Browsing by Author "Sperna Weiland, Christina J."

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Development and Validation of a Machine Learning-based, Point-of-Care Risk Calculator for Post-ERCP Pancreatitis and Prophylaxis Selection
    (Elsevier, 2024) Brenner, Todd; Kuo, Albert; Sperna Weiland, Christina J.; Kamal, Ayesha; Elmunzer, B. Joseph; Luo, Hui; Buxbaum, James; Gardner, Timothy B.; Mok, Shaffer S.; Fogel, Evan S.; Phillip, Veit; Choi, Jun-Ho; Lua, Guan W.; Lin, Ching-Chung; Reddy, D. Nageshwar; Lakhtakia, Sundeep; Goenka, Mahesh K.; Kochhar, Rakesh; Khashab, Mouen A.; van Geenen, Erwin J. M.; Singh, Vikesh K.; Tomasetti, Cristian; Akshintala, Venkata S.; Medicine, School of Medicine
    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.
  • Thumbnail Image
    Item
    Preventive Measures and Risk Factors for Post-ERCP Pancreatitis: A Systematic Review and Individual Patient Data Meta-Analysis
    (Springer, 2024) Sperna Weiland, Christina J.; Akshintala, Venkata S.; Singh, Anmol; Buxbaum, James; Choi, Jun-Ho; Elmunzer, Badih J.; Fogel, Evan S.; Lai, Jian-Han; Levenick, John M.; Gardner, Timothy B.; Lua, Guan W.; Luo, Hui; de Jong, Mike; Mok, Shaffer R. S.; Phillip, Veit; Singh, Vikesh; Siersema, Peter D.; Drenth, Joost P. H.; van Geenen, Erwin J. M.; Medicine, School of Medicine
    Background: Post-endoscopic retrograde cholangiopancreatography (ERCP) pancreatitis (PEP) is the most common complication of ERCP, with limited studies comparing combined prophylactic measures and their efficacy relative to individual patient risk profiles. This study aims to perform an individual patient data meta-analysis (IPDMA) to evaluate the contribution of patient and ERCP-related risk factors to PEP development and to identify the best prophylaxis strategies according to the patient's risk profile. Methods: We systematically searched MEDLINE, Embase, and Cochrane databases until November 2022 for randomized controlled PEP prophylaxis trials. We invited authors to share individual patient data, including PEP risk profile and prophylaxes used. PEP incidence rates for different prophylaxis were calculated. Efficacy was compared using multilevel logistic regression and expressed as relative risk (RR). Subgroup analysis evaluated the role of patient and ERCP-related risk factors in developing PEP. Results: Data from 11 studies, including 6430 patients, were analyzed. After adjusting for risk factors, rectal NSAIDs (RR 0.69, 95%CI 0.54-0.88) and peri-procedural high-volume intravenous fluid (IVF) (RR 0.40, 95%CI 0.21-0.79) were effective in reducing PEP incidence, while no benefit was noted with pancreatic duct (PD) stents (RR 1.25, 95%CI 0.91-1.73). In patients receiving rectal NSAIDs (n = 2617), difficult cannulation (RR 1.99, 1.45-2.73), contrast injection into the pancreatic duct (PD) (RR2.37, 1.68-3.32), and prior history of PEP (RR 1.90, 1.06-3.41) were associated with increased PEP risk. Conclusion: This IPDMA confirms that rectal NSAIDs and peri-procedural IVF are effective PEP prophylactic strategies. Further studies focusing on combination therapy or the development of personalized PEP risk calculators are needed to improve prophylactic strategies.