Current clinical algorithms for predicting common bile duct stones have only moderate accuracy

Ebrahim, Mohamed A.; Sørensen, Lars Tue; Jørgensen, Lars N.; Kalaitzakis, Evangelos

doi:10.1111/den.12994

Cited by 12 publications

(11 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Recently, with a widely open data movement, the vigorous development of deep learning methods have greatly improved ability of computer-assisted diagnosis method [2]. There are three major tasks in medical image analysis, which are image classification, detection and segmentation.…”

Section: Introductionmentioning

confidence: 99%

A novel YOLOv3-arch model for identifying cholelithiasis and classifying gallstones on CT images

et al. 2019

View full text Add to dashboard Cite

Locating diseases precisely from medical images, like ultrasonic and CT images, have been one of the most challenging problems in medical image analysis. In recent years, the vigorous development of deep learning models have greatly improved the accuracy in disease location on medical images. However, there are few artificial intelligent methods for identifying cholelithiasis and classifying gallstones on CT images, since no open source CT images dataset of cholelithiasis and gallstones is available for training the models and verifying their performance. In this paper, we build up the first medical image dataset of cholelithiasis by collecting 223846 CT images with gallstone of 1369 patients. With these CT images, a neural network is trained to “pick up” CT images of high quality as training set, and then a novel Yolo neural network, named Yolov3-arch neural network, is proposed to identify cholelithiasis and classify gallstones on CT images. Identification and classification accuracies are obtained by 10-fold cross-validations. It is obtained that our Yolov3-arch model is with average accuracy 92.7% in identifying granular gallstones and average accuracy 80.3% in identifying muddy gallstones. This achieves 3.5% and 8% improvements in identifying granular and muddy gallstones to general Yolo v3 model, respectively. Also, the average cholelithiasis identifying accuracy is improved to 86.50% from 80.75%. Meanwhile, our method can reduce the misdiagnosis rate of negative samples by the object detection model.

show abstract

Section: Introductionmentioning

confidence: 99%

A novel YOLOv3-arch model for identifying cholelithiasis and classifying gallstones on CT images

et al. 2019

View full text Add to dashboard Cite

show abstract

“…26 While some suggest that hyperbilirubinemia reflects true biliary obstruction at presentation of acute cholecystitis and pancreaticobiliary disease, another hypothesis is that it may be reactive to hepatocellular injury in the acute setting. 7,10,11,27,28 In our study, the majority of our cohort had abnormal biliary enzymes at presentation (80.6% elevated GGT, 73.5% elevated bilirubin and 55.5% elevated ALP), although most of these patients had no choledocholithiasis.…”

Section: Discussionmentioning

confidence: 51%

“…[7][8][9] However, these are of mediocre accuracy and there is no current generalized consensus on the ideal utilization of MRCP. 10 The purpose of this study was to evaluate the yield of urgent MRCPs performed for in-hospital and emergency department (ED) patients presenting with acute pancreaticobiliary disease, and to determine potential predictors of a positive study. This was done via scrutinizing multiple variables, including patient age, gender, preceding pancreaticobiliary enzymes, and results of initial US assessment.…”

Section: Introductionmentioning

confidence: 99%

The Diagnostic Yield of Magnetic Resonance Cholangiopancreatography in the Setting of Acute Pancreaticobiliary Disease — A Single Center Experience

et al. 2021

View full text Add to dashboard Cite

Purpose: To discern whether preceding ultrasound (US) results, patient demographics and biochemical markers can be implemented as predictors of an abnormal Magnetic Resonance Cholangiopancreatography (MRCP) study in the context of acute pancreaticobiliary disease. Methods: A retrospective study was performed assessing US results, age, gender, elevated lipase and biliary enzymes for consecutive patients who underwent an urgent MRCP following an initial US for acute pancreaticobiliary disease between January 2017-December 2018. Multivariable binary logistic regression models were constructed to assess for predictors of clinically significant MRCPs, and discrepant US/MRCP results. Results: A total of 155 patients (mean age 56, 111 females) were included. Age (OR 1.03, P < 0.05), hyperlipasemia (OR 5.33, P < 0.05) and a positive US (OR 40.75, P < 0.05) were found to be independent predictors for a subsequent abnormal MRCP. Contrarily, gender and elevated biliary enzymes were not reliable predictors of an abnormal MRCP, or significant MRCP/US discrepancies. Of 66 cases (43%) of discordant US/MRCPs, half had clinically significant discrepant findings such as newly discovered choledocholithiasis and pancreaticobiliary neoplasia. Age was the sole predictor for a significant US/MRCP discrepancy, with 2% increase in the odds of a significant discrepancy per year of increase in age. Conclusion: An abnormal US, hyperlipasemia and increased age serve as predictors for a subsequent abnormal MRCP, as opposed to gender and biliary enzyme elevation. Age was the sole predictor of a significant US/MRCP discrepancy that provided new information which significantly impacted subsequent management. In the remaining cases, however, MRCP proved useful in reaffirming the clinical diagnosis and avoiding further investigations.

