RESUMO
BACKGROUND: Artificial intelligence (AI) that utilizes deep learning (DL) has potential for systemic disease prediction using retinal imaging. The retina's unique features enable non-invasive visualization of the central nervous system and microvascular circulation, aiding early detection and personalized treatment plans for personalized care. This review explores the value of retinal assessment, AI-based retinal biomarkers, and the importance of longitudinal prediction models in personalized care. MAIN TEXT: This narrative review extensively surveys the literature for relevant studies in PubMed and Google Scholar, investigating the application of AI-based retina biomarkers in predicting systemic diseases using retinal fundus photography. The study settings, sample sizes, utilized AI models and corresponding results were extracted and analysed. This review highlights the substantial potential of AI-based retinal biomarkers in predicting neurodegenerative, cardiovascular, and chronic kidney diseases. Notably, DL algorithms have demonstrated effectiveness in identifying retinal image features associated with cognitive decline, dementia, Parkinson's disease, and cardiovascular risk factors. Furthermore, longitudinal prediction models leveraging retinal images have shown potential in continuous disease risk assessment and early detection. AI-based retinal biomarkers are non-invasive, accurate, and efficient for disease forecasting and personalized care. CONCLUSION: AI-based retinal imaging hold promise in transforming primary care and systemic disease management. Together, the retina's unique features and the power of AI enable early detection, risk stratification, and help revolutionizing disease management plans. However, to fully realize the potential of AI in this domain, further research and validation in real-world settings are essential.
RESUMO
Background: The ultrathin-strut drug-eluting stent (DES) has shown better clinical results than thin- or thick-strut DES. We investigated if re-endothelialization was different among three types of DES: ultrathin-strut abluminal polymer-coated sirolimus-eluting stent (SES), thin-strut circumferential polymer-coated everolimus-eluting stent (EES), and thick-strut polymer-free biolimus-eluting stent (BES) to gain insight into the effect of stent design on promoting vascular healing. Methods: After implanting three types of DES in the coronary arteries of minipigs, we performed optical coherence tomography (OCT) at weeks 2, 4, and 12 (n = 4, each). Afterward, we harvested the coronary arteries and performed immunofluorescence for endothelial cells (ECs), smooth muscle cells (SMCs), and nuclei. We obtained 3D stack images of the vessel wall and reconstructed the en face view of the inner lumen. We compared re-endothelialization and associated factors among the different types of stents at different time points. Results: SES showed significantly faster and denser re-endothelialization than EES and BES at weeks 2 and 12. Especially in week 2, SES elicited the fastest SMC coverage and greater neointimal cross-sectional area (CSA) compared to EES and BES. A strong correlation between re-endothelialization and SMC coverage was observed in week 2. However, the three stents did not show any difference at weeks 4 and 12 in SMC coverage and neointimal CSA. At weeks 2 and 4, SMC layer morphology showed a significant difference between stents. A sparse SMC layer was associated with denser re-endothelialization and was significantly higher in SES. Unlike the sparse SMC layer, the dense SMC layer did not promote re-endothelialization during the study period. Conclusion: Re-endothelialization after stent implantation was related to SMC coverage and SMC layer differentiation, which were faster in SES. Further investigation is needed to characterize the differences among the SMCs and explore methods for increasing the sparse SMC layer in order to improve stent design and enhance safety and efficacy.