Diagnostic Value and Effectiveness of an Artificial Neural Network in Biliary Atresia

Predictive modeling for early detection of biliary atresia in infants with cholestasis: Insights from a machine learning study

Cholestasis, characterized by the obstruction of bile flow, poses a significant concern in neonates and infants. It can result in jaundice, inadequate weight gain, and liver dysfunction. However, distinguishing between biliary atresia (BA) and non-biliary atresia in these young patients presenting with cholestasis poses a formidable challenge, given the similarity in their clinical manifestations. To this end, our study endeavors to construct a screening model aimed at prognosticating outcomes in cases of BA. Within this study, we introduce a wrapper feature selection model denoted as bWFMVO-SVM-FS, which amalgamates the water flow-based multi-verse optimizer (WFMVO) and support vector machine (SVM) technology. Initially, WFMVO is benchmarked against eleven state-of-the-art algorithms, with its efficiency in searching for optimized feature subsets within the model validated on IEEE CEC 2017 and IEEE CEC 2022 benchmark functions. Subsequently, the developed bWFMVO-SVM-FS model is employed to analyze a cohort of 870 consecutively registered cases of neonates and infants with cholestasis (diagnosed as either BA or non-BA) from Xinhua Hospital and Shanghai Children's Hospital, both affiliated with Shanghai Jiao Tong University. The results underscore the remarkable predictive capacity of the model, achieving an accuracy of 92.639 % and specificity of 88.865 %. Gamma-glutamyl transferase, triangular cord sign, weight, abnormal gallbladder, and stool color emerge as highly correlated with early symptoms in BA infants. Furthermore, leveraging these five significant features enhances the interpretability of the machine learning model's performance outcomes for medical professionals, thereby facilitating more effective clinical decision-making.

Does amyloid β precursor protein gene expression have a role in diagnosis of biliary atresia?

Aim of the study

Biliary atresia (BA) is an important cause of surgical jaundice. Although the precise etiology is unknown, β-amyloid (Aβ) has been observed around the bile ducts in BA livers. It is unclear whether Aβ plays a role in the pathogenesis of this disease. This study aims to assess the amyloid β precursor protein (APP) gene expression in infants with BA in comparison with other causes of neonatal cholestasis. This could help explore the role of Aβ in the pathogenesis and diagnosis of BA.

Material and methods

A prospective study was conducted at the outpatient clinic of Paediatric Hepatology, Gastroenterology, and Nutrition Department, National Liver Institute, Menoufia University, Shebin El Kom, Menoufia, Egypt during the period March 2022 to December 2022. Clinical data were gathered and laboratory and radiological investigations were conducted including β precursor protein gene expression measured in liver biopsies of the three groups using quantitative real-time PCR (qPCR).

Results

Gene expression of APP was considerably higher in the BA group (p = 0.0001) compared to neonatal cholestasis (NC) patients. Gamma glutamyl transferase (GGT) and APP had a positive correlation (p = 0.001). No significant association was found between APP and fibrosis. APP was noticeably higher in BA than NC other than BA. Also, APP in BA was higher (statistically significant, p = 0.0001) than the control. There was no statistically significant difference among NC, BA, and control groups regarding APP (p = 0.07). Both males and females did not show significant differences as regards APP (p = 0.851). Age did not have a statistically significant correlation with APP (p = 0.532). Also, there were no correlations between APP and alkaline phosphatase (ALP), aspartate transaminase (AST), or total bilirubin (TB) (p > 0.05).

Conclusions

We concluded that the development and identification of BA may depend on the liver expression of serum APP. Surgeons may be able to carry out early intraoperative cholangiography for BA confirmation if the combination of APP with GGT and other hepatic function parameters exhibits a high predictive potential as a diagnostic test for BA. To evaluate this hypothesis, more research with sizable sample numbers is necessary.

Machine learning-based model for predicting the esophagogastric variceal bleeding risk in liver cirrhosis patients

BACKGROUND

Liver cirrhosis patients are at risk for esophagogastric variceal bleeding (EGVB). Herein, we aimed to estimate the EGVB risk in patients with liver cirrhosis using an artificial neural network (ANN).

METHODS

We included 999 liver cirrhosis patients hospitalized at the Beijing Ditan Hospital, Capital Medical University in the training cohort and 101 patients from Shuguang Hospital in the validation cohort. The factors independently affecting EGVB occurrence were determined via univariate analysis and used to develop an ANN model.

