1
|
Steinway SN, Tang B, Telezing J, Ashok A, Kamal A, Yu CY, Jagtap N, Buxbaum JL, Elmunzer J, Wani SB, Khashab MA, Caffo BS, Akshintala VS. A machine learning-based choledocholithiasis prediction tool to improve ERCP decision making: a proof-of-concept study. Endoscopy 2024; 56:165-171. [PMID: 37699524 DOI: 10.1055/a-2174-0534] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 09/14/2023]
Abstract
BACKGROUND Previous studies demonstrated limited accuracy of existing guidelines for predicting choledocholithiasis, leading to overutilization of endoscopic retrograde cholangiopancreatography (ERCP). More accurate stratification may improve patient selection for ERCP and allow use of lower-risk modalities. METHODS A machine learning model was developed using patient information from two published cohort studies that evaluated performance of guidelines in predicting choledocholithiasis. Prediction models were developed using the gradient boosting model (GBM) machine learning method. GBM performance was evaluated using 10-fold cross-validation and area under the receiver operating characteristic curve (AUC). Important predictors of choledocholithiasis were identified based on relative importance in the GBM. RESULTS 1378 patients (mean age 43.3 years; 61.2% female) were included in the GBM and 59.4% had choledocholithiasis. Eight variables were identified as predictors of choledocholithiasis. The GBM had accuracy of 71.5% (SD 2.5%) (AUC 0.79 [SD 0.06]) and performed better than the 2019 American Society for Gastrointestinal Endoscopy (ASGE) guidelines (accuracy 62.4% [SD 2.6%]; AUC 0.63 [SD 0.03]) and European Society of Gastrointestinal Endoscopy (ESGE) guidelines (accuracy 62.8% [SD 2.6%]; AUC 0.67 [SD 0.02]). The GBM correctly categorized 22% of patients directed to unnecessary ERCP by ASGE guidelines, and appropriately recommended as the next management step 48% of ERCPs incorrectly rejected by ESGE guidelines. CONCLUSIONS A machine learning-based tool was created, providing real-time, personalized, objective probability of choledocholithiasis and ERCP recommendations. This more accurately directed ERCP use than existing ASGE and ESGE guidelines, and has the potential to reduce morbidity associated with ERCP or missed choledocholithiasis.
Collapse
Affiliation(s)
- Steven N Steinway
- Division of Gastroenterology and Hepatology, Johns Hopkins Medical Institutions, Baltimore, United States
| | - Bohao Tang
- Department of Biostatistics, Johns Hopkins Bloomberg School of Public Health, Baltimore, United States
| | - Jeremy Telezing
- Department of Biostatistics, Johns Hopkins Bloomberg School of Public Health, Baltimore, United States
| | - Aditya Ashok
- Division of Gastroenterology and Hepatology, Johns Hopkins Medical Institutions, Baltimore, United States
| | - Ayesha Kamal
- Division of Gastroenterology and Hepatology, Johns Hopkins Medical Institutions, Baltimore, United States
| | - Chung Yao Yu
- Division of Gastroenterology, University of Southern California Keck School of Medicine, Los Angeles, United States
| | - Nitin Jagtap
- Department of Gastroenterology, Asian Institute of Gastroenterology, Hyderabad, India
| | - James L Buxbaum
- Division of Gastroenterology, University of Southern California Keck School of Medicine, San Francisco, United States
| | - Joseph Elmunzer
- Division of Gastroenterology and Hepatology, Medical University of South Carolina, Charleston, United States
| | - Sachin B Wani
- Division of Gastroenterology, University of Colorado Anschutz Medical Campus, Aurora, United States
| | - Mouen A Khashab
- Division of Gastroenterology and Hepatology, Johns Hopkins Medical Institutions, Baltimore, United States
| | - Brian S Caffo
- Department of Biostatistics, Johns Hopkins Bloomberg School of Public Health, Baltimore, United States
| | - Venkata S Akshintala
- Division of Gastroenterology and Hepatology, Johns Hopkins Medical Institutions, Baltimore, United States
| |
Collapse
|
2
|
Law R, Perez-Miranda M. A ghost in the machine: is machine learning necessary for prediction of choledocholithiasis? Endoscopy 2024; 56:172-173. [PMID: 38262425 DOI: 10.1055/a-2233-0136] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 01/25/2024]
Affiliation(s)
- Ryan Law
- Division of Gastroenterology and Hepatology, Mayo Clinic, Rochester, United States
| | - Manuel Perez-Miranda
- Gastroenterology Department, Hospital Universitario Rio Hortega, Valladolid, Spain
| |
Collapse
|
3
|
Lattanzi B, Ramai D, Gkolfakis P, Facciorusso A. Predictive models in EUS/ERCP. Best Pract Res Clin Gastroenterol 2023; 67:101856. [PMID: 38103924 DOI: 10.1016/j.bpg.2023.101856] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/10/2023] [Accepted: 07/30/2023] [Indexed: 12/19/2023]
Abstract
Predictive models (PMs) in endoscopic retrograde cholangiopancreatography (ERCP) and endoscopic ultrasound (EUS) have the potential to improve patient outcomes, enhance diagnostic accuracy, and guide therapeutic interventions. This review aims to summarize the current state of predictive models in ERCP and EUS and their clinical implications. To be considered useful in clinical practice a PM should be accurate, easy to perform, and may consider objective variables. PMs in ERCP estimate correct indication, probability of success, and the risk of developing adverse events. These models incorporate patient-related factors and technical aspects of the procedure. In the field of EUS, these models utilize clinical and imaging data to predict the likelihood of malignancy, presence of specific lesions, or risk of complications related to therapeutic interventions. Further research, validation, and refinement are necessary to maximize the utility and impact of these models in routine clinical practice.
