Developing Trustworthy Artificial Intelligence (AI)-Driven Tools to Predict Vascular Disease Risk and Progression (VASCULAIDRETRO)

The VASCULAID-RETRO study, within the broader VASCULAID project, aims to create artificial intelligence (AI) algorithms that can predict cardiovascular events and the progression of abdominal aortic aneurysm (AAA) and peripheral arterial disease (PAD). The study plans to gather and analyze data from at least 5000 AAA and 6000 PAD patients, combining existing cohorts and retrospectively collected data. During this project, AI tools will be developed to perform automatic anatomical segmentation and analyses on multimodal imaging. AI prediction algorithms will be developed based on multisource data (imaging, medical history, -omics).

Study Overview

• Status: Recruiting
• Conditions: Peripheral Arterial Disease; Aneurysm Abdominal
• Intervention / Treatment: Other: No intervention, retrospective study

Detailed Description

To date, it is unknown which abdominal aortic aneurysm (AAA) and peripheral arterial disease (PAD) patients will suffer cardiovascular events or in which patients the AAA or PAD will progress. In the VASCULAID project, the VASCULAID-RETRO study aims to leverage data from existing cohorts and retrospectively collected data to develop artificial intelligence (AI) algorithms able to evaluate the risk of cardiovascular events and extent of disease progression.

In order to build and train the algorithms for the predictions, we plan to retrospectively enroll at least 5000 AAA and 6000 PAD patients AI-tools will be applied to the patient data. Automatic anatomical segmentation on images and image analysis on US, CTA and MRI will be performed. Also, algorithms to predict cardiovascular events and AAA or PAD progression based on multi-source data analysis will be developed.

Patient data from European clinical consortium partners is available. This consortium has access to big cohorts with relevant data for the envisioned study that will be used to enrich the existing registries. These data will be used to refine the algorithms developed for the prediction of cardiovascular events and AAA/PAD progression.

• Study Type: Observational
• Enrollment (Estimated): 11000

Contacts and Locations

• Study Contact: Name: Kak Khee Yeung, MD, PhD; Phone Number: +31 6 14278725; Email: k.yeung@amsterdamumc.nl
• Study Contact Backup: Name: Lotte Rijken, Msc.; Email: l.rijken@amsterdamumc.nl

Study Locations

• Finland
  • Helsinki, Finland
    • Recruiting
    • Hospital District of Helsinki and Uusimaa (HUS)
    • Contact: Riikka Tulamo
• Germany
  • Hamburg, Germany
    • Recruiting
    • Asklepios Kliniken Hamburg
    • Contact: Christian Behrendt
• Netherlands
  • Amsterdam, Netherlands
    • Recruiting
    • Amsterdam UMC
    • Contact: Kak Khee Yeung
• Portugal
  • Porto, Portugal
    • Recruiting
    • University Hospital Center of São João
    • Contact: Marina Dias-Neto
• Serbia
  • Belgrade, Serbia
    • Recruiting
    • University Clinical Centre of Serbia
    • Contact: Igor Koncar
• United Kingdom
  • Oxford, United Kingdom
    • Recruiting
    • Oxford University Hospitals
    • Contact: Regent Lee

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: No

• Sampling Method: Non-Probability Sample

Study Population

Males and females between 40 and 90 years of age with an abdominal aortic aneurysm and/or peripheral arterial disease.

Description

Inclusion Criteria:

• Males and females, 40-90 years old, with an AAA >3cm. This includes patients with infrarenal, juxtarenal, suprarenal, iliac (defined as 1.5x its normal diameter) aneurysms, as well as mycotic aneurysms. Patients that have had interventions or ruptures will also be included
• Males and females, 40-90 years old, all PAD patients (Fontaine stages 1,2,3, and 4).

Exclusion Criteria:

• Patients with an ascending, thoracic, thoracoabdominal (type 1-3) aneurysm.

Study Plan

How is the study designed?

Number of groups / cohorts

2

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
Abdominal Aortic Aneurysm patients	Other: No intervention, retrospective study; No intervention, retrospective study
Peripheral Arterial Disease patients	Other: No intervention, retrospective study; No intervention, retrospective study

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Development of disease progression prediction algorithms	The primary goal of this retrospective study is to develop and train algorithms to predict disease progression and risk of cardiovascular events in AAA and PAD patients by leveraging multi-parametric data from 5000 AAA (>1000 in AUMC) and 6000 PAD (>1000 in AUMC) patients from existing cohorts and biobanks.	3 years

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Internal validation of disease progression prediction algorithms	The secondary objective will be the internal validation of the developed algorithms using data from retrospective cohorts.	3 years

Collaborators and Investigators

• Sponsor: Amsterdam UMC, location VUmc
• Collaborators: University of Bergen; University of Oxford; Centre Hospitalier Universitaire de Nice; Academisch Medisch Centrum - Universiteit van Amsterdam (AMC-UvA); Universidade do Porto; Asklepios Kliniken Hamburg GmbH; Hospital District of Helsinki and Uusimaa; Technical University of Twente; Faculty of Medicine, University of Belgrade; Stichting Allai; Brightfish Be; VINČA INSTITUTE OF NUCLEAR SCIENCES Belgrado

Study record dates

Study Major Dates

• Study Start (Actual): October 31, 2023
• Primary Completion (Estimated): May 1, 2029
• Study Completion (Estimated): May 1, 2029

Study Registration Dates

• First Submitted: January 4, 2024
• First Submitted That Met QC Criteria: January 4, 2024
• First Posted (Actual): January 16, 2024

Study Record Updates

• Last Update Posted (Actual): January 16, 2024
• Last Update Submitted That Met QC Criteria: January 4, 2024
• Last Verified: January 1, 2024

More Information

Terms related to this study

• Keywords: Artificial Intelligence, Prediction models, Image analysis, Abdominal Aortic Aneurysms, Peripheral Arterial Disease
• Additional Relevant MeSH Terms: Cardiovascular Diseases; Arteriosclerosis; Arterial Occlusive Diseases; Atherosclerosis; Aortic Diseases; Aortic Aneurysm; Vascular Diseases; Peripheral Arterial Disease; Peripheral Vascular Diseases; Aneurysm; Aortic Aneurysm, Abdominal
• Other Study ID Numbers: 2011279

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No