The prediction of common bile duct stones using a neural network

A machine learning-based choledocholithiasis prediction tool to improve ERCP decision making: a proof-of-concept study

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.

Comprehensive Review on the Use of Artificial Intelligence in Ophthalmology and Future Research Directions

BACKGROUND

Having several applications in medicine, and in ophthalmology in particular, artificial intelligence (AI) tools have been used to detect visual function deficits, thus playing a key role in diagnosing eye diseases and in predicting the evolution of these common and disabling diseases. AI tools, i.e., artificial neural networks (ANNs), are progressively involved in detecting and customized control of ophthalmic diseases. The studies that refer to the efficiency of AI in medicine and especially in ophthalmology were analyzed in this review.

MATERIALS AND METHODS

We conducted a comprehensive review in order to collect all accounts published between 2015 and 2022 that refer to these applications of AI in medicine and especially in ophthalmology. Neural networks have a major role in establishing the demand to initiate preliminary anti-glaucoma therapy to stop the advance of the disease.

RESULTS

Different surveys in the literature review show the remarkable benefit of these AI tools in ophthalmology in evaluating the visual field, optic nerve, and retinal nerve fiber layer, thus ensuring a higher precision in detecting advances in glaucoma and retinal shifts in diabetes. We thus identified 1762 applications of artificial intelligence in ophthalmology: review articles and research articles (301 pub med, 144 scopus, 445 web of science, 872 science direct). Of these, we analyzed 70 articles and review papers (diabetic retinopathy (N = 24), glaucoma (N = 24), DMLV (N = 15), other pathologies (N = 7)) after applying the inclusion and exclusion criteria.

CONCLUSION

In medicine, AI tools are used in surgery, radiology, gynecology, oncology, etc., in making a diagnosis, predicting the evolution of a disease, and assessing the prognosis in patients with oncological pathologies. In ophthalmology, AI potentially increases the patient's access to screening/clinical diagnosis and decreases healthcare costs, mainly when there is a high risk of disease or communities face financial shortages. AI/DL (deep learning) algorithms using both OCT and FO images will change image analysis techniques and methodologies. Optimizing these (combined) technologies will accelerate progress in this area.

Application of artificial intelligence in pancreaticobiliary diseases

The role of artificial intelligence and its applications has been increasing at a rapid pace in the field of gastroenterology. The application of artificial intelligence in gastroenterology ranges from colon cancer screening and characterization of dysplastic and neoplastic polyps to the endoscopic ultrasonographic evaluation of pancreatic diseases. Artificial intelligence has been found to be useful in the evaluation and enhancement of the quality measure for endoscopic retrograde cholangiopancreatography. Similarly, artificial intelligence techniques like artificial neural networks and faster region-based convolution network are showing promising results in early and accurate diagnosis of pancreatic cancer and its differentiation from chronic pancreatitis. Other artificial intelligence techniques like radiomics-based computer-aided diagnosis systems could help to differentiate between various types of cystic pancreatic lesions. Artificial intelligence and computer-aided systems also showing promising results in the diagnosis of cholangiocarcinoma and the prediction of choledocholithiasis. In this review, we discuss the role of artificial intelligence in establishing diagnosis, prognosis, predicting response to treatment, and guiding therapeutics in the pancreaticobiliary system.

Scope of Artificial Intelligence in Screening and Diagnosis of Colorectal Cancer

Globally, colorectal cancer is the third most diagnosed malignancy. It causes significant mortality and morbidity, which can be reduced by early diagnosis with an effective screening test. Integrating artificial intelligence (AI) and computer-aided detection (CAD) with screening methods has shown promising colorectal cancer screening results. AI could provide a “second look” for endoscopists to decrease the rate of missed polyps during a colonoscopy. It can also improve detection and characterization of polyps by integration with colonoscopy and various advanced endoscopic modalities such as magnifying narrow-band imaging, endocytoscopy, confocal endomicroscopy, laser-induced fluorescence spectroscopy, and magnifying chromoendoscopy. This descriptive review discusses various AI and CAD applications in colorectal cancer screening, polyp detection, and characterization.

Regression tree for choledocholithiasis prediction

OBJECTIVES

The aim of this study was to develop and compare the predictive accuracy of classification and regression tree (CART) analysis with logistic regression (LR) for predicting common bile duct stones (CBDS) in patients subjected to laparoscopic cholecystectomy.

