Developing Trustworthy Artificial Intelligence (AI)-Driven Tools to Predict Vascular Disease Risk and Progression: the Prospective VASCUL-AID Study

Overview

Introduction: Peripheral arterial disease (PAD) and abdominal aortic aneurysm (AAA) are vascular conditions associated with significant morbidity and mortality, with 25% of AAA patients and 23% of PAD patients being at a high risk of developing cardiovascular disease. Cardiovascular risk management can reduce the risk of major adverse cardiovascular events in AAA patients from 43% to 14%. However, cardiovascular risk is not always adequately addressed in these patients. The VASCUL-AID-PRO study aims to deliver clinically relevant prediction models using artificial intelligence and machine learning of patient outcomes to enable personalized management of vascular disease. Method: VASCUL-AID-PRO is a multi-centre international prospective cross-sectional study aiming to include 500 AAA patients and 600 PAD patients across 6 European centres. The aim is to achieve a follow-up time up to 4 years. The study will include individuals aged 40-90 with either an abdominal aortic aneurysm (infrarenal, juxtarenal, pararenal, or suprarenal abdominal aortic aneurysm) or Fontaine stage 2 peripheral arterial disease. The VASCUL-AID-PRO study will gather a variety of data from all participants, including clinical data, blood and tissue samples, cardiovascular lab values, imaging data, electrocardiograms, data from wearables and quality of life. This data gathered will be used to further develop the multi model prediction models being developed on 5000 AAA and 6000 PAD patients included in the currently ongoing VASCUL-AID-RETRO study, with the aim of providing a clinically relevant prediction models of disease progression and other cardiovascular disease for AAA and PAD patients. Furthermore, the models developed in the VASCUL-AID studies will be internally validated using a subset of patients from the VASCUL-AID-PRO study. Ethical considerations: Ethical and legal considerations are paramount throughout the VASCUL-AID project. To address these concerns, an ELSI framework will be developed and integrated into all stages of the project. This framework will be continuously updated to ensure alignment with evolving ethical, legal, and social standards. This framework will specifically focus on patient safety, data handling, AI regulation and implementation, and potential biases associated with AI.

Primary outcome measures

• Development and internal validation of AI-driven tools to predict high or low risk disease progression in AAA and PAD. [Time frame: From baseline to 4 years follow-up.]

Secondary outcome measures (12)

• Accuracy of developed VASCUL-AID driven algorithms that classify AAA patients according to high or low risk disease progression. [Time frame: From baseline to 4 years follow-up]
• Accuracy of developed VASCUL-AID driven algorithms that classify PAD patients according to high or low risk disease progression. [Time frame: From baseline to 4 years follow-up]
• Patient reported outcome measures for AAA and PAD. [Time frame: From baseline to 4 years follow-up.]
• Patient reported outcome measures for health-related quality of life. [Time frame: From baseline to 4 year follow-up.]
• Patient reported outcome measures for health-related quality of life. [Time frame: From baseline to 4 year follow-up]
• Patient reported outcome measures for health-related quality of life. [Time frame: From baseline to 4 years follow-up.]
• Patient reported outcome measures for vascular quality of life for PAD. [Time frame: From baseline to 4 year follow-up]
• Patient reported outcome measures for AAA related quality of life. [Time frame: From baseline to 4 year follow-up.]
• Questions regarding medical status. [Time frame: From baseline to 4 year follow-up]
• 6-minute walking test questionnaire [Time frame: From baseline to 4 year follow-up]
• Medication use questionnaire [Time frame: From baseline to 4 year follow-up]
• Smoking cessation questionnaire [Time frame: From baseline to 4 year follow-up.]

Eligibility criteria

Inclusion Criteria AAA:

• Males/females between 40 and 90 years of age.
• Males and females with AAA at inclusion, any diameter >3 cm (or 1.5x larger than their non-dilated part of the aorta).
• Include: infrarenal, juxtarenal, pararenal, suprarenal abdominal aortic aneurysms.

Exclusion Criteria AAA:

Patients with:

• Insufficient schooling or sensorial deficits that interfere understanding informed consent.
• Not able to use the VASCUL-AID mobile health app (that will be provided in Dutch, English, German, Portuguese, Serbian, Finish, Swedish languages).
• Proven or highly suspected for infected, mycotic AAA
• Previous AAA surgery or planned for an AAA surgery within 6 months
• Ruptured AAA

Inclusion Criteria PAD:

• Males/females between 40 and 90 years of age.
• Patients with peripheral arterial disease stage Fontaine 2a and 2b at inclusion. Medical history (e.g. CLTI) does not matter, current disease stage is leading at inclusion.

Exclusion Criteria PAD:

Patients with:

• Insufficient schooling or sensorial deficits that interfere understanding informed consent.
• Not able to use the VASCUL-AID mobile health app (provided in Dutch, English, German, Portuguese, Serbian, Finnish, Swedish languages).

Criteria are shown verbatim from the registry (in English). Final eligibility is always assessed by the study center.

Healthy volunteers: No

Study design

Observational model

Cohort

Study locations

Center list to be confirmed — check the primary protocol.

Identifiers

NCT: NCT07187700 · 2025.0042

Primary sources (government registries)

• ClinicalTrials.gov (US NIH)

View this study on ClinicalTrials.gov ↗