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 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.