Prediction of Cardiovascular Parameters With Supervised Machine Learning From Singapore “I” Vessel Assessment and OCT-Angiography: A Pilot Study

Arnould, Louis; Guenancia, Charles; Bourredjem, Abderrahmane; Binquet, Christine; Gabrielle, Pierre‐Henry; Eid, Pétra; Baudin, Florian; Kawasaki, Ryo; Cottin, Yves; Creuzot‐Garcher, Catherine; Jacquir, Sabir

doi:10.1167/tvst.10.13.20

Cited by 13 publications

(7 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This preliminary approach opens the way to assessing the value of OCT-A-based artificial intelligence analysis for CAC score evaluation. The quantitative analysis of retinal vascular density could implement automatic algorithms in order to refine cardiovascular risk stratification [ 37 , 38 , 39 ]. A quantitative analysis of retinal microvascularization using SS OCT-A imaging could offer an interesting new perspective on the link between the retina and atherosclerosis evaluation in FH.…”

Section: Discussionmentioning

confidence: 99%

Retinal Microvascular Changes in Familial Hypercholesterolemia: Analysis with Swept-Source Optical Coherence Tomography Angiography

Eid

Arnould

Gabrielle

et al. 2022

JPM

Self Cite

View full text Add to dashboard Cite

Familial hypercholesterolemia (FH) is a common but underdiagnosed genetic disorder affecting cholesterol metabolism, leading to atherosclerotic disease. The relationship between retinal microvascular changes and the presence of atheroma in patients with FH (FH group), and in comparison to volunteers without FH (CT group), needs further investigation. This cross-sectional study was conducted in a university hospital between October 1, 2020 and May 31, 2021. Cardiovascular data, including the Coronary Artery Calcium (CAC) score, were recorded for FH patients. Macula angiograms were acquired using swept-source optical coherence tomography angiography (SS OCT-A) to analyze both the superficial capillary plexus (SCP) and deep capillary plexus (DCP). A total of 162 eyes of 83 patients were enrolled in the FH group and 121 eyes of 78 volunteers in the CT group. A statistically significant association was found between the CAC score and both vessel density (β = −0.002 [95% CI, −0.004; −0.0005], p = 0.010) and vessel length (β = −0.00005 [95% CI, −0.00008; −0.00001], p = 0.010) in the DCP. The FH group had a significantly lower foveal avascular zone circularity index than the CT group in multivariate analysis (0.67 ± 0.16 in the FH group vs. 0.72 ± 0.10 in the CT group, β = 0.04 [95% CI, 0.002; 0.07], p = 0.037). Retinal microvascularization is altered in FH and retinal vascular densities are modified according to the CAC score.

show abstract

Section: Discussionmentioning

confidence: 99%

Retinal Microvascular Changes in Familial Hypercholesterolemia: Analysis with Swept-Source Optical Coherence Tomography Angiography

Eid

Arnould

Gabrielle

et al. 2022

JPM

Self Cite

View full text Add to dashboard Cite

show abstract

“…Second, Reti-CVD can aid the CVD prevention program that NHS England has developed. The NHS CVD primary prevention focusses on three main components: atrial fibrillation, blood pressure, and cholesterol [ 28 ]. Given that our study included individuals who are not on statin or anti-hypertensive medication in the general population, physicians can use Reti-CVD while monitoring patients’ blood pressure and cholesterol levels to better predict CVD risk.…”

Section: Discussionmentioning

confidence: 99%

Validation of a deep-learning-based retinal biomarker (Reti-CVD) in the prediction of cardiovascular disease: data from UK Biobank