PATIENTS AND METHODS

We prospectively collected preoperative (demographic, biochemical, ultrasonographic) and intraoperative (intraoperative cholangiography, cystic duct diameter) data for 154 patients considered for elective laparoscopic cholecystectomy at the department of General Surgery at Gornji Milanovac from 2013 through 2014. Univariate and multivariate regression analyses were used to determine independent predictors of CBDS. The CART analysis was carried out using the predictors identified by LR analysis. Various measures for the assessment of risk prediction models were determined, such as predictive ability, accuracy, the area under the receiver operating characteristic curve, and clinical utility using decision curve analysis.

RESULTS

The most decisive variable at the time of classification was the cystic duct diameter category, the alkaline phosphatase, and dangerous stones. The CART model was shown to have good discriminatory ability (93.9%). Accuracy was similar in both models, ranging from 92.9% in the CART model and 93.5% in the LR model. In decision curve analysis, the CART model outperformed the LR model.

CONCLUSION

We developed a user-friendly risk model that can successfully predict the presence of choledocholithiasis in patients planned for elective cholecystectomy. However, before recommending its use in clinical practice, a larger and more complete database should be used to further clarify the differences between models in terms of prediction of the CBDS.

Artificial neural network predicts the need for therapeutic ERCP in patients with suspected choledocholithiasis

BACKGROUND

Selection of patients with the highest probability for therapeutic ERCP remains an important task in a clinical workup of patients with suspected choledocholithiasis (CDL).

OBJECTIVE

To determine whether an artificial neural network (ANN) model can improve the accuracy of selecting patients with a high probability of undergoing therapeutic ERCP among those with strong clinical suspicion of CDL and to compare it with our previously reported prediction model.

DESIGN

Prospective, observational study.

SETTING

Single, tertiary-care endoscopy center.

PATIENTS

Between January 2010 and September 2012, we prospectively recruited 291 consecutive patients who underwent ERCP after being referred to our center with firm suspicion for CDL.

INTERVENTIONS

Predictive scores for CDL based on a multivariate logistic regression model and ANN model.

MAIN OUTCOME MEASUREMENTS

The presence of common bile duct stones confirmed by ERCP.

RESULTS

There were 80.4% of patients with positive findings on ERCP. The area under the receiver-operating characteristic curve for our previously established multivariate logistic regression model was 0.787 (95% CI, 0.720-0.854; P < .001), whereas area under the curve for the ANN model was 0.884 (95% CI, 0.831-0.938; P < .001). The ANN model correctly classified 92.3% of patients with positive findings on ERCP and 69.6% patients with negative findings on ERCP.

LIMITATIONS

Only those variables believed to be related to the outcome of interest were included. The majority of patients in our sample had positive findings on ERCP.

CONCLUSIONS

An ANN model has better discriminant ability and accuracy than a multivariate logistic regression model in selecting patients for therapeutic ERCP.

Prediction of conversion of laparoscopic cholecystectomy to open surgery with artificial neural networks

Background

The intent of this study was to predict conversion of laparoscopic cholecystectomy (LC) to open surgery employing artificial neural networks (ANN).

Methods

The retrospective data of 793 patients who underwent LC in a teaching university hospital from 1997 to 2004 was collected. We employed linear discrimination analysis and ANN models to examine the predictability of the conversion. The models were validated using prospective data of 100 patients who underwent LC at the same hospital.

Results

The overall conversion rate was 9%. Conversion correlated with experience of surgeons, emergency LC, previous abdominal surgery, fever, leukocytosis, elevated bilirubin and alkaline phosphatase levels, and ultrasonographic detection of common bile duct stones. In the validation group, discriminant analysis formula diagnosed the conversion in 5 cases out of 9 (sensitivity: 56%; specificity: 82%); the ANN model diagnosed 6 cases (sensitivity: 67%; specificity: 99%).

Conclusion

The conversion of LC to open surgery is effectively predictable based on the preoperative health characteristics of patients using ANN.

Recurrent acute biliary pancreatitis: the protective role of cholecystectomy and endoscopic sphincterotomy

BACKGROUND

Recurrent attacks of acute biliary pancreatitis (RABP) are prevented by (laparoscopic) cholecystectomy. Since the introduction of endoscopic retrograde cholangiopancreaticography (ERCP), several series have described a similar reduction of RABP after endoscopic sphincterotomy (ES). This report discusses the different treatment options for preventing RABP including conservative treatment, cholecystectomy, ES, and combinations of these options as well as their respective timing.

METHODS

A search in PubMed for observational studies and clinical (comparative) trials published in the English language was performed on the subject of recurrent acute biliary pancreatitis and other gallstone complications after an initial attack of acute pancreatitis.

RESULT

Cholecystectomy and ES both are superior to conservative treatment in reducing the incidence of RABP. Cholecystectomy provides additional protection for gallstone-related complications and mortality. Observational studies indicate that cholecystectomy combined with ES is the most effective treatment for reducing the incidence of RABP attacks.

