Browsing by Author "Lakhtakia, Sundeep"

Now showing 1 - 3 of 3
  • 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
    Safety and efficacy of lumen-apposing metal stents versus plastic stents to treat walled-off pancreatic necrosis: systematic review and meta-analysis
    (Thieme, 2020-11) Chandrasekhara, Vinay; Barthet, Marc; Devière, Jacques; Bazerbachi, Fateh; Lakhtakia, Sundeep; Easler, Jeffrey J.; Peetermans, Joyce A.; McMullen, Edmund; Gjata, Ornela; Gourlay, Margaret L.; Abu Dayyeh, Barham K.; Medicine, School of Medicine
    Background and study aims Lumen-apposing metal stents (LAMS) are increasingly used for drainage of walled-off pancreatic necrosis (WON). Recent studies suggested greater adverse event (AE) rates with LAMS for WON. We conducted a systematic review and meta-analysis to compare the safety and efficacy of LAMS with double-pigtail plastic stents (DPPS) for endoscopic drainage of WON. The primary aim was to evaluate stent-related AEs. Methods In October 2019, we searched the Ovid (Embase, MEDLINE, Cochrane) and Scopus databases for studies assessing a specific LAMS or DPPS for WON drainage conducted under EUS guidance. Safety outcomes were AE rates of bleeding, stent migration, perforation, and stent occlusion. Efficacy outcomes were WON resolution and number of procedures needed to achieve resolution. A subanalysis including non-EUS-guided cases was performed. Results Thirty studies including one randomized controlled trial (total 1,524 patients) were analyzed. LAMS were associated with similar bleeding (2.5 % vs. 4.6 %, P = 0.39) and perforation risk (0.5 % vs. 1.1 %, P = 0.35) compared to DPPS. WON resolution (87.4 % vs. 87.5 %, P = 0.99), number of procedures to achieve resolution (2.09 vs. 1.88, P = 0.72), stent migration (5.9 % vs. 6.8 %, P = 0.79), and stent occlusion (3.8 % vs. 5.2 %, P = 0.78) were similar for both groups. Inclusion of non-EUS-guided cases led to significantly higher DPPS bleeding and perforation rates. Conclusions LAMS and DPPS were associated with similar rates of AEs and WON resolution when limiting analysis to EUS-guided cases. Higher bleeding rates were seen in historical studies of DPPS without EUS guidance. Additional high-quality studies of WON treatment using consistent outcome definitions are needed.
  • Thumbnail Image
    Item
    Soft self-expandable metal stent to treat painful pancreatic duct strictures secondary to chronic pancreatitis: a prospective multicenter trial
    (Elsevier, 2023) Sherman, Stuart; Kozarek, Richard A.; Costamagna, Guido; Reddy, Nageshwar; Tarnasky, Paul; Shah, Raj J.; Slivka, Adam; Fogel, Evan; Watkins, James; Delhaye, Myriam; Irani, Shayan S.; Tringali, Andrea; Lakhtakia, Sundeep; Kedia, Prashant; Edmundowicz, Steven; Peetermans, Joyce A.; Rousseau, Matthew J.; Devière, Jacques; Pancreatic SEMS in Chronic Pancreatitis Study Group; Medicine, School of Medicine
    Background and aims: Fully covered self-expandable metal stents (FCSEMSs) may offer a treatment option for pain associated with a dilated pancreatic duct (PD) in chronic pancreatitis (CP), but optimal patient selection and FCSEMS design, efficacy, and safety remain uncertain. We studied an investigational pancreatic FCSEMS for treatment of CP-associated pain. Methods: Patients with painful CP, a dominant distal PD stricture, and PD dilation upstream were enrolled in a prospective, multicenter, single-arm trial studying 6-month indwell of a 4- to 6-cm-long soft pancreatic FCSEMS. Primary efficacy and safety endpoints were pain reduction 6 months after FCSEMS indwell (performance goal ≥53%) and PD stenting-related serious adverse events (SAEs), respectively (performance goal <32%). The primary efficacy endpoint was assessed in patients with sufficiently severe and frequent pain at FCSEMS placement as a first stent or in exchange of a plastic stent. Results: Among 67 patients (mean age, 52.7 ± 12.5 years; mean time since CP diagnosis, 6.4 ± 6.4 years), 34 (50.7%) had plastic stent placement within 90 days of FCSEMS placement, and 46 patients were eligible for the primary efficacy endpoint analysis. Technical success was 97.0% (65/67). The observed primary efficacy (26.1%, 12/46) and safety endpoints (31.3%, 21/67) failed to meet the a priori study hypotheses. Study stent migration occurred in 47.7% of patients (31/65). Conclusions: Six-month treatment with an FCSEMS did not lead to an expected degree of pain reduction, and migrations and SAEs were common. Further study is needed to clarify optimal decompressive strategy, FCSEMS design, and patient selection.