Development of a diagnostic model for biliary atresia based on MMP7 and serological tests using machine learning
link.springer.com shows its articles on its own site.
Read the article on link.springer.com ↗Article · Jul 2024 · 1 min read
In brief
In brief
Researchers developed machine learning models using serum MMP7 levels and routine lab tests to diagnose biliary atresia in infants with jaundice. The XGBoost and random forest algorithms achieved near-perfect accuracy, identifying MMP7, GGT levels, and acholic stools as key diagnostic indicators for early BA detection.
- XGBoost and Random Forest models achieved near-perfect diagnostic accuracy (AUROC ~100%) for biliary atresia using serum biomarkers.
- Serum MMP7, GGT levels, and presence of acholic stools are the three most critical diagnostic indicators for biliary atresia.
- Machine learning models can enable earlier, non-invasive BA diagnosis compared to traditional workup requiring liver biopsy or cholangiography.
- The XGBoost-based nomogram provides a practical clinical tool for rapid BA risk stratification in infants with cholestatic jaundice.
- Combining MMP7 with routine serological tests improves diagnostic efficiency over MMP7 alone in differentiating BA from other cholestatic diseases.
Written by the GCMD Library team from the article.
Abstract
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.