In particular, projects should:

• Access and integrate clinical data routinely generated using existing technologies during the patient journey (e.g. medical history profile of patients, diagnosis achieved, for example, by medical imaging and in-vitro diagnostic (IVD) tests, digital information generated during the hospital procedure, vital signs and anaesthesia management, electronic healthcare record systems (EHRs), and drug prescriptions such as analgesics). Suitable, secure IT infrastructure to support edge and cloud computing in compliance with the general data protection regulation (GDPR) and other data privacy policies at national and local levels should be utilised.
• Train and clinically validate explainable AI algorithms to support the development of training programmes, procedure planning and intraoperative assistance solutions, including clinical decision support systems.
• Demonstrate, via use cases using these data & algorithms, how combinations of and/or synergies between the above-mentioned tools, technologies, and therapeutic approaches can be harnessed to improve patient care. This should include comparing the combination of innovative interventional approaches and clinical decision support systems (CDSS) versus limited or no systematic combination of these innovative interventional approaches and CDSS.
• Implement tools to confirm successful treatment during or after the procedure and monitor therapy response and disease regression.
• Develop and implement new methodologies to assess and demonstrate the added value of combining innovative interventional approaches and clinical decision support systems to all relevant stakeholders.
• Encourage the uptake of the results of the project through a strong communication and outreach plan, including the publication of a gap assessment in order to guide future research in this field.