatitis (PEP) risk, helping clinicians select prophylaxis and monitoring strategies. This model identifies low-risk patients, potentially reducing unnecessary interventions.
Area of Science:
- Gastroenterology and Hepatology
- Medical Informatics
- Machine Learning in Healthcare
Background:
- Post-ERCP pancreatitis (PEP) poses a significant clinical challenge.
- A robust risk prediction model for PEP is currently lacking.
- Accurate risk stratification is crucial for guiding prophylactic interventions and patient monitoring.
Purpose of the Study:
- To develop and validate a machine learning-based tool for predicting the risk of post-ERCP pancreatitis (PEP).
- To aid clinical decision-making regarding periprocedural prophylaxis and postprocedural monitoring strategies.
- To identify patients at low risk for PEP who may not require intensive monitoring.
Main Methods:
- A gradient-boosted machine (GBM) model was developed using patient data from 12 randomized controlled trials.
- Feature selection involved 20 PEP risk factors and 5 prophylactic interventions.
- Model performance was evaluated using the area under the receiver operating curve (AUC) with cross-validation and a prospective pilot study.
Main Results:
- The GBM model was trained on 7389 patients with an 8.6% PEP rate.
- The model achieved an AUC of 0.70 during training and 0.74 in a prospective pilot study.
- The model demonstrated a 95% negative predictive value, indicating high confidence in identifying low-risk patients.
Conclusions:
- A novel machine learning tool for PEP risk estimation is feasible and useful.
- The tool can effectively aid in selecting appropriate prophylactic measures.
- High negative predictive value allows for confident identification of patients unlikely to develop PEP, optimizing resource allocation.
Background And Aims:
A robust model of post-ERCP pancreatitis (PEP) risk is not currently available. We aimed to develop a machine learning-based tool for PEP risk prediction to aid in clinical decision making related to periprocedural prophylaxis selection and postprocedural monitoring.
Methods:
Feature selection, model training, and validation were performed using patient-level data from 12 randomized controlled trials. A gradient-boosted machine (GBM) model was trained to estimate PEP risk, and the performance of the resulting model was evaluated using the area under the receiver operating curve (AUC) with 5-fold cross-validation. A web-based clinical decision-making tool was created, and a prospective pilot study was performed using data from ERCPs performed at the Johns Hopkins Hospital over a 1-month period.
Results:
A total of 7389 patients were included in the GBM with an 8.6% rate of PEP. The model was trained on 20 PEP risk factors and 5 prophylactic interventions (rectal nonsteroidal anti-inflammatory drugs [NSAIDs], aggressive hydration, combined rectal NSAIDs and aggressive hydration, pancreatic duct stenting, and combined rectal NSAIDs and pancreatic duct stenting). The resulting GBM model had an AUC of 0.70 (65% specificity, 65% sensitivity, 95% negative predictive value, and 15% positive predictive value). A total of 135 patients were included in the prospective pilot study, resulting in an AUC of 0.74.
Conclusions:
This study demonstrates the feasibility and utility of a novel machine learning-based PEP risk estimation tool with high negative predictive value to aid in prophylaxis selection and identify patients at low risk who may not require extended postprocedure monitoring.
Related Concept Videos
01:29Chronic Pancreatitis II: Collaborative Care
Assessment:
01:30Acute Pancreatitis II: Clinical Manifestations and Management
01:26Endoscopic Procedures V: ERCP
Patient...