Camellia Dalai1, John Azizian1, Harry Trieu2, Anand Rajan1, Formosa Chen3, Tien Dong4, Simon Beaven4,5, James H Tabibian4,5. 1. UCLA-Olive View Internal Medicine Residency Program, Department of Medicine, Olive View-UCLA Medical Center, Sylmar, CA, USA. 2. Keck School of Medicine, University of Southern California, Los Angeles, CA, USA. 3. Department of Surgery, David Geffen School of Medicine at UCLA, Los Angeles, CA, USA. 4. Tamar and Vatche Manoukian Division of Digestive Diseases, David Geffen School of Medicine at UCLA, Los Angeles, CA, USA. 5. Division of Gastroenterology, Department of Medicine, Olive View-UCLA Medical Center, Sylmar, CA, USA.
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.
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.
Entities:
Keywords:
Bile duct disorders; Common bile duct stones; Endoscopic retrograde cholangiopancreatography (ERCP); Gallstones; Machine learning models (MLMs); Noninvasive imaging
Authors: John T Maple; Tamir Ben-Menachem; Michelle A Anderson; Vasundhara Appalaneni; Subhas Banerjee; Brooks D Cash; Laurel Fisher; M Edwyn Harrison; Robert D Fanelli; Norio Fukami; Steven O Ikenberry; Rajeev Jain; Khalid Khan; Mary Lee Krinsky; Laura Strohmeyer; Jason A Dominitz Journal: Gastrointest Endosc Date: 2010-01 Impact factor: 9.427
Authors: P A Abboud; P F Malet; J A Berlin; R Staroscik; M D Cabana; J R Clarke; J A Shea; J S Schwartz; S V Williams Journal: Gastrointest Endosc Date: 1996-10 Impact factor: 9.427
Authors: James L Buxbaum; Syed M Abbas Fehmi; Shahnaz Sultan; Douglas S Fishman; Bashar J Qumseya; Victoria K Cortessis; Hannah Schilperoort; Lynn Kysh; Lea Matsuoka; Patrick Yachimski; Deepak Agrawal; Suryakanth R Gurudu; Laith H Jamil; Terry L Jue; Mouen A Khashab; Joanna K Law; Jeffrey K Lee; Mariam Naveed; Mandeep S Sawhney; Nirav Thosani; Julie Yang; Sachin B Wani Journal: Gastrointest Endosc Date: 2019-04-09 Impact factor: 9.427
Authors: Chung Yao Yu; Nitzan Roth; Niraj Jani; Jaehoon Cho; Jacques Van Dam; Rick Selby; James Buxbaum Journal: Surg Endosc Date: 2019-03-25 Impact factor: 4.584
Authors: B A Chapman; I R Wilson; C M Frampton; R J Chisholm; N R Stewart; G M Eagar; R B Allan Journal: Dig Dis Sci Date: 1996-11 Impact factor: 3.199
Authors: V Parra Pérez; G Vargas Cárdenas; M Astete Benavides; M Valdivia Roldán; L Morán Tisoc; N Nuñez Calixto; M Chávez Rossell; C Mayurí Bravo De Rueda Journal: Rev Gastroenterol Peru Date: 2007 Apr-Jun
Authors: Mark W Russo; Jeffrey T Wei; Michelle T Thiny; Lisa M Gangarosa; Alphonso Brown; Yehuda Ringel; Nicholas J Shaheen; Robert S Sandler Journal: Gastroenterology Date: 2004-05 Impact factor: 22.682