Machine learning-based decision tool for selecting patients with idiopathic acute pancreatitis for endosonography to exclude a biliary aetiology

BACKGROUND Biliary microlithiasis/sludge is detected in approximately 30%of patients with idiopathic acute pancreatitis(IAP).As recurrent biliary pancreatitis can be prevented,the underlying aetiology of IAP should be established.AIM To develop a machine learning(ML)based decision tool for the use of endosonography(EUS)in pancreatitis patients to detect sludge and microlithiasis.METHODS We retrospectively used routinely recorded clinical and laboratory parameters of 218 consecutive patients with confirmed AP admitted to our tertiary care hospital between 2015 and 2020.Patients who did not receive EUS as part of the diagnostic work-up and whose pancreatitis episode could be adequately explained by other causes than biliary sludge and microlithiasis were excluded.We trained supervised ML classifiers using H_(2)O.ai automatically selecting the best suitable predictor model to predict microlithiasis/sludge.The predictor model was further validated in two independent retrospective cohorts from two tertiary care centers(117 patients).RESULTS Twenty-eight categorized patients’variables recorded at admission were identified to compute the predictor model with an accuracy of 0.84[95%confidence interval(CI):0.791-0.9185],positive predictive value of 0.84,and negative predictive value of 0.80 in the identification cohort(218 patients).In the validation cohort,the robustness of the prediction model was confirmed with an accuracy of 0.76(95%CI:0.673-0.8347),positive predictive value of 0.76,and negative predictive value of 0.78(117 patients).CONCLUSION We present a robust and validated ML-based predictor model consisting of routinely recorded parameters at admission that can predict biliary sludge and microlithiasis as the cause of AP.

Pathophysiology of severe gallstone pancreatitis:A new paradigm

Severe gallstone pancreatitis(GSP)refractory to maximum conservative therapy has wide clinical variations,and its pathophysiology remains controversial.This Editorial aimed to investigate the pathophysiology of severe disease based on Opie’s theories of obstruction,the common channel,and duodenal reflux and describe its types.Severe GSP might be a hybrid disease with pathology polarized between acute cholangitis with mild pancreatitis(biliary type)and necrotizing pancreatitis uncomplicated with biliary tract disease(pancreatic type),in which hepatobiliary and pancreatic lesion severity is inversely related to the presence or absence of impacted ampullary stones.Severe GSP is caused by stones that are persistently impacted at the ampulla with biliopancreatic obstruction(biliary type),and probably,stones that are either temporarily lodged at the duodenal orifice or passed into the duodenum,thereby permitting reflux of bile or possible duodenal contents into the pancreas(pancreas type).When the status of the stones and the presence or absence of impacted ampullary stones with biliopancreatic obstruction are determined,the clinical course and outcome can be predicted.Gallstones represent the main cause of acute pancreatitis globally,and clinicians are expected to encounter GSP more often.Awareness of the etiology and pathogenesis of severe disease is mandatory.

Therapeutic effects of endoscopic therapy combined with enteral nutrition on acute severe biliary pancreatitis

Background Acute severe biliary pancreatitis （ASBP） is a severe and fatal disease, and the expenditure is huge and therapeutic effects are still not satisfactory. This study aimed to improve the therapeutic effects and reduce the expenditure of ASBP treatment.Methods One hundred and five patients diagnosed with ASBP were referred to our department from January 2004 to July 2009. Diagnosis was based on the 2007 criteria of the Chinese Society of Surgery. Patients were divided into two groups; the E group： 50 patients who underwent endoscopic retrograde choledochopancreatography （ERCP） ＋ endoscopic sphincterotomy （EST） ＋ endoscopic lithotripsy basket （ESR） ＋endoscopic retrograde biliary drainage （ERBD）and enteral nutrition （EN）, and the R group： 55 patients who underwent traditional treatment without ERCP. Subsequently,subjective symptoms, signs, biochemical analysis, serum endotoxin, tumor necrosis factor a, grades by computed tomography （CT）, cost of hospitalization and length of stay were compared between the two groups.Results All enrolled patients complied well with all therapeutic regimens. Endoscopic therapy that combined EN could significantly improve symptoms, clinical signs, laboratory values, tumor necrosis factor a and endotoxin while significantly reducing hospital expenditure and length of hospital stay. The experimental findings revealed that there were obvious advantages in the E group compared with the R group.Conclusions Endoscopic therapy combined with EN is an effective, safe and economic therapeutic regimen of ASBP.

Early versus delayed laparoscopic cholecystectomy in uncomplicated biliary colic: An observational study

Objective:Biliary colic is a condition treated with laparoscopic cholecystectomy.However,the outcomes of surgery depend on early or delayed time points.Few research findings reported no benefits of early over delayed,on contra,other reported benefits.This study aims to compare the benefits associated with early and delayed laparoscopic cholecystectomy among uncomplicated biliary colic patients.Methods:This observational study included patients with right upper abdominal pain and abdominal ultrasound showing cholelithiasis.Patients who were admitted at the first and second visits(within 6 weeks of the first visit)were assigned to the early and delayed groups,respectively.All participants were followed up for one-week postsurgery.The diagnosis of the patient,postoperative hospital stay,duration of surgery and complications were noted and compared primarily.Results:A total of 80 patients were included,40 each in the early group and delayed group.The patients in the two groups had comparable mean ages(40.55±13.12 y vs.40.45±12.06 y,p=0.972).The early group had more female patients(72.5%vs.45.0%,p=0.012).The duration of hospital stay(2.18±0.38 d vs.2.68±1.04 d,p=0.009)and duration of surgery(61.63±3.64 min vs.71.13±16.19 min,p=0.001)were found to be significantly different between the early and delayed groups.Only 1(2.5%)patient in both groups was converted to open cholecystectomy.Recurrent biliary colic requiring hospital admission was seen in 1(2.5%)patient and 6(15.0%)patients,acute cholecystitis in 2(5.0%)and 6(15.0%),biliary pancreatitis in 1(2.5%)and 2(5.0%),and obstructive jaundice in 1(2.5%)and 1(2.5%)in the early and delayed groups,respectively,with insignificant differences(p>0.05).Conclusion:Early laparoscopic cholecystectomy decreases the operating time and duration of hospital stay.In terms of postoperative complications,our study did not find any significant difference between the groups.