Perez Sean, Thandra Sneha, Mellah Ines, Kraemer Laura, Ross Elsie
Department of Surgery, University of California San Diego Health, La Jolla, San Diego, CA USA.
University of California San Diego School of Medicine, La Jolla, San Diego, CA USA.
Curr Cardiovasc Risk Rep. 2024;18(12):187-195. doi: 10.1007/s12170-024-00752-7. Epub 2024 Nov 4.
Peripheral Artery Disease (PAD), a condition affecting millions of patients, is often underdiagnosed due to a lack of symptoms in the early stages and management can be complex given differences in genetic and phenotypic characteristics. This review aims to provide readers with an update on the utility of machine learning (ML) in the management of PAD.
Recent research leveraging electronic health record (EHR) data and ML algorithms have demonstrated significant advances in the potential use of automated systems, namely artificial intelligence (AI), to accurately identify patients who might benefit from further PAD screening. Additionally, deep learning algorithms can be used on imaging data to assist in PAD diagnosis and automate clinical risk stratification.ML models can predict major adverse cardiovascular events (MACE) and major adverse limb events (MALE) with considerable accuracy, with many studies also demonstrating the ability to more accurately risk stratify patients for deleterious outcomes after surgical intervention. These predictions can assist physicians in developing more patient-centric treatment plans and allow for earlier, more aggressive management of modifiable risk-factors in high-risk patients. The use of proteomic biomarkers in ML models offers a valuable addition to traditional screening and stratification paradigms, though clinical utility may be limited by cost and accessibility.
The application of AI to the care of PAD patients may enable earlier diagnosis and more accurate risk stratification, leveraging readily available EHR and imaging data, and there is a burgeoning interest in incorporating biological data for further refinement. Thus, the promise of precision PAD care grows closer. Future research should focus on validating these models via real-world integration into clinical practice and prospective evaluation of the impact of this new care paradigm.
外周动脉疾病（PAD）影响着数百万患者，由于早期缺乏症状，该病常常未被充分诊断，而且鉴于遗传和表型特征的差异，其管理可能很复杂。本综述旨在为读者提供机器学习（ML）在PAD管理中的应用的最新情况。
最近利用电子健康记录（EHR）数据和ML算法的研究表明，在使用自动化系统（即人工智能（AI））准确识别可能从进一步的PAD筛查中受益的患者方面取得了重大进展。此外，深度学习算法可用于影像数据，以协助PAD诊断并实现临床风险分层自动化。ML模型能够相当准确地预测主要不良心血管事件（MACE）和主要不良肢体事件（MALE），许多研究还表明其有能力更准确地对手术干预后有害结局的患者进行风险分层。这些预测可以帮助医生制定更以患者为中心的治疗计划，并允许对高危患者的可改变风险因素进行更早、更积极的管理。在ML模型中使用蛋白质组学生物标志物为传统的筛查和分层模式提供了有价值的补充，尽管临床应用可能受到成本和可及性的限制。
将AI应用于PAD患者的护理可能有助于早期诊断和更准确的风险分层，利用现有的EHR和影像数据，并且人们对纳入生物数据以进一步完善的兴趣日益浓厚。因此，精准PAD护理的前景越来越近。未来的研究应侧重于通过实际整合到临床实践中验证这些模型，并对这种新护理模式的影响进行前瞻性评估。
