An interpretable machine learning model for preoperative prediction of aldosterone secretion and CYP11B2 status of adrenal gland

Key Points

• To develop a machine learning model for predicting adrenal aldosterone secretion and CYP11B2 status using radiomic and clinical data.
• Integrated radiomics with clinical features in a machine learning framework.
• Evaluated the model's performance on an independent external cohort for generalizability.
• Assessed predictive accuracy of aldosterone secretion and histopathological subtypes.
• The model showed effectiveness in predicting aldosterone secretion function.
• It successfully categorized different histopathological subtypes of adrenal tissues.
• Results indicated potential applicability in clinical settings.

Abstract