Tseng

Rim

Shantsila

et al. 2023

BMC Med

View full text Add to dashboard Cite

Background Currently in the United Kingdom, cardiovascular disease (CVD) risk assessment is based on the QRISK3 score, in which 10% 10-year CVD risk indicates clinical intervention. However, this benchmark has limited efficacy in clinical practice and the need for a more simple, non-invasive risk stratification tool is necessary. Retinal photography is becoming increasingly acceptable as a non-invasive imaging tool for CVD. Previously, we developed a novel CVD risk stratification system based on retinal photographs predicting future CVD risk. This study aims to further validate our biomarker, Reti-CVD, (1) to detect risk group of ≥ 10% in 10-year CVD risk and (2) enhance risk assessment in individuals with QRISK3 of 7.5–10% (termed as borderline-QRISK3 group) using the UK Biobank. Methods Reti-CVD scores were calculated and stratified into three risk groups based on optimized cut-off values from the UK Biobank. We used Cox proportional-hazards models to evaluate the ability of Reti-CVD to predict CVD events in the general population. C-statistics was used to assess the prognostic value of adding Reti-CVD to QRISK3 in borderline-QRISK3 group and three vulnerable subgroups. Results Among 48,260 participants with no history of CVD, 6.3% had CVD events during the 11-year follow-up. Reti-CVD was associated with an increased risk of CVD (adjusted hazard ratio [HR] 1.41; 95% confidence interval [CI], 1.30–1.52) with a 13.1% (95% CI, 11.7–14.6%) 10-year CVD risk in Reti-CVD-high-risk group. The 10-year CVD risk of the borderline-QRISK3 group was greater than 10% in Reti-CVD-high-risk group (11.5% in non-statin cohort [n = 45,473], 11.5% in stage 1 hypertension cohort [n = 11,966], and 14.2% in middle-aged cohort [n = 38,941]). C statistics increased by 0.014 (0.010–0.017) in non-statin cohort, 0.013 (0.007–0.019) in stage 1 hypertension cohort, and 0.023 (0.018–0.029) in middle-aged cohort for CVD event prediction after adding Reti-CVD to QRISK3. Conclusions Reti-CVD has the potential to identify individuals with ≥ 10% 10-year CVD risk who are likely to benefit from earlier preventative CVD interventions. For borderline-QRISK3 individuals with 10-year CVD risk between 7.5 and 10%, Reti-CVD could be used as a risk enhancer tool to help improve discernment accuracy, especially in adult groups that may be pre-disposed to CVD.

show abstract

“…In research settings, photographs with multiple ocular diseases were usually excluded to prevent the potential concomitant influences on CVD prediction. Arnould et al [53 ▪▪ ] evaluated the accuracy of a machine learning system in predicting CVD risk scores based on quantitative retinal vascular parameters measured from both retinal photographs and OCT-angiography images. Although the algorithm performed well with more than 80% accuracy compared with the traditional American Hospital Association (AHA) risk score, they excluded those with vascular occlusion, diabetic retinopathy and macular degeneration from the study [53 ▪▪ ].…”

Section: Current Challengesmentioning

confidence: 99%

“…Arnould et al [53 ▪▪ ] evaluated the accuracy of a machine learning system in predicting CVD risk scores based on quantitative retinal vascular parameters measured from both retinal photographs and OCT-angiography images. Although the algorithm performed well with more than 80% accuracy compared with the traditional American Hospital Association (AHA) risk score, they excluded those with vascular occlusion, diabetic retinopathy and macular degeneration from the study [53 ▪▪ ]. However, it is common for patients in clinical settings to present with multiple diseases.…”

Section: Current Challengesmentioning

confidence: 99%

Artificial intelligence in retinal imaging for cardiovascular disease prediction: current trends and future directions

Wong

Lam

Ran

et al. 2022

Current Opinion in Ophthalmology

View full text Add to dashboard Cite

Purpose of reviewRetinal microvasculature assessment has shown promise to enhance cardiovascular disease (CVD) risk stratification. Integrating artificial intelligence into retinal microvasculature analysis may increase the screening capacity of CVD risks compared with risk score calculation through blood-taking. This review summarizes recent advancements in artificial intelligence based retinal photograph analysis for CVD prediction, and suggests challenges and future prospects for translation into a clinical setting. Recent findingsArtificial intelligence based retinal microvasculature analyses potentially predict CVD risk factors (e.g. blood pressure, diabetes), direct CVD events (e.g. CVD mortality), retinal features (e.g. retinal vessel calibre) and CVD biomarkers (e.g. coronary artery calcium score). However, challenges such as handling photographs with concurrent retinal diseases, limited diverse data from other populations or clinical settings, insufficient interpretability and generalizability, concerns on cost-effectiveness and social acceptance may impede the dissemination of these artificial intelligence algorithms into clinical practice.

show abstract

Prediction of Cardiovascular Parameters With Supervised Machine Learning From Singapore “I” Vessel Assessment and OCT-Angiography: A Pilot Study

Cited by 13 publications

References 34 publications

Retinal Microvascular Changes in Familial Hypercholesterolemia: Analysis with Swept-Source Optical Coherence Tomography Angiography

Retinal Microvascular Changes in Familial Hypercholesterolemia: Analysis with Swept-Source Optical Coherence Tomography Angiography

Validation of a deep-learning-based retinal biomarker (Reti-CVD) in the prediction of cardiovascular disease: data from UK Biobank

Artificial intelligence in retinal imaging for cardiovascular disease prediction: current trends and future directions

Contact Info

Product

Resources

About