Active learning-based multistage sequential decision-making model with application on common bile duct stone evaluation.

Multistage sequential decision-making occurs in many real-world applications such as healthcare diagnosis and treatment. One concrete example is when the doctors need to decide to collect which kind of information from subjects so as to make the good medical decision cost-effectively. In this paper, an active learning-based method is developed to model the doctors' decision-making process that actively collects necessary information from each subject in a sequential manner. The effectiveness of the proposed model, especially its two-stage version, is validated on both simulation studies and a case study of common bile duct stone evaluation for pediatric patients.

Pancreatitis in Children.

Pediatric pancreatitis describes a spectrum covering acute pancreatitis, acute recurrent pancreatitis, and chronic pancreatitis, each with varying clinical manifestations and risk factors requiring a tailored diagnostic approach. We emphasize management strategies based on age, risk factors, recurrence, and complications. A discussion of the role of therapeutic endoscopy is reviewed and highlights the growing role of endoscopic ultrasound and endoscopic retrograde cholangiopancreatography in children with pancreatitis. Particular diagnostic challenges in autoimmune pancreatitis are reviewed with an emphasis on differentiating this entity from alternate pancreaticobiliary pathologies. Finally, we explore a multidisciplinary approach to acute recurrent and chronic pancreatitis.

Creation of a Pediatric Choledocholithiasis Prediction Model.

BACKGROUND: Definitive non-invasive detection of pediatric choledocholithiasis could allow more efficient identification of those patients who are most likely to benefit from therapeutic endoscopic retrograde cholangiopancreatography (ERCP) for stone extraction. OBJECTIVE: To craft a pediatric choledocholithiasis prediction model using a combination of commonly available serum laboratory values and ultrasound results. METHODS: A retrospective review of laboratory and imaging results from 316 pediatric patients who underwent intraoperative cholangiogram or ERCP due to suspicion of choledocholithiasis were collected and compared to presence of common bile duct stones on cholangiography. Multivariate logistic regression with supervised machine learning was used to create a predictive scoring model. Monte-Carlo cross-validation was used to validate the scoring model and a score threshold that would provide at least 90% specificity for choledocholithiasis was determined in an effort to minimize non-therapeutic ERCP. RESULTS: Alanine aminotransferase (ALT), total bilirubin, alkaline phosphatase, and common bile duct diameter via ultrasound were found to be the key clinical variables to determine the likelihood of choledocholithiasis. The dictated specificity threshold of 90.3% yielded a sensitivity of 40.8% and overall accuracy of 71.5% in detecting choledocholithiasis. Positive predictive value was 71.4% and negative predictive value was 72.1%. CONCLUSION: Our novel pediatric choledocholithiasis predictive model is a highly specific tool to suggest ERCP in the setting of likely choledocholithiasis.

Retrospective Multicenter Matched Controlled Comparison of Endoscopic Retrograde Cholangiopancreatography in Pediatric Patients: A 10-year Experience.

INTRODUCTION: This study was designed to evaluate outcomes in pediatric patients undergoing endoscopic retrograde cholangiopancreatography (ERCP) as compared with an American Society of Gastrointestinal Endoscopy (ASGE) complexity grade-matched adult cohort. METHOD: In this retrospective case-control study, ERCPs performed in pediatric patients from January 2008 to December 2018 in 2 tertiary referral hospitals were compared with a complexity-matched adult control group with similar procedural indications. Primary outcomes included the clinical success rate, technical success rate, and complication rate. Secondary outcomes included postprocedural admission rates, mode of sedation, procedure time, fluoroscopy time, hospitalization length, and the number of repeat procedures. RESULTS: Two hundred thirty-two ERCPs performed in 110 pediatric patients (average age 13.3) and 318 ERCPs performed in 160 ASGE grade-matched adult controls (average age 47.2 years) were analyzed. All procedures were therapeutic. There was no difference in the technical success rate (P = 0.2), clinical success rate (P = 0.5), complication rates (P = 0.1), and fluoroscopy time (P = 0.4), between the pediatric and adult cohorts. General anesthesia use and length of stay were significantly higher in the pediatric group (P = 0.0001). In subgroup analysis, technical (P = 0.2) and clinical success (P = 0.2) as well as complication rates (P = 0.6) were comparable between patients 10 years or less and patients 11 to 18 years within pediatric cohort. CONCLUSIONS: ERCP in pediatric cohorts appears to be safe and effective with equivalent outcomes relative to an ASGE complexity-matched adult cohort. Pediatric patients are more likely to require general anesthesia and have a longer average length of stay relative to adult controls.

Management of Anti-drug Antibodies to Biologic Medications in Children With Inflammatory Bowel Disease.

BACKGROUND: Treatment of pediatric inflammatory bowel disease (IBD) with monoclonal anti- tumor necrosis factor-alpha (TNFα) can result in immunogenicity and formation of anti-drug antibodies (ADAs). ADAs are associated with loss of clinical response and worsening disease progression. Data examining treatment interventions to overcome ADA in pediatric patients with IBD are lacking. RESULTS: Medical records were reviewed from 234 children and adolescents with IBD treated with infliximab or adalimumab who underwent therapeutic drug monitoring (626 tests). All patients who had detectable antibodies were further analyzed. A total 58 patients (24.8%) developed ADA while being treated with infliximab or adalimumab. The incidence of antibody development was 12.9 per 100 person-years of anti-TNF treatment. Twenty-eight patients underwent dose optimization and 54% had undetectable ADA on follow-up monitoring. The mean duration of antibody suppression was 16.8 ±â€Š10.9 months in those who were successfully suppressed with optimization. Patients who switched to a second anti-TNF medication were not more likely to develop antibodies to the second agent. CONCLUSIONS: With limited therapies for IBD and the chronicity of the disease, we advocate salvage of the current anti-TNF through dose optimization in pediatric patients with antibody level <10 U/mL.

Outcomes analysis of radioactive iodine and total thyroidectomy for pediatric Graves' disease.

BACKGROUND: The majority of pediatric patients with Graves' disease will ultimately require definitive therapy in the form of radioactive iodine (RAI) ablation or thyroidectomy. There are few studies that directly compare the efficacy and complication rates between RAI and thyroidectomy. We compared the relapse rate as well as the acute and long-term complications of RAI and total thyroidectomy among children and adolescents with Graves' disease treated at our center. METHODS: Medical records from 81 children and adolescents with a diagnosis of Graves' disease who received definitive therapy over a 12-year period were reviewed. RESULTS: Fifty one patients received RAI and 30 patients underwent thyroidectomy. The relapse rate was not significantly different between RAI and thyroidectomy (12.1% vs. 0.0%, p=0.28). There were no acute or long-term complications in the RAI group, but there were eight cases of hypoparathyroidism (two transient and six permanent) in the thyroidectomy group. None of the patients developed a recurrent laryngeal nerve injury. CONCLUSIONS: RAI is a safe and effective option for treatment of children and adolescents with Graves' disease. In light of the rate of permanent hypoparathyroidism seen at our center with thyroidectomy and previously published long-term safety of RAI, we recommend RAI as the first line treatment for children and adolescents with Graves' disease. For those centers performing thyroidectomies, we recommend that each center select 1-2 high-volume pediatric surgeons to perform all thyroid procedures, allowing individuals to increases case volume and potentially decrease long-term complications of thyroidectomy.