Machine learning-based diagnostic model for preoperative differentiation between xanthogranulomatous cholecystitis and gallbladder carcinoma: a multicenter retrospective cohort study.

Background: Xanthogranulomatous cholecystitis (XGC) and gallbladder carcinoma (GBC) share similar imaging and serological profiles, posing significant challenges in accurate preoperative diagnosis. This study aimed to identify reliable indicators and develop a predictive model to differentiate between XGC and GBC. Methods: This retrospective study involved 436 patients from Zhejiang Provincial People's Hospital and The Affiliated Lihuili Hospital of Ningbo University. Comprehensive preoperative imaging, including ultrasound, Computed Tomography (CT), Magnetic Resonance Imaging (MRI), and blood tests, were analyzed. Machine learning (Random Forest method) was employed for variable selection, and a multivariate logistic regression analysis was used to construct a nomogram for predicting GBC. Statistical analyses were performed using SPSS and RStudio software. Results: The study identified gender, Murphy's sign, absolute neutrophil count, glutamyl transpeptidase level, carcinoembryonic antigen level, and comprehensive imaging diagnosis as potential risk factors for GBC. A nomogram incorporating these factors demonstrated high predictive accuracy for GBC, outperforming individual or combined traditional diagnostic methods. External validation of the nomogram showed consistent results. Conclusion: The study successfully developed a predictive nomogram for distinguishing GBC from XGC with high accuracy. This model, integrating multiple clinical and imaging indicators, offers a valuable tool for clinicians in making informed diagnostic decisions. The findings advocate for the use of comprehensive preoperative evaluations combined with advanced analytical tools to improve diagnostic accuracy in complex medical conditions.