Stereotactic ABlative Radiotherapy (SABR) in Oligometastatic Cancer (OC): a Radiomics, Multi-omics, and Machine Learning Approach to Clinical Decision-making. the OC-SABR Multicentric Project

Metastases are the most threatening challenge in cancer. In patients with metastatic cancer, local radiotherapy treatment remains an essential tool with different goals that depend on numerous factors, especially on the number and extent of the metastases and whether disease control is feasible and desirable according to the expected quality of life. Oligometastatic Cancer (OC), i.e., a few metastases in a few organs, has been recently incorporated as a less aggressive state than widely disseminated metastatic disease. Consequently, OC is a serious candidate for aggressive treatments based on Stereotactic ABlative Radiotherapy (SABR). This treatment has shown promising results and is already incorporated into habitual clinical practices. However, OC is a complex and heterogeneous disease, and not all patients have improved their life quality and expectation. Identifying patients who would benefit from this treatment is an important area of research that needs factual information from a large sample provided by multiple centers. Therefore, this multicenter, retrospective, prospective, observational, and longitudinal study incorporates clinical data, medical images, and biological samples to feed artificial intelligence algorithms. The objective is to determine which patient profile achieves complete response after SABR. The secondary objectives are: 1. To analyze metastases by radiomics using computed tomography, magnetic resonance, or positron emission tomography images; and 2. To evaluate intratumoral metabolites released into circulation by multi-omics analyses. These will contribute to determining the systemic molecular effects of treatment in search of biomarkers with predictive value. Centralized storage of patient management data, clinical image analysis, and candidate biomarkers measured in blood samples may eventually meet the expectations of integrating data into clinical decision-making and influence evolution based on precision medicine.