Collapse
Affiliation(s)
- Barbara Lattanzi
- Gastroenterology and Emergency Endoscopy Unit, Sandro Pertini Hospital of Rome, Italy.
| | - Daryl Ramai
- Gastroenterology and Hepatology, University of Utah Hospital, Utah, USA.
| | - Paraskevas Gkolfakis
- Department of Gastroenterology, General Hospital of Nea Ionia "Konstantopoulio-Patision", 14233, Athens, Greece.
| | - Antonio Facciorusso
- Gastroenterology Unit, Department of Medical Sciences, University of Foggia, Via Pinto 1, 71122, Foggia, Italy.
| |
Collapse
|
4
|
Engin AB, Engin A, Engin ED, Memis L. Does lithium attenuate the liver damage due to oxidative stress and liver glycogen depletion in experimental common bile duct obstruction? Toxicol Appl Pharmacol 2023; 466:116489. [PMID: 36963521 DOI: 10.1016/j.taap.2023.116489] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/08/2022] [Revised: 03/20/2023] [Accepted: 03/21/2023] [Indexed: 03/26/2023]
Abstract
In extrahepatic cholestasis, the molecular mechanisms of liver damage due to bile acid accumulation remain elusive. In this study, the activation of glutamatergic receptors was hypothesized to be responsible for bile acid-induced oxidative stress and liver damage. Recent evidence showed that lithium, as an N-methyl-d-aspartate receptor (NMDAR) GluN2B subunit inhibitor, may act on the glutamate/NMDAR signaling axis. Guinea pigs were assigned to four groups, as sham laparotomy (SL), bile duct ligated (BDL), lithium-treated SL (SL + Li) and lithium-treated BDL (BDL + Li) groups. Cholestasis-induced liver injury was evaluated by aspartate aminotransferase (AST), alanine transaminase (ALT), interleukin-6 (IL-6), tissue malondialdehyde (MDA), copper‑zinc superoxide dismutase and reduced glutathione levels. The liability of glutamate/NMDAR signaling axis was clarified by glutamate levels in both plasma and liver samples, with the production of nitric oxide (NO), as well as with the serum calcium concentrations. Blood glucose, glucagon, insulin levels and glucose consumption rates, in addition to tissue glycogen were measured to evaluate the liver glucose-glycogen metabolism. A high liver damage index (AST/ALT) was calculated in BDL animals in comparison to SL group. In the BDL animals, lithium reduced plasma NO and glutamate in addition to tissue glutamate concentrations, while serum calcium increased. The antioxidant capacities and liver glycogen contents significantly increased, whereas blood glucose levels unchanged and tissue MDA levels decreased 3-fold in lithium-treated cholestatic animals. It was concluded that lithium largely protects the cholestatic hepatocyte from bile acid-mediated damage by blocking the NMDAR-GluN2B subunit.
Collapse
Affiliation(s)
- Ayse Basak Engin
- Gazi University, Faculty of Pharmacy, Department of Toxicology, Ankara, Turkey.
| | - Atilla Engin
- Gazi University, Faculty of Medicine, Department of General Surgery, Ankara, Turkey
| | - Evren Doruk Engin
- Ankara University, Biotechnology Institute, Gumusdere Campus, Kecioren, Ankara, Turkey
| | - Leyla Memis
- Gazi University, Faculty of Medicine, Department of Pathology, Ankara, Turkey
| |
Collapse
|
5
|
Test Performance Characteristics of Dynamic Liver Enzyme Trends in the Prediction of Choledocholithiasis. J Clin Med 2022; 11:jcm11154575. [PMID: 35956191 PMCID: PMC9369577 DOI: 10.3390/jcm11154575] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/18/2022] [Revised: 07/18/2022] [Accepted: 08/02/2022] [Indexed: 11/17/2022] Open
Abstract
(1) Background: Various methods to predict the presence or absence of choledocholithiasis (CDL) have been proposed. We aimed to assess the performance characteristics of dynamic liver enzyme trends in the prediction of CDL. (2) Methods: This was a single-center retrospective cohort study. All adult in-patients undergoing endoscopy for suspected CDL between 1 January 2012 and 7 October 2018 were identified, with patients with prior cholecystectomy, prior sphincterotomy, or indwelling biliary prostheses were excluded. Available laboratory parameters within 72 h preceding the procedure were recorded, allowing for the assessment of trends. Dynamic enzyme trends were defined as any increase or decrease by 30% and 50% within 72 h of the index procedure. (3) Results: A total of 878 patients were included. Mean age was 61.8 years, with 58.6% female. Increases in alkaline phosphatase (ALP) of at least 30% or 50% were both specific for the presence of CDL, with specificities of 82.7% (95% CI 69.7–91.8%) and 88.5% (95% CI 76.6–95.6%), respectively. Decreases in bilirubin or ALP of at least 50% were highly specific for the absence of CDL, with specificities of 91.7% (95% CI 85.7–95.8%) and 100.0% (97.2–100.0%), respectively. (4) Conclusions: Several liver enzyme trends appear to be specific for the absence or presence of stones; in particular, significant decreases in total bilirubin or ALP of at least 30–50% over the prior 72 h appear to be especially predictive of an absence of intraductal findings during endoscopy.
