Prognostic risk factor of major salivary gland carcinomas and survival prediction model based on random survival forests.

Abstract in brief

• This study developed a risk prediction model using random survival forests (RSF) to identify patients with salivary gland cancers who are at higher risk of poor outcomes, helping to improve follow-up care and treatment strategies.
• Key risk factors for worse prognosis include age, smoking, alcohol use, neural invasion, tumor size over 4cm, advanced disease stages, metastasis, and certain tumor types; multivariable analysis identified female gender, aging, smoking, untreated tumors, and nonmucous cell carcinoma as significant predictors.
• The RSF model demonstrated good accuracy in predicting 1-, 2-, and 3-year survival rates, with a specific risk score cutoff effectively distinguishing patients with significantly different prognoses, making it a useful tool for clinical decision-making.]