Integrating etiological insights with machine learning for precision diagnosis of obstructive jaundice: findings from a high-volume center.

Introduction: Large-scale cohort studies exploring the etiology of obstructive jaundice (OJ) are scarce, with current serum-based diagnostic markers offering suboptimal performance. This study leverages the largest retrospective cohort of OJ patients to date to investigate its disease spectrum and to develop a novel diagnostic system.

Methods: This study involves two retrospective observational cohorts. The biliary surgery cohort (BS cohort, n=349) served for initial data exploration and external validation of ML models. The large general cohort (LG cohort, n=5726) enabled an in-depth analysis of etiologies and the determination of relevant diagnostic indicators, in addition to supporting ML model development. Interpretable ML techniques were employed to derive insights from the models.

Results: The LG cohort highlighted a diverse disease spectrum of OJ, including cholangiocarcinoma (10.39% distal, 10.01% perihilar, 5.59% intrahepatic), pancreatic adenocarcinoma (19.11%), and common bile duct stones (18.27%) as leading causes. Traditional serum markers such as CA 19-9 and CEA lacked standalone diagnostic accuracy. Two ML-based models (collectively termed the MOLT model) were developed: a classifier to differentiate benign from malignant causes (AUROC=0.862) and a multi-class model to further stratify malignant and benign diseases (ACC=0.777). Interpretable ML tools provided clarity on critical features, offering actionable insights and enhancing transparency in the decision-making process.

Discussion: This study elucidates the etiological spectrum of OJ, meanwhile providing a practical and interpretable ML-based diagnostic tool. By leveraging large-scale clinical data, our model provides a rapid and reliable primary assessment for patients with OJ, enabling clinicians to identify potential etiologies and guide further diagnostic workup.