CONCLUSION

From the literature data it can be concluded that ES is as effective in reducing RABP as cholecystectomy but inferior in reducing mortality and overall morbidity. The combination of ES and cholecystectomy seems superior to either of the treatment methods alone. A prospective randomized clinical trial comparing ES plus cholecystectomy with cholecystectomy alone is needed.

The selective use of magnetic resonance cholangiopancreatography in the imaging of the axial biliary tree in patients with acute gallstone pancreatitis

BACKGROUND

Magnetic resonance cholangiopancreatography (MRCP) is an emerging modality in the management of acute gallstone pancreatitis (AGP). The aim of this study was to assess the impact following the introduction of MRCP in the management of AGP in a tertiary referral unit.

METHODS

Patients presenting with AGP from January 2002 to December 2004 were reviewed to assess the impact of the introduction of MRCP in June 2003. The indication for MRCP was suspected common bile duct (CBD) stones in the absence of biliary sepsis. Definitive treatment for AGP was laparoscopic cholecystectomy, with endoscopic retrograde cholangiopancreatography (ERCP) and sphincterotomy reserved for patients unfit for cholecystectomy and those with biliary sepsis.

RESULTS

249 patients were identified of whom 36 (14.5%) underwent ERCP and sphincterotomy as definitive treatment. 96 patients with a non-dilated CBD and normal or resolving liver function tests proceeded to laparosocopic cholecystectomy and intraoperative cholangiogram (IOC), 8 (8.5%) of whom had CBD stones intraoperatively. Eleven patients underwent cholecystectomy during pancreatic necrosectomy. Of those undergoing preoperative diagnostic biliary tract imaging, ERCP was undertaken in 57 patients and MRCP in 49 patients. There was no significant difference in serum bilirubin levels [ERCP 43 mmol/l (18-204) vs. MRCP 39 mmol/l (24-180), p = NS] or the proportion of patients with CBD stones [ERCP 10 (17.5%) vs. MRCP 7 (14.2%), p = NS] between the two groups. Patients who underwent MRCP had a shorter median hospital stay [MRCP 5 days (range: 3-14) vs. ERCP 9 days (range: 4-20), p < 0.01] and higher rate of cholecystectomy during the index admission (MRCP 83.3% vs. ERCP 67.2%, p < 0.05). There was a high degree of correlation between preoperative MRCP results and findings of subsequent IOC or therapeutic ERCP (area under ROC curve: 0.94).

CONCLUSIONS

MRCP is an accurate modality for imaging the axial biliary tree in patients with AGP. Selective use of MRCP reduces the need for ERCP and results in shorter hospital stay. and IAP.

Design of an Artificial Neural Network for Diagnosis of Facial Pain Syndromes

A classification scheme for facial pain syndromes describing seven categories has previously been proposed. Based on this classification scheme and a binomial (yes/no) facial pain questionnaire, we have designed and trained an artificial neural network (ANN) and as an initial feasibility assessment of such an ANN system examined its ability to recognize and correctly diagnose patients with different facial pain syndromes. One hundred patients with facial pain were asked to respond to a facial pain questionnaire at the time of their initial visit. After interview, an independent diagnosis was assigned to each patient. The patients' responses to the questionnaire and their diagnoses were input to an ANN. The ANN was able to retrospectively predict the correct diagnosis for 95 of 100 patients (95%), and prospectively determine a correct diagnosis of trigeminal neuralgia Type 1 with 84% sensitivity and 83% specificity in 43 new patients. The ability of the ANN to accurately predict a correct diagnosis for the remaining types of facial pain was limited by our clinic sample size and hence less exposure to those categories. This is the first demonstration of the utilization of an ANN to diagnose facial pain syndromes.

Indications for selective intraoperative cholangiography

The indications for selective intraoperative cholangiography (IOC) include a clinical history of jaundice, pancreatitis, elevated bilirubin level, abnormal liver function test results, increased amylase levels, a high lipase level, or dilated common bile duct on preoperative ultrasonography. Although these clinical features are widely accepted as indications for IOC, they have not been tested for their ability to predict choledocholithiasis. Charts were reviewed for a 6-month time period in 2003 at Parkland Memorial Hospital for all patients undergoing cholecystectomy. Univariate analysis and logistic regression were used to determine which factors predicted choledocholithiasis. Of the 572 patients undergoing cholecystectomies during the study period, 189 underwent IOC and common bile duct stones were found in 57. Only preoperative hyperbilirubinemia or ultrasonograph identification of common bile duct dilation reliably predicted choledocholithiasis. There were 13 cases of choledocholithiasis that would not have been identified by preoperative hyperbilirubinemia or an enlarged common bile duct. However, common bile duct stones were clinically significant in only 2 of the 13 cases. One of these was treated with postoperative endoscopic retrograde cholangiopancreatography, and the other was treated with laparoscopic common bile duct exploration. Preoperative identification of a dilated common bile duct or elevated bilirubin levels can be the sole criteria for performing IOC on a selective basis in patients without malignancy. Reliance on a history of remote jaundice, pancreatitis, elevated liver function test values, or pancreatic enzymes results in unnecessary IOCs.

