A novel mobile phone application for infant stool color recognition: An easy and effective tool to identify acholic stools in newborns

Updates in Biliary Atresia: Aetiology, Diagnosis and Surgery

Biliary atresia (BA) is an obliterative disease of the bile ducts affecting between 1 in 10,000-20,000 infants with a predominance in Asian countries. It is clinically heterogeneous with a number of distinct variants (e.g., isolated, Biliary Atresia Splenic Malformation syndrome, Cat-eye syndrome, cystic BA, and CMV-associated BA). Facts about its aetiology are hard to encounter but might include genetic, developmental, exposure to an environmental toxin, or perinatal virus infection. However, the cholestatic injury triggers an intrahepatic fibrotic process beginning at birth and culminating in cirrhosis some months later. Affected infants present with a triad of conjugated jaundice, pale stools, and dark urine and may have hepatosplenomegaly upon examination, with later ascites coincident with the onset of progressive liver disease. Rapid, efficient, and expeditious diagnosis is essential with the initial treatment being surgical, typically with an attempt to restore the bile flow (Kasai portoenterostomy (KPE)) or primary liver transplantation (<5%) if considered futile. Failure to restore bile drainage or the onset of complications such as recurrent cholangitis, treatment-resistant varices, ascites, hepatopulmonary syndrome, and occasionally malignant change are usually managed by secondary liver transplantation. This issue summarises recent advances in the disease and points a way to future improvements in its treatment.

Development of a diagnostic model for biliary atresia based on MMP7 and serological tests using machine learning

OBJECTIVE

To develop a machine learning diagnostic model based on MMP7 and other serological testing indicators for early and efficient diagnosis of biliary atresia (BA).

METHODS

A retrospective analysis was conducted on patient information from those hospitalized for pathological jaundice at Beijing Children's Hospital between January 1, 2019, and December 31, 2023. Patients with serum MMP7, liver stiffness measurements, and other routine serological tests were included in the study. Six machine learning models were constructed, including logistic regression (LR), random forest (RF), decision tree (DET), support vector machine classifier (SVC), neural network (MLP), and extreme gradient boosting (XGBoost), to diagnose BA. The area under the receiver operating characteristic curve was used to evaluate the diagnostic efficacy of the various models.

RESULTS

A total of 98 patients were included in the study, comprising 64 BA patients and 34 patients with other cholestatic liver diseases. Among the six machine learning models, the XGBoost algorithm model and RF algorithm model achieved the best predictive performance, with an AUROC of nearly 100% in both the training and validation sets. In the training set, these two algorithm models achieved an accuracy, precision, recall, F1 score, and AUROC of 1. Through model interpretation analysis, serum MMP7 levels, serum GGT levels, and acholic stools were identified as the most important indicators for diagnosing BA. The nomogram constructed based on the XGBoost algorithm model also demonstrated convenient and efficient diagnostic efficacy.

CONCLUSION

Machine learning models, especially the XGBoost algorithm and RF algorithm models, constructed based on preoperative serum MMP7 and serological tests can diagnose BA more efficiently and accurately. The most important influencing factors for diagnosis are serum MMP7, serum GGT, and acholic stools.

Diseases of bile duct in children

Several diseases originate from bile duct pathology. Despite studies on these diseases, certain etiologies of some of them still cannot be concluded. The most common disease of the bile duct in newborns is biliary atresia, whose prognosis varies according to the age of surgical correction. Other diseases such as Alagille syndrome, inspissated bile duct syndrome, and choledochal cysts are also time-sensitive because they can cause severe liver damage due to obstruction. The majority of these diseases present with cholestatic jaundice in the newborn or infant period, which is quite difficult to differentiate regarding clinical acumen and initial investigations. Intraoperative cholangiography is potentially necessary to make an accurate diagnosis, and further treatment will be performed synchronously or planned as findings suggest. This article provides a concise review of bile duct diseases, with interesting cases.

Cost-Effectiveness Analysis of Universal Screening for Biliary Atresia in Japan

OBJECTIVE

To evaluate the cost-effectiveness of universal newborn screening using stool color card or direct bilirubin (DB) testing when comparing with no screening for biliary atresia in Japanese setting.

STUDY DESIGN

A decision analytic Markov microsimulation model was developed to evaluate the universal screening for biliary atresia. Our screening strategies included stool color card, DB, or no screening. The outcomes of all newborns undergoing 3 strategies were simulated to analyze event-free life-years defined as liver transplant-free survival, costs, and incremental cost-effectiveness ratio (ICER) over a 25-year period with an annual discount rate of 2% applied for both costs and outcomes. A 1-way sensitivity analysis was performed to assess the uncertainty.

RESULTS

There were 941 000 newborn infants in our cohort and 114 cases of biliary atresia. The base case analysis showed that the stool color card strategy was $14 927 337 higher than no screening with an increase in 44 more event-free life-years gained, resulting in an ICER of $339 258 per event-free life-year gained. The DB screening strategy compared with stool color card was $138 994 060 higher with an increase in 271 more event-free life-years gained and an ICER of $512 893 per event-free life-year gained. The DB screening strategy compared with no screening resulted in an ICER of $488 639 per event-free life-year gained. The DB screening resulted in 16 fewer liver transplants than stool color card and stool color card had 2 fewer liver transplants than no screening.