RESULTS

The 1-year cumulative EGVB incidence rates were 11.9 and 11.9% in the training and validation groups, respectively. A total of 12 independent risk factors, including gender, drinking and smoking history, decompensation, ascites, location and size of varices, alanine aminotransferase (ALT), γ-glutamyl transferase (GGT), hematocrit (HCT) and neutrophil-lymphocyte ratio (NLR) levels as well as red blood cell (RBC) count were evaluated and used to establish the ANN model, which estimated the 1-year EGVB risk. The ANN model had an area under the curve (AUC) of 0.959, which was significantly higher than the AUC for the North Italian Endoscopic Club (NIEC) (0.669) and revised North Italian Endoscopic Club (Rev-NIEC) indices (0.725) (all P <  0.001). Decision curve analyses revealed improved net benefits of the ANN compared to the NIEC and Rev-NIEC indices.

CONCLUSIONS

The ANN model accurately predicted the 1-year risk for EGVB in liver cirrhosis patients and might be used as a basis for risk-based EGVB surveillance strategies.

Plasma amyloid-beta levels correlated with impaired hepatic functions: An adjuvant biomarker for the diagnosis of biliary atresia

BACKGROUND

Biliary atresia (BA) is an infantile fibro-obstructive cholestatic disease with poor prognosis. An early diagnosis and timely Kasai portoenterostomy (KPE) improve clinical outcomes. Aggregation of amyloid-beta (Aβ) around hepatic bile ducts has been discovered as a factor for BA pathogenesis, yet whether plasma Aβ levels correlate with hepatic dysfunctions and could be a biomarker for BA remains unknown.

METHOD

Plasma samples of 11 BA and 24 controls were collected for liver function test, Aβ40 and Aβ42 measurement by enzyme-linked immunosorbent assay (ELISA). Pearson's chi-squared test or Mann-Whitney U test was performed to assess differences between groups. Correlation between Aβ42/Aβ40 and liver function parameters was performed using Pearson analysis. The area under the receiver-operative characteristic (ROC) curve (area under curve; AUC) was measured to evaluate the diagnostic power of Aβ42/Aβ40 for BA. Diagnostic enhancement was further evaluated by binary regression ROC analysis of Aβ42/Aβ40 combined with other hepatic function parameters.

RESULTS

Plasma Aβ42/Aβ40 was elevated in BA patients. Aβ42 displayed a weak positive correlation with γ-glutamyl transpeptidase (GGT) (Pearson's correlation = 0.349), while there was no correlation for Aβ40 with hepatic functions. Aβ42/Aβ40 was moderately correlated with GGT, total bile acid (TBA), direct bilirubin (DBIL) (Pearson's correlation = 0.533, 0.475, 0.480), and weakly correlated with total bilirubin (TBIL) (Pearson's correlation = 0.337). Aβ42/Aβ40 showed an acceptable predictive power for cholestasis [AUC = 0.746 (95% CI: 0.552-0.941), p < 0.05]. Diagnostic powers of Aβ42/Aβ40 together with hepatic function parameters for cholestasis were markedly improved compared to any indicator alone. Neither Aβ42/Aβ40 nor hepatic function parameters displayed sufficient power in discriminating BA from choledochal cysts (CC); however, combinations of Aβ42/Aβ40 + GGT along with any other hepatic function parameters could differentiate BA from CC-cholestasis (AUC = 1.000, p < 0.05) with a cut-off value as 0.02371, -0.28387, -0.34583, 0.06224, 0.01040, 0.06808, and 0.05898, respectively.

CONCLUSION

Aβ42/Aβ40 is a good indicator for cholestasis, but alone is insufficient for a distinction of BA from non-BA. However, Aβ42/Aβ40 combined with GGT and one other hepatic function parameter displayed a high predictive power as a screening test for jaundiced neonates who are more likely to be BA, enabling them to early intraoperative cholangiography for BA confirmation and KPE to improve surgical outcomes. However, a multi-centers validation is needed before introduction into daily clinical practice.

Role of Artificial Intelligence (AI) in Surgery: Introduction, General Principles, and Potential Applications

AI (Artificial intelligence) is an interdisciplinary field aimed at the development of algorithms to endow machines with the capability of executing cognitive tasks. The number of publications regarding AI and surgery has increased dramatically over the last two decades. This phenomenon can partly be explained by the exponential growth in computing power available to the largest AI training runs. AI can be classified into different sub-domains with extensive potential clinical applications in the surgical setting. AI will increasingly become a major component of clinical practice in surgery. The aim of the present Narrative Review is to give a general introduction and summarized overview of AI, as well as to present additional remarks on potential surgical applications and future perspectives in surgery.