Advancing Vascular Surgery - The Role of Artificial Intelligence and Machine Learning in Managing Carotid Stenosis

Aug 5, 2026

Upload by Maeve

Cardiovascular disease affects 17.7 million people annually worldwide, and carotid degenerative disease—driven largely by atherosclerotic plaque accumulation—substantially contributes to cerebrovascular events and ischemic stroke. This review synthesizes evidence on how artificial intelligence and machine learning improve diagnosis, clinical staging, and risk stratification in carotid stenosis, supporting timely management and safer surgical decision-making. It summarizes deep-learning imaging advances, integration of clinical risk factors, and ML approaches for identifying culprit arteries, while addressing validation and data privacy challenges.

LanguageEnglish

CategoryHealthcare

FormatPDF

Pages10

Reading Time25 min

AccessFree to download

Abstract

Introduction

Epidemiology and clinical burden

Treatment options and perioperative risk

Predictors and need for improved prediction

Methods

Results

AI-enhanced imaging for plaque vulnerability

Integrating clinical risk factors with AI

ML for identifying culprit arteries

Conclusion

PORTUGUESE JOURNAL OF CARDIAC THORACIC AND VASCULAR SURGERY |
REVIEW ARTICLE | | | --- | --- | | ADVANCING VASCULAR SURGERY: THE ROLE OF ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING IN MANAGING CAROTID STENOSIS | | | Ana Daniela Pias*1, Juliana Pereira-Macedo2, 3, Ana Marreiros1, Nuno António4, João Rocha-Neves3, 5 | | | 1 Faculdade de Medicina e Ciências Biomédicas da Universidade do Algarve, Faro, Portugal
2 Department of General Surgery – Unidade Local de Saúde do Médio Ave, Santo Tirso, Portugal
3 RISE@Health, Rua Dr. Plácido da Costa, Porto, Portugal
4 NOVA Information Management School (NOVA IMS), Universidade NOVA de Lisboa, Lisbon, Portugal
5 Department of Biomedicine – Unit of Anatomy, Faculdade de Medicina da Universidade do Porto, Portugal | | | * Corresponding author: [daniela.pias@gmail.com](daniela.pias@gmail.com)
Abstract
Introduction: Cardiovascular diseases affect 17.7 million people annually, worldwide. Carotid degenerative disease, commonly described as atherosclerotic plaque accumulation, significantly contributes to this, posing a risk for cerebrovascular events and ischemic strokes. With carotid stenosis (CS) being a primary concern, accurate diagnosis, clinical staging, and timely surgical interventions, such as carotid endarterectomy (CEA), are crucial. This review explores the impact of Artificial Intelligence (AI) and Machine Learning (ML) in improving diagnosis, risk stratification, and management of CS.
Methods: A comprehensive literature review was conducted using PubMed and SCOPUS, focusing on AI and ML applications in diagnosing and managing extracranial CS. English language publications from the past two decades were reviewed, including cross-referenced scientific articles.
Results: Recent advancements in AI-enhanced imaging techniques, particularly in deep learning, have significantly improved diagnostic accuracy in identifying carotid plaque vulnerability and symptomatic plaques. Integration of clinical risk factors with AI systems has further enhanced precision. Additionally, ML models have shown promising results in identifying culprit arteries in patients with previous cerebrovascular events. These advancements hold immense potential for improving CS diagnosis and classification, leading to better patient management.
Conclusion: Integrating AI and ML into vascular surgery, particularly in managing CS, marks a transformative advancement. These technologies have significantly improved diagnostic accuracy and risk assessment, paving the way for more personalized and safer patient care. Despite clinical validation and data privacy challenges, AI and ML have immense potential for enhancing clinical decision-making in vascular surgery, marking a pivotal phase in the field's evolution.
Keywords: Carotid stenosis; carotid endarterectomy; perioperative stroke. | | | INTRODUCTION
Annually, around 17.7 million people are affected by cardiovascular (CV) diseases, including myocardial infarction (MI) and strokes, with atherosclerosis being the major contributor to these events.(1)
Carotid disease, which involves the accumulation of atherosclerotic plaques, is a significant risk factor forcerebrovascular events and ischemic strokes. It is estimated | that carotid disease affects roughly 27. 6% of individuals between the ages of 30 and 90, globally.(2)
For high-risk stroke patients with carotid stenosis (CS), carotid endarterectomy (CEA) is the preferred treatment, whether symptomatic or asymptomatic, while transfemoral carotid stenting (CAS) is considered as an alternative in selected cases.(3) However, it's important to note that every surgery involves inherent perioperative risks. Surgical interventions such as CEA often involve patients with multiple | 55 comorbidities, which categorizes these procedures as high-risk interventions.(4) Despite advancements in surgical techniques and perioperative care, certain patients undergoing CEA under regional

FAQs

How do AI and machine learning improve diagnosis in carotid stenosis?

They enhance diagnostic accuracy using AI-enhanced imaging techniques, especially deep learning, to identify carotid plaque vulnerability and symptomatic plaques.

What is the role of combining clinical risk factors with AI systems?

Integrating clinical risk factors with AI systems further improves precision in diagnosis and risk assessment for carotid stenosis management.

What challenges and limitations are highlighted for clinical use of AI and ML in vascular surgery?

Clinical validation and data privacy challenges are noted, alongside the overall potential to improve decision-making and patient care.

Aug 5, 2026

Upload by Maeve