Integrating Artificial Intelligence and Imaging in Peripheral Artery Disease: A Systematic Review from Diagnostics to Guided Endovascular Therapy

Abstract

Peripheral artery disease (PAD) is a significant vascular, which is the subject of early diagnosis, precise risk assessment, and proper endovascular treatment. The systematic review is a synthesis of evidence on 11 primary studies based on the PAD care pathway but published between 2021 and 2025 that tested the integration of artificial intelligence (AI), machine learning (ML), and advanced imaging tools. The AI-based Doppler waveform interpretation, biomarker-based diagnostic models, and clinical parameter-driven algorithms showed high accuracy in early PAD. Innovations in imaging that were developed such as fusion-guided endovascular systems minimised radiation exposure and contrast volume used during interventions. Doppler signal-based, clinical feature-based, biomarker-based, and genomic signature-based prognostic models demonstrated exemplary performance in major adverse limb events, cardiovascular complications, and mortality. In all fields, AI made significant strides in comparison with traditional approaches and offered practical information to aid personalised treatment planning. These results indicate that AI has the potential to improve accuracy, efficiency, and safety in modern PAD management.