Magnetic resonance cholangiography: applications in patients with calculus disease of the biliary tract

Magnetic resonance cholangiography (MRC) is a non-invasive imaging modality that has become widely available. In the short time since its introduction, MRC has been shown to possess excellent accuracy for the diagnosis of various biliary pathologies, including choledocholithiasis. Investigations of the clinical applications of MRC are ongoing. This review summarizes the diagnostic capabilities of MRC and discusses its application in the management of patients with gallstone diseases.

Predicting fatal outcome in the early phase of severe acute pancreatitis by using novel prognostic models

BACKGROUND/AIMS

Survival in acute pancreatitis and particularly in severe acute and necrotizing pancreatitis is a combination of therapy-associated and patient-related factors. There are only few relevant methods for predicting fatal outcome in acute pancreatitis. Scores such as Ranson, Imrie, Blamey, and APACHE II are practical in assessing the severity of the disease, but are not sufficiently validated for predicting fatal outcome among patients with severe acute pancreatitis. The aim of this study was to construct a novel prediction model for predicting fatal outcome in the early phase of severe acute pancreatitis (SAP) and to compare this model with previously reported predictive systems.

METHODS

Hospital records of 253 patients with SAP were retrospectively analyzed. 234 patients with adequate data were included to the test set to construct five logistic regression and three artificial neural network (ANN) models. Two models were tested in an independent prospective validation set of 60 consecutive patients with SAP and compared with previously reported predictive systems.

RESULTS

The prediction model considered optimal was a logistic model with four variables: age, highest serum creatinine value within 60-72 h from primary admission, need for mechanical ventilation, and chronic health status. In the validation set, the predictive accuracy, determined by the area under the receiver operating characteristic curve value, was 0.862 for the chosen model, 0.847 for the ANN model using eight variables, 0.817 for APACHE II, 0.781 for multiple organ dysfunction score, 0.655 for Ranson, and 0.536 for Imrie scores.

CONCLUSIONS

Ranson and Imrie scores are inaccurate indicators of the mortality in SAP. A novel predictive model based on four variables can reach at least the same predictive performance as the APACHE II system with 14 variables.

A review of evidence of health benefit from artificial neural networks in medical intervention

The purpose of this review is to assess the evidence of healthcare benefits involving the application of artificial neural networks to the clinical functions of diagnosis, prognosis and survival analysis, in the medical domains of oncology, critical care and cardiovascular medicine. The primary source of publications is PUBMED listings under Randomised Controlled Trials and Clinical Trials. The rĵle of neural networks is introduced within the context of advances in medical decision support arising from parallel developments in statistics and artificial intelligence. This is followed by a survey of published Randomised Controlled Trials and Clinical Trials, leading to recommendations for good practice in the design and evaluation of neural networks for use in medical intervention.

The efficacy of magnetic resonance cholangiography for the evaluation of patients with suspected choledocholithiasis before laparoscopic cholecystectomy

BACKGROUND

Endoscopic retrograde cholangiography is the most commonly utilized tool for the identification of common bile duct stones (CBDS) before laparoscopic cholecystectomy, whereas the role of magnetic resonance cholangiography (MRC) for patient evaluation before laparoscopic cholecystectomy is currently undefined.

METHODS

We prospectively evaluated the efficacy of MRC for the identification of CBDS among patients with high risk for choledocholithiasis. Patient selection was based on clinical, sonographic, and laboratory criteria. Standard cholangiograms were obtained when possible for verification of MRC results.

RESULTS

Ninety-nine patients underwent evaluation with preoperative MRC. CBDS was visualized in 30% of patients. MRC sensitivity, specificity, positive predictive value, negative predictive value, and accuracy were 85%, 90%, 77%, 94%, and 89%, respectively.

CONCLUSIONS

MRC is useful for the evaluation of patients with suspected choledocholithiasis. Advantages of MRC include its noninvasive nature, ease of application, and accuracy in identifying and estimating the size of CBDS. Application of MRC in this setting reduces the need for diagnostic endoscopic retrograde cholangiography. Future investigations should be directed at the development of cost-effective utilization strategies for MRC application.