Endoleak Risk Index (ERI)

Guiding surgeons toward optimal device selection to reduce the chances of complications and enhance patients’ outcomes.

FOR CLINICIANS & MEDTECH TEAMS

Assess type 1A Endoleak risk before EVAR intervention

Explore various endograft diameters, landing zones and choose the optimal configuration for the patient

AI-POWERED TECHNOLOGY

16,000 data points measured around the proximal neck

Ask for a Demo

Clinical Validation

Validation Study - EnduSim II

Retrospective European multicenter study  - ongoing enrollment: Prof Antoine Millon, University Hospitals of Lyon.

Training dataset: 117 patients (Type 1A endoleaks: 34 (13 early, 21 late), 83 controls.

Validation dataset: 56 patients
Assessment blinded to Endoleak status. 20 type 1A Endoleaks (6 early, 14 late), 36 controls.

Ask for a Demo
Core capabilities

AI-Powered EVAR Planning

Distance Colour Map

With iView Colour, instantly highlight the apposition gaps between the graft and aortic wall thanks to Distance Colour Map.

Benefits
Ease risk assessment.
Visually detect critical apposition.
Facilitate simulation comparison understanding.
Ask for a Demo
testimonials

The expert perspective

First-hand experience from operating rooms to R&D labs — professionals trust PrediSurge to improve outcomes, enhance safety, and accelerate innovation.

“Since we started to use this technology, we have been very impressed with the precision of fenestration positioning associated with outstanding intra and postoperative results…”

Pr. A. Millon
Lyon University Hospitals
Lyon, France

“PrediSurge technology will represent a significant breakthrough in planning and visualization for endovascular intervention.”

Pr. S. Haulon
Lannelongue Hospital
Paris, France

“PrediSurge technology will profoundly change the planning approach for mitral valve interventions. It will be used by most cardiac centers on a routine basis before any mitral intervention.”

Pr. D. Messika-Zeitoun
Professor of Cardiology
University of Ottawa Heart Institute

“We strongly believe that this technique will be the gold standard for aortic stent-graft planning and other endovascular procedures in the very near future, bringing huge benefits to patients”

Pr. A. Assadian
Klinik Ottakring
Vienna, Austria
use cases

Clinical Stories

Insights from clinical and R&D practice, directly from our experts

ERI in action

This case, presented by Dr. Nilo J. Mosquera from Hospital Santiago de Compostela, Spain, highlights how a hostile proximal neck can be managed using ERI to leverage AI-powered Digital Twin technology, enhancing clinical decision-making and improving patient outcomes.

news & blog

Press highlights & Insights

Independent recognition through clinical research and media coverage and PrediSurge insights

Answers to common questions

Frequently asked questions

Book a Free Call

What is aortic digital twin?

From a patient’s pre-operative CT scan, the aortic digital twin is created to faithfully reproduce both the shape and the bio mechanical behavior of the real aorta. This advanced 3D model allows precise simulation of how the patient’s anatomy responds to mechanical forces, providing a reliable virtual counterpart of the vessel.

What is ERI?

ERI stands for Endoleak Risk Index, is an AI-powered index based on the analysis of the intervention simulation, with a specific focus on the proximal apposition between the endograft and the patient-specific aortic digital twin. It assesses preoperatively the risk of Type IA endoleak associated with EVAR.

How is ERI calculated?

Each EVAR simulation automatically analyses the proximal aortic neck using 40 cross-sectional slices. For each slice, the aortic wall and endograft are sampled at 200 points each to measure local radii and apposition. This generates up to 16,000 detailed measurements per patient.

Are thrombus and calcifications taken into account?

It is important to distinguish between two different stages of analysis:

  • Simulation: Only the aortic lumen is modeled; thrombus and calcifications are not yet included.
  • Risk assessment (ERI): Thrombus burden is included as a variable in the machine-learning model used to compute risk.