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 one-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 twenty PEP risk factors and 5 prophylactic interventions (rectal non-steroidal anti-inflammatory drugs [NSAID], aggressive hydration, combined rectal NSAID and aggressive hydration, pancreatic duct [PD] stenting, and combined rectal NSAID and PD stenting). The resulting GBM model had an AUC of 0.70 (65% specificity, 65% sensitivity, 95% negative predictive value, 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 post-procedure monitoring.
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.
METHODS: We conducted a cross-sectional, observational, retrospective study across 6 continents, 70 countries, and 457 stroke centers. Diagnoses were identified by their ICD-10 codes or classifications in stroke databases.
RESULTS: There were 91,373 stroke admissions in the 4 months immediately before compared to 80,894 admissions during the pandemic months, representing an 11.5% (95% confidence interval [CI] -11.7 to -11.3, p < 0.0001) decline. There were 13,334 IVT therapies in the 4 months preceding compared to 11,570 procedures during the pandemic, representing a 13.2% (95% CI -13.8 to -12.7, p < 0.0001) drop. Interfacility IVT transfers decreased from 1,337 to 1,178, or an 11.9% decrease (95% CI -13.7 to -10.3, p = 0.001). Recovery of stroke hospitalization volume (9.5%, 95% CI 9.2-9.8, p < 0.0001) was noted over the 2 later (May, June) vs the 2 earlier (March, April) pandemic months. There was a 1.48% stroke rate across 119,967 COVID-19 hospitalizations. Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection was noted in 3.3% (1,722/52,026) of all stroke admissions.
CONCLUSIONS: The COVID-19 pandemic was associated with a global decline in the volume of stroke hospitalizations, IVT, and interfacility IVT transfers. Primary stroke centers and centers with higher COVID-19 inpatient volumes experienced steeper declines. Recovery of stroke hospitalization was noted in the later pandemic months.