Machine-learning model accurately predicts gallbladder polyp malignancy

A novel machine-learning model, particularly the random forest algorithm, distinguishes between benign and malignant gallbladder polyps, utilizing clinical and ultrasound data from 1,050 patients. Key predictive factors identified include polyp size, age, fibrinogen levels, and presence of stones. The model achieved impressive performance metrics with area under the curve values ranging from 0.940 to 0.963 in various cohorts, showcasing significant clinical applicability and offering a tool for preoperative decision-making regarding gallbladder polyp management.