CONCLUSIONS

Universal screening for biliary atresia could be cost-effective depending on the willingness to pay thresholds for health benefits.

Biliary Atresia in 2021: Epidemiology, Screening and Public Policy

Biliary atresia (BA) is a rare newborn liver disease with significant morbidity and mortality, especially if not recognized and treated early in life. It is the most common cause of liver-related death in children and the leading indication for liver transplantation in the pediatric population. Timely intervention with a Kasai portoenterostomy (KPE) can significantly improve prognosis. Delayed disease recognition, late patient referral, and untimely surgery remains a worldwide problem. This article will focus on biliary atresia from a global public health perspective, including disease epidemiology, current national screening programs, and their impact on outcome, as well as new and novel BA screening initiatives. Policy challenges for the implementation of BA screening programs will also be discussed, highlighting examples from the North American, European, and Asian experience.

Neonatal Cholestasis: Updates on Diagnostics, Therapeutics, and Prevention

Cholestatic jaundice is a common presenting feature of hepatobiliary and/or metabolic dysfunction in the newborn and young infant. Timely detection of cholestasis, followed by rapid step-wise evaluation to determine the etiology, is crucial to identify those causes that are amenable to medical or surgical intervention and to optimize outcomes for all infants. In the past 2 decades, genetic etiologies have been elucidated for many cholestatic diseases, and next-generation sequencing, whole-exome sequencing, and whole-genome sequencing now allow for relatively rapid and cost-effective diagnosis of conditions not previously identifiable via standard blood tests and/or liver biopsy. Advances have also been made in our understanding of risk factors for parenteral nutrition-associated cholestasis/liver disease. New lipid emulsion formulations, coupled with preventive measures to decrease central line-associated bloodstream infections, have resulted in lower rates of cholestasis and liver disease in infants and children receiving long-term parental nutrition. Unfortunately, little progress has been made in determining the exact cause of biliary atresia. The median age at the time of the hepatoportoenterostomy procedure is still greater than 60 days; consequently, biliary atresia remains the primary indication for pediatric liver transplantation. Several emerging therapies may reduce the bile acid load to the liver and improve outcomes in some neonatal cholestatic disorders. The goal of this article is to review the etiologies, diagnostic algorithms, and current and future management strategies for infants with cholestasis.

Province-Wide Stool Color Card Screening for Biliary Atresia in Lower-Saxony: Experiences with Passive Distribution Strategies and Results

BACKGROUND

Stool color card (SCC) screenings for biliary atresia (BA) have shown to improve Kasai timing and outcome significantly. Both obligatory and non-obligatory screenings with passive distribution strategies have proven to be effective. Therefore, we have initiated a voluntary SCC program and aim to describe our experience.

METHODS

Since 2017 we supply all maternity wards in Lower-Saxony with SCC. Attending pediatricians and parents of BA infants were contacted via questionnaires and asked for their evaluation of the SCC screening.

RESULTS

85.2% of attending pediatricians support the SCC screening, but only 78.1% considered the initiative useful. In their clinical routine, only 67% of visiting parents report to have received an SCC at the maternity hospital. In the group of parents of BA infants, only 54% (7/13) had received an SCC. Out of those seven parents, only one had referred their child to a children's hospital based on pathological SCC results. The lack of SCC education in the maternity hospitals was made responsible by parents. Within three years, only one infant with BA was identified through the SCC.

CONCLUSIONS

Our voluntary SCC screening shows serious limitations with inacceptable distribution of SCCs and low acceptance of attending pediatricians. SCC programs in decentralized health care systems without educational campaigns, standardized diagnostic and treatment algorithms and the definition of reference centers are additional burdens for local health care providers without the promised benefit.

Machine Learning Evaluation of Biliary Atresia Patients to Predict Long-Term Outcome after the Kasai Procedure

Kasai portoenterostomy (KP) represents the first-line treatment for biliary atresia (BA). The purpose was to compare the accuracy of quantitative parameters extracted from laboratory tests, US imaging, and MR imaging studies using machine learning (ML) algorithms to predict the long-term medical outcome in native liver survivor BA patients after KP. Twenty-four patients were evaluated according to clinical and laboratory data at initial evaluation (median follow-up = 9.7 years) after KP as having ideal (n = 15) or non-ideal (n = 9) medical outcomes. Patients were re-evaluated after an additional 4 years and classified in group 1 (n = 12) as stable and group 2 (n = 12) as non-stable in the disease course. Laboratory and quantitative imaging parameters were merged to test ML algorithms. Total and direct bilirubin (TB and DB), as laboratory parameters, and US stiffness, as an imaging parameter, were the only statistically significant parameters between the groups. The best algorithm in terms of accuracy, sensitivity, specificity, and AUCROC was naive Bayes algorithm, selecting only laboratory parameters (TB and DB). This preliminary ML analysis confirms the fundamental role of TB and DB values in predicting the long-term medical outcome for BA patients after KP, even though their values may be within the normal range. Physicians should be alert when TB and DB values change slightly.