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.
METHODS: Plasma concentrations of artesunic acid and dihydroartemisinin were determined simultaneously by HPLC with electrochemical detection. The test drug was well tolerated and no undesirable adverse effects were observed.
RESULTS: Comparison of pharmacokinetic parameters of artesunic acid after oral and rectal administration showed statistically significant differences in t(max) and AUC, with no changes for Cmax and t1/2. As for dihydroartemisinin, differences were observed for t(max) and Cmax but not for AUC.
CONCLUSION: There appear to be pharmacokinetic differences between oral and rectal modes of administration. The significance of these findings should be explored in malaria patients before appropriate therapeutic regimens are devised.
AIMS: The aims of this study were to determine the efficacy of rectal diclofenac in preventing PEP and to evaluate any adverse events.
METHODS: This was a randomized, open-label, two-arm, prospective clinical trial. Only patients at high risk of developing PEP were recruited. They received 100 mg rectal diclofenac or no intervention immediately after ERCP. The patients were reviewed 30 days after discharge to evaluate any adverse event.
RESULTS: Among 144 recruited patients, 69 (47.9%) received diclofenac and 75 (52.1%) had no intervention. Eleven patients (7.6%) developed PEP, in which seven were from the diclofenac group and four were in the control group. Eight cases of PEP (5.5%) were mild and three cases (2.1%) were moderate. The differences in pancreatitis incidence and severity between both groups were not statistically significant. There were 11 adverse events reported. Clinically significant bleeding happened in four patients (2.8%): one from the diclofenac group and three from the control group. Other events included cholangitis: two patients (2.9%) from the diclofenac group and four (5.3%) from the control group. One patient from the diclofenac group (1.4%) had a perforation which was treated conservatively.
CONCLUSIONS: In summary, prophylactic rectal diclofenac did not significantly decrease the incidence of PEP among patients at high risk for developing PEP. However, the administration of diclofenac was fairly safe with few clinical adverse events.