Periodic Reporting for period 1 - METASTRA (COMPUTER-AIDED EFFECTIVE FRACTURE RISK STRATIFICATION OF PATIENTS WITH VERTEBRAL METASTASES FOR PERSONALISED TREATMENT THROUGH ROBUST COMPUTATIONAL MODELS VALIDATED IN CLINICAL SETTINGS)
Reporting period: 2023-07-01 to 2024-12-31
Cancer patients (2.7M in Europe) with a positive prognosis are exposed to a high incidence of secondary tumours (≈1M). Bone metastases spread to the spine in 30-70% cases, reducing the load bearing capacity of the vertebrae and triggering fracture in 30% cases. Clinicians have only two options: either operate to stabilise the spine, or leave the patient exposed to a high fracture risk. The decision is highly subjective and can either lead to unnecessary surgery, or a fracture significantly affecting the quality of life and cancer treatment.
The standard-of-care to stratify patients with vertebral metastasis are scoring systems based on radiographic images, with little consideration of the local biomechanics. Current scoring systems are unable to establish an indication for surgery in around 60% of cases. Thus, there is an unmet need to accurately and timely quantify the risk of fracture, to improve patient stratification and identify the best personalised treatment.
METASTRA aims to enhance the prevention of fractures in patients with vertebral metastases and provide tailored patient-specific treatment by creating robust computational models capable of reliably stratifying patients according to their fracture risk. METASTRA will offer a collection of biomechanically validated models, demonstrated within relevant clinical contexts, which will be integrated into a Decision Support System (DSS). Additionally, METASTRA will formulate a novel stratification strategy by formulating new guidelines to assist clinicians in the patient stratification process based on fracture risk. These guidelines will also aid in identifying the most suitable treatment options by employing the computational models developed and validated within the METASTRA project.
These Strategic Objectives (SO) align with the primary needs of the end-users and are closely linked to the expected outcomes of the project:
• SO1. Broaden the understanding of the circumstances leading to fractures of vertebral metastases and the mechanical consequences of metastases, with unprecedentedly rich and complete retrospective and prospective databases of fractured and non-fractured patients, and an ex vivo dataset.
• SO2. Develop an integrated toolbox (segmentation, mechanistic models) to identify critical metastases.
• SO3. Develop three computational models and encapsulate them into a decision support system, to support clinicians in the stratification of patients with vertebral metastases and recommended the best treatment option.
• SO4. Pave the way for later certification of the METASTRA-DSS by regulatory bodies.
• SO5. Draft and disseminate new guidelines for patient stratification, and for safely choosing the best patient treatment, reducing the risk of fracture, avoiding unneeded interventions, and optimising cost-effectiveness.
The standard-of-care to stratify patients with vertebral metastasis are scoring systems based on radiographic images, with little consideration of the local biomechanics. Current scoring systems are unable to establish an indication for surgery in around 60% of cases. Thus, there is an unmet need to accurately and timely quantify the risk of fracture, to improve patient stratification and identify the best personalised treatment.
METASTRA aims to enhance the prevention of fractures in patients with vertebral metastases and provide tailored patient-specific treatment by creating robust computational models capable of reliably stratifying patients according to their fracture risk. METASTRA will offer a collection of biomechanically validated models, demonstrated within relevant clinical contexts, which will be integrated into a Decision Support System (DSS). Additionally, METASTRA will formulate a novel stratification strategy by formulating new guidelines to assist clinicians in the patient stratification process based on fracture risk. These guidelines will also aid in identifying the most suitable treatment options by employing the computational models developed and validated within the METASTRA project.
These Strategic Objectives (SO) align with the primary needs of the end-users and are closely linked to the expected outcomes of the project:
• SO1. Broaden the understanding of the circumstances leading to fractures of vertebral metastases and the mechanical consequences of metastases, with unprecedentedly rich and complete retrospective and prospective databases of fractured and non-fractured patients, and an ex vivo dataset.
• SO2. Develop an integrated toolbox (segmentation, mechanistic models) to identify critical metastases.
• SO3. Develop three computational models and encapsulate them into a decision support system, to support clinicians in the stratification of patients with vertebral metastases and recommended the best treatment option.
• SO4. Pave the way for later certification of the METASTRA-DSS by regulatory bodies.
• SO5. Draft and disseminate new guidelines for patient stratification, and for safely choosing the best patient treatment, reducing the risk of fracture, avoiding unneeded interventions, and optimising cost-effectiveness.
This interdisciplinary project has been running one and a half years. Briefly, this is the work performed so far:
• Standard operating procedures (SOP) have been established for the different research activities.
• All the ethical authorization relevant at this stage have been collected.
• A very large multicentric retrospective study, to retrieve data for training the models has been completed. This study has recruited 2000 cases, each case contains many data points.
• The initial steps have been initiated to conduct a multicentric prospective study, which will collect data to validate the models.
• Artificial Intelligence (AI) computation models are under development, suitable architectures have been identified and tested on open-source datasets. These models are now being prepared for training on the retrospective dataset.
• Pipelines for creating the different modules of a Physiology-based (VPH) biomechanical computational models are being developed and are undergoing testing. Initial steps have been taken to combine the models to create a singular Physiology-based (VPH) biomechanical computational model of an entire spine segment.
• The first steps towards regulatory compliance have been taken for a software as a medical device that can be brought to market.
• Communication materials have been developed and released to engage with several different stakeholders.
• Standard operating procedures (SOP) have been established for the different research activities.
• All the ethical authorization relevant at this stage have been collected.
• A very large multicentric retrospective study, to retrieve data for training the models has been completed. This study has recruited 2000 cases, each case contains many data points.
• The initial steps have been initiated to conduct a multicentric prospective study, which will collect data to validate the models.
• Artificial Intelligence (AI) computation models are under development, suitable architectures have been identified and tested on open-source datasets. These models are now being prepared for training on the retrospective dataset.
• Pipelines for creating the different modules of a Physiology-based (VPH) biomechanical computational models are being developed and are undergoing testing. Initial steps have been taken to combine the models to create a singular Physiology-based (VPH) biomechanical computational model of an entire spine segment.
• The first steps towards regulatory compliance have been taken for a software as a medical device that can be brought to market.
• Communication materials have been developed and released to engage with several different stakeholders.
We are developing Artificial Intelligence (AI)- and Physiology-based (VPH) biomechanical computational models to stratify patients with spine metastasis who are at high risk of fracture and to identify the best personalised surgical treatment. After rigorous model training with clinical (2000 retrospective cases) and biomechanical (120 ex vivo specimens) data, the new approach will be tested in a multicentric prospective observational study (200 patients). The models will be combined in a decision support system (DSS) enabling clinicians to successfully stratify metastatic patients. The models and the DSS will be designed so as to be suitable for regulatory requirements and future exploitation.