show abstract

“…The guideline recommended that endoscopy or surgery should be performed for high-risk patients to remove stones, while those patients with intermediate risk should further make a definite diagnosis by EUS or MRCP [14]. However, several studies showed unsatisfactory diagnostic accuracy of ASGE guideline for predicting CBD stones [15,16]. MRCP is widely accepted as a non-invasive diagnostic method with high sensitivity and specificity, but it is time-consuming, relatively expensive, and its diagnostic accuracy mainly depends on the image quality and radiologist's experience.…”

Section: Discussionmentioning

confidence: 99%

A Nomogram for Predicting the Risk of Common Bile Duct Stones Based on Preoperative Laboratory Tests and Ultrasonography 

Wang

Zhu

et al. 2021

Preprint

View full text Add to dashboard Cite

Objective: The objective of this study was to determine the predictive factors for common bile duct (CBD) stone and establish a nomogram model based on the preoperative laboratory tests and imaging findings.Methods: A total of 1701 patients who underwent laparoscopic cholecystectomy (LC) combined with common bile duct exploration (CBDE) for suspected choledochlithiasis from November 2014 to October 2020 were eligible for this analysis. All patients were divided into the training set (from November 2014 to November 2019, n=1,453) and validation set (from November 2019 to October 2020, n=248) based on the admission time. The predictive factors for CBD stone were determined by the univariate and multivariate logistic regression model. A nomogram model for predicting the presence of CBD stone was developed based on significant variables, and receiver operating characteristic (ROC) curve, calibration plot and decision curve analysis (DCA) were used to assess the predictive performance of the nomogram. Results: The results of multivariate logistic regression analysis demonstrated that multiple gallbladder stones (OR: 7.463, 95%CI: 5.437-10.243, P<0.001), the maximal diameter of CBD stone measured by preoperative ultrasonography (OR for 0.8-1.5 cm: 4.756, 95%CI: 3.513-6.438, P<0.001; OR for 1.5-2.0 cm: 9.597, 95%CI: 4.621-19.931, P<0.001; OR for >2.0 cm: 24.473, 95%CI: 2.809-213.207, P<0.001), preoperative GGT level (OR for 90-225 U/L: 2.828, 95%CI: 1.898-4.214, P<0.001; OR for 225-450 U/L: 9.994, 95%CI: 4.668-21.403, P<0.001; OR for >450 U/L: 12.535, 95%CI: 4.452-35.292, P<0.001) and DB/TB ratio (OR: 394.329, 95%CI: 79.575-1954.064, P<0.001) were independent predictive factors for CBD stone. The nomogram model for predicting the presence of CBD stone was developed based on the above-mentioned variables. ROC curve showed that the C-index of the nomogram model for the training set and validation set was 0.875 (95% CI: 0.857-0.893) and 0.834 (95% CI: 0.784-0.883), which were better than that of MRCP for preoperative diagnosis of CBD stone. The calibration curve and DCA curve demonstrated that the nomogram model had a good clinical utility for predicting the presence of CBD stone .Conclusion: The nomogram based on preoperative laboratory tests and ultrasonography had an excellent predictive power for CBD stone, and it might provide useful information for making treatment strategies.

show abstract

Current clinical algorithms for predicting common bile duct stones have only moderate accuracy

Abstract: Three diagnostic algorithms commonly used for predicting CBD stones have comparable but only moderate accuracy. Further research is warranted to improve risk stratification of patients with suspected CBD stones.

Cited by 12 publications

References 25 publications

A novel YOLOv3-arch model for identifying cholelithiasis and classifying gallstones on CT images

A novel YOLOv3-arch model for identifying cholelithiasis and classifying gallstones on CT images

The Diagnostic Yield of Magnetic Resonance Cholangiopancreatography in the Setting of Acute Pancreaticobiliary Disease — A Single Center Experience

A Nomogram for Predicting the Risk of Common Bile Duct Stones Based on Preoperative Laboratory Tests and Ultrasonography

Contact Info

Product

Resources

About

Current clinical algorithms for predicting common bile duct stones have only moderate accuracy

Abstract: Three diagnostic algorithms commonly used for predicting CBD stones have comparable but only moderate accuracy. Further research is warranted to improve risk stratification of patients with suspected CBD stones.

Cited by 12 publications

References 25 publications

A novel YOLOv3-arch model for identifying cholelithiasis and classifying gallstones on CT images

A novel YOLOv3-arch model for identifying cholelithiasis and classifying gallstones on CT images

The Diagnostic Yield of Magnetic Resonance Cholangiopancreatography in the Setting of Acute Pancreaticobiliary Disease — A Single Center Experience

A Nomogram for Predicting the Risk of Common Bile Duct Stones Based on Preoperative Laboratory Tests and Ultrasonography&nbsp;

Contact Info

Product

Resources

About

A Nomogram for Predicting the Risk of Common Bile Duct Stones Based on Preoperative Laboratory Tests and Ultrasonography