Machine Learning Uncovers Novel Predictors of PRRT Eligibility in Neuroendocrine Neoplasms

Background/Objectives: Neuroendocrine neoplasms (NENs) are a diverse group of malignancies in which somatostatin receptor expression can be crucial in guiding therapy. We aimed to evaluate the effectiveness of 99mTcTc-EDDA/HYNIC-TOC SPECT/CT in differentiating neuroendocrine tumor histology, selecting candidates for radioligand therapy, and identifying correlations between somatostatin receptor expression and non-imaging parameters in metastatic NENs. Methods: This retrospective study included 65 patients (29 women, 36 men, mean age 61) with metastatic neuroendocrine neoplasms confirmed by histology, follow-up, or imaging, comprising 14 poorly differentiated carcinomas and 51 well-differentiated tumors. Somatostatin receptor SPECT/CT results were assessed visually and semi-quantitatively, with mathematical models incorporating histological, oncological, immunohistochemical, and laboratory parameters, followed by biostatistical analysis. Results: Of 392 lesions evaluated, the majority were metastases in the liver, lymph nodes, and bones. Mathematical models estimated somatostatin receptor expression accurately (70-83%) based on clinical parameters alone. Key factors included tumor origin, oncological treatments, and the immunohistochemical marker CK7. Associations were found with age, grade, disease extent, and markers (CEA, CA19-9, AFP). Conclusions: Our findings suggest that 99mTcTc-EDDA/HYNIC-TOC SPECT/CT effectively evaluates somatostatin receptor expression in NENs. Certain immunohistochemical and laboratory parameters, beyond recognised factors, show potential prognostic value, supporting individualised treatment strategies.