Jul 2026· Ageing Research Reviews· Vol 121, pp.
103247
· 0 citations· 209 references
Medicine
TL;DR
This review provides a comprehensive overview of current AI applications in vascular aging, spanning from basic mechanistic research to clinical risk prediction and discusses future directions and key challenges, including the need for external validation, algorithmic fairness, domain adaptation, and model interpretability.
Abstract
Vascular aging is a fundamental contributor to the development of chronic diseases and has emerged as a critical focus in biomedical research. With the rapid advancement of artificial intelligence (AI), new opportunities have arisen to enhance the precision and efficiency of vascular aging studies. AI techniques, particularly those applied to large-scale multi-omics and medical imaging data, enable the identification of novel biomarkers and the development of robust models to quantify the rate and extent of vascular aging. For example, AI has been successfully deployed for multi-omics biomarker discovery, automated quantification of coronary plaque and calcium scoring from CT imaging, and the development of vascular aging clocks based on retinal images or photoplethysmography (PPG). These approaches facilitate early detection, individualized risk assessment, and potential intervention strategies. This review provides a comprehensive overview of current AI applications in vascular aging, spanning from basic mechanistic research to clinical risk prediction. It also discusses future directions and key challenges, including the need for external validation, algorithmic fairness, domain adaptation, and model interpretability, emphasizing the transformative role of AI in advancing precision medicine for vascular health.
Coronary artery disease (CAD) is a typical age-related chronic condition, with its development and progression spanning a long course of life and exhibiting significant inter-individual heterogeneity. Traditional risk assessment models based on chronological age and single risk factors are often insufficient to capture the cumulative physiological decline and the dynamic progression of disease. In this review, biological age, as a comprehensive indicator reflecting an individual’s true aging status, has gradually emerged as an important tool for understanding differences in CAD risk and disease progression. In recent years, various methods for assessing biological age have been applied in CAD research, primarily including composite biological age derived from routine clinical indicators, telomere length, and epigenetic clocks. Evidence suggests that different biological age markers provide complementary information and are suited into distinct applications. Among them, composite clinical biological age, based on routine clinical measurements, can dynamically reflect multi-system functional changes and has demonstrated feasibility and stability in CAD risk stratification, disease progression monitoring, and evaluation of intervention effects, highlighting its potential clinical utility. Telomere length and epigenetic clocks, on the other hand, provide supplementary information at the cellular and molecular regulatory levels regarding cumulative physiological burden and aging mechanisms. Looking forward, integrating molecular-level aging markers with composite clinical biological age to establish a multi-tiered assessment framework may improve early identification and precision intervention for CAD and other chronic diseases.
Ru Sun, Weijian Hang, Ling Zhou et al.· International Journal of Dru...· 0 citations
Cardiovascular disease (CVD) is a major source of morbidity and mortality across the globe. Effective screening and risk stratification of patients can improve long‑term outcomes by allowing physicians to offer fine-tuned advice and treatments. Advances in technology have enabled the study of various biomarkers associated with CVD, allowing researchers to study the molecular processes underlying illness. In this study, we sampled recent advances in the application of Machine Learning (ML) techniques to transcriptome datasets of CVD patients in the hopes of progressing our understanding of underlying pathophysiology, improving our ability to detect disease, and refining our methods of risk stratification of patients. These studies suggest that ML algorithms may help identify complex relationships within high-dimensional datasets to isolate relationships within datasets that were previously missed, enhancing our understanding of disease. However, there are several challenges that need to be addressed before these innovations can reach the clinic. Researchers must verify their results via means that are readily obtainable for physicians and must adequately identify the indications for a particular test so they can integrate into preexisting workflows. We offer potential solutions and suggestions to these issues so that these approaches may eventually contribute to improved patient care.
The identification of valid biomarkers for ischemic stroke would greatly benefit not only diagnostic and prognostic assessment but also the development of new therapies. The development of omics technologies has made it possible to explore various perspectives of the pathophysiology of ischemic stroke, in particular genomics, transcriptomics, proteomics and metabolomics, and well-known clinical variables, such as hypertension, diabetes, heart diseases, and many others. Omics-based research has produced a mass of data evidencing candidate biomarkers at different stages in the disease process. However, further scientific evidence must be presented and affordable, and rapid detection techniques developed before these technologies can be usefully applied to the clinical setting of stroke. Here, we aim to provide stroke clinicians with an updated overview of the contribution of these emerging technologies in the individuation of diagnostic and prognostic biomarkers and the development of specifically targeted therapies. Cross-fertilization (translation and reverse translation) between preclinical and clinical research is of particular relevance in the identification of stroke biomarkers. We believe it is useful to provide, in parallel, an updated review of omics investigations using stroke rodent models. This review presents a detailed discussion of the state of the art, focusing on the strengths and limitations of the individual technologies and an outline of the promising, most recent results of both clinical and preclinical research in this field related to stroke.
Emilia Conti, M. Baldereschi, A. Di Carlo et al.· Journal of Clinical Medicine· 0 citations
This review focuses on the transition from single-omics to integrative multi-omics analysis, which helps overcome the constraints of individual omics strategies and provides a more systematic understanding of PD pathogenesis.
This paper summarizes recent advances in biosensor technologies, AI-derived biomarkers, and predictive frameworks used to help identify patients more accurately, monitor their progress continuously, and receive optimized therapies.
S. Bukke, Chandrashekar Thalluri, Mallikarjun Vasam et al.· Personalized Medicine· 0 citations
Diabetic cardiomyopathy (DCM) is a cardiac condition characterized by various structural and functional abnormalities that are associated with diabetes mellitus. Its development involves multiple factors, among which endothelial dysfunction plays a significant role. To fully describe the relationship between DCM and endothelial dysfunction, we conducted a literature search across several databases, including PubMed, Web of Science, and EMBASE. Our review of DCM research focused on understanding its mechanisms, exploring the methods used to diagnose it, and potential treatment options. Although researchers have made significant progress in DCM diagnosis and treatment in recent years, considerable challenges persist as well. Artificial intelligence (AI)-based multimodal approaches may provide new opportunities for cardiovascular risk stratification and early DCM screening, but DCM-specific models still require external validation before clinical implementation. Regarding treatment options, emerging evidence suggests potential benefits of medications that enhance mitochondrial function and antioxidant properties, as well as anti-inflammatory therapies and lifestyle modifications. Future research should focus on combining different relevant data types, such as genetic and molecular information, to improve the AI tools utilized in medical environments. This study aims to identify novel markers for diagnosing DCM and to devise tailored treatment approaches. These advancements have the potential to improve the prognosis of DCM patients and enhance the identification and management of this condition.
Sheng-Ying Jia, Li Wang, Zuowei Pei· Journal of Cardiovascular De...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