Collapse
|
6
|
Dalai C, Azizian J, Trieu H, Rajan A, Chen F, Dong T, Beaven S, Tabibian JH. Machine learning models compared to existing criteria for noninvasive prediction of endoscopic retrograde cholangiopancreatography-confirmed choledocholithiasis. LIVER RESEARCH 2021; 5:224-231. [PMID: 35186364 PMCID: PMC8855981 DOI: 10.1016/j.livres.2021.10.001] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 02/09/2023]
Abstract
BACKGROUND AND AIMS Noninvasive predictors of choledocholithiasis have generally exhibited marginal performance characteristics. We aimed to identify noninvasive independent predictors of endoscopic retrograde cholangiopancreatography (ERCP)-confirmed choledocholithiasis and accordingly developed predictive machine learning models (MLMs). METHODS Clinical data of consecutive patients undergoing first-ever ERCP for suspected choledocholithiasis from 2015-2019 were abstracted from a prospectively-maintained database. Multiple logistic regression was used to identify predictors of ERCP-confirmed choledocholithiasis. MLMs were then trained to predict ERCP-confirmed choledocholithiasis using pre-ERCP ultrasound (US) imaging only and separately using all available noninvasive imaging (US/CT/magnetic resonance cholangiopancreatography). The diagnostic performance of American Society for Gastrointestinal Endoscopy (ASGE) "high-likelihood" criteria was compared to MLMs. RESULTS We identified 270 patients (mean age 46 years, 62.2% female, 73.7% Hispanic/Latino, 59% with noninvasive imaging positive for choledocholithiasis) with native papilla who underwent ERCP for suspected choledocholithiasis, of whom 230 (85.2%) were found to have ERCP-confirmed choledocholithiasis. Logistic regression identified choledocholithiasis on noninvasive imaging (odds ratio (OR) = 3.045, P = 0.004) and common bile duct (CBD) diameter on noninvasive imaging (OR=1.157, P = 0.011) as predictors of ERCP-confirmed choledocholithiasis. Among the various MLMs trained, the random forest-based MLM performed best; sensitivity was 61.4% and 77.3% and specificity was 100% and 75.0%, using US-only and using all available imaging, respectively. ASGE high-likelihood criteria demonstrated sensitivity of 90.9% and specificity of 25.0%; using cut-points achieving this specificity, MLMs achieved sensitivity up to 97.7%. CONCLUSIONS MLMs using age, sex, race, presence of diabetes, fever, body mass index (BMI), total bilirubin, maximum CBD diameter, and choledocholithiasis on pre-ERCP noninvasive imaging predict ERCP-confirmed choledocholithiasis with good sensitivity and specificity and outperform the ASGE criteria for patients with suspected choledocholithiasis.
Collapse
Affiliation(s)
- Camellia Dalai
- UCLA-Olive View Internal Medicine Residency Program, Department of Medicine, Olive View-UCLA Medical Center, Sylmar, CA, USA
| | - John Azizian
- UCLA-Olive View Internal Medicine Residency Program, Department of Medicine, Olive View-UCLA Medical Center, Sylmar, CA, USA
| | - Harry Trieu
- Keck School of Medicine, University of Southern California, Los Angeles, CA, USA
| | - Anand Rajan
- UCLA-Olive View Internal Medicine Residency Program, Department of Medicine, Olive View-UCLA Medical Center, Sylmar, CA, USA
| | - Formosa Chen
- Department of Surgery, David Geffen School of Medicine at UCLA, Los Angeles, CA, USA
| | - Tien Dong
- Tamar and Vatche Manoukian Division of Digestive Diseases, David Geffen School of Medicine at UCLA, Los Angeles, CA, USA
| | - Simon Beaven
- Tamar and Vatche Manoukian Division of Digestive Diseases, David Geffen School of Medicine at UCLA, Los Angeles, CA, USA,Division of Gastroenterology, Department of Medicine, Olive View-UCLA Medical Center, Sylmar, CA, USA
| | - James H. Tabibian
- Tamar and Vatche Manoukian Division of Digestive Diseases, David Geffen School of Medicine at UCLA, Los Angeles, CA, USA,Division of Gastroenterology, Department of Medicine, Olive View-UCLA Medical Center, Sylmar, CA, USA
| |
Collapse
|