Train-METASTRA is a retrospective study that will be performed in order to collect a large and harmonised amount of clinical and imaging data concerning vertebral metastases, focusing in particular on the risk of fractures. This type of dataset will be created from the medical records of 2000 patients admitted in the last ten years in the four European clinical centers participating in METASTRA project: "COMPUTER-AIDED EFFECTIVE FRACTURE RISK STRATIFICATION OF PATIENTS WITH VERTEBRAL METASTASES FOR PERSONALISED TREATMENT THROUGH ROBUST COMPUTATIONAL MODELS VALIDATED IN CLINICAL SETTINGS", funded by the European Union under the call "HORIZON-HLTH-2022-TOOL-12-two-stage/Computational models for new patient stratification strategies". The project is coordinated by the University of Bologna (UNIBO) (PI prof. Luca Cristofolini) and involves 15 European partners, including Sarl Voisin Consulting Life Sciences VCLS, University of Szeged (Hungary), University of Sheffield (UK) and FrontEndART (Hungary).

This type of dataset is not currently available in the literature and it will be pivotal to the development of the METASTRA computational models for the stratification of the risk of fracture of patients affected by spinal metastases.

Inclusion Criteria:

• Alive or dead
• Age 18 -99 years old
• Both male and female
• Diagnosis of cancer metastases at the spine
• Any SINS score
• Admitted for hospitalisation or outpatient visit from Jan 2012 to Dec 2022 N ≥ 1 non-stabilised metastatic vertebra
• Presence of baseline CT scan, and/or MRI and x-rays, showing the presence of metastatic lesions that are not surgically treated
• At least one follow-up visit at ≥ 3 months after the first evaluation or treatment

Exclusion Criteria:

• Minor patients
• Patients with diagnosis of primary spine tumour, degenerative spinal diseases, deformity or trauma
• Patients without non-stabilised vertebral metastases
• Patients without baseline CT scan or MRI
• Patients without follow up visits

The expected study population is a cohort of patients affected by spinal metastases admitted in the last ten years (from 2012 to 2022) in the four clinical centers involved in the study. This cohort of patients is characterised by the presence of one or more vertebral metastatic lesions that are not surgically treated.