Search

BACKGROUND: Atherosclerotic cardiovascular disease (ASCVD) is a leading cause of death globally, and early detection of high-risk individuals is essential for initiating timely interventions. The authors aimed to develop and validate a deep learning (DL) model to predict an individuals elevated 10-year ASCVD risk score based on retinal images and limited demographic data. METHODS: The study used 89,894 retinal fundus images from 44,176 UK Biobank participants (96% non-Hispanic White, 5% diabetic) to train and test the DL model. The DL model was developed using retinal images plus age, race/ethnicity, and sex at birth to predict an individuals 10-year ASCVD risk score using the pooled cohort equation (PCE) as the ground truth. This model was then tested on the US EyePACS 10K dataset (5.8% non-Hispanic White, 99.9% diabetic), composed of 18,900 images from 8969 diabetic individuals. Elevated ASCVD risk was defined as a PCE score of ≥7.5%. RESULTS: In the UK Biobank internal validation dataset, the DL model achieved an area under the receiver operating characteristic curve of 0.89, sensitivity 84%, and specificity 90%, for detecting individuals with elevated ASCVD risk scores. In the EyePACS 10K and with the addition of a regression-derived diabetes modifier, it achieved sensitivity 94%, specificity 72%, mean error -0.2%, and mean absolute error 3.1%. CONCLUSION: This study demonstrates that DL models using retinal images can provide an additional approach to estimating ASCVD risk, as well as the value of applying DL models to different external datasets and opportunities about ASCVD risk assessment in patients living with diabetes.

Deep learning (DL) models have shown promise in detecting chronic kidney disease (CKD) from fundus photographs. However, previous studies have utilized a serum creatinine-only estimated glomerular rate (eGFR) equation to measure kidney function despite the development of more up-to-date methods. In this study, we developed two sets of DL models using fundus images from the UK Biobank to ascertain the effects of using a creatinine and cystatin-C eGFR equation over the baseline creatinine-only eGFR equation on fundus image-based DL CKD predictors. Our results show that a creatinine and cystatin-C eGFR significantly improved classification performance over the baseline creatinine-only eGFR when the models were evaluated conventionally. However, these differences were no longer significant when the models were assessed on clinical labels based on ICD10. Furthermore, we also observed variations in model performance and systemic condition incidence between our study and the ones conducted previously. We hypothesize that limitations in existing eGFR equations and the paucity of retinal features uniquely indicative of CKD may contribute to these inconsistencies. These findings emphasize the need for developing more transparent models to facilitate a better understanding of the mechanisms underpinning the ability of DL models to detect CKD from fundus images. [ABSTRACT FROM AUTHOR]

Abstract Background It has been proposed that in the absence of a blood supply, the ocular lens operates an internal microcirculation system. This system delivers nutrients, removes waste products and maintains ionic homeostasis in the lens. The microcirculation is generated by spatial differences in membrane transport properties; and previously has been modelled by an equivalent electrical circuit and solved analytically. While effective, this approach did not fully account for all the anatomical and functional complexities of the lens. To encapsulate these complexities we have created a 3D finite element computer model of the lens. Methods Initially, we created an anatomically-correct representative mesh of the lens. We then implemented the Stokes and advective Nernst-Plank equations, in order to model the water and ion fluxes respectively. Next we complemented the model with experimentally-measured surface ionic concentrations as boundary conditions and solved it. Results Our model calculated the standing ionic concentrations and electrical potential gradients in the lens. Furthermore, it generated vector maps of intra- and extracellular space ion and water fluxes that are proposed to circulate throughout the lens. These fields have only been measured on the surface of the lens and our calculations are the first 3D representation of their direction and magnitude in the lens. Conclusion Values for steady state standing fields for concentration and electrical potential plus ionic and fluid fluxes calculated by our model exhibited broad agreement with observed experimental values. Our model of lens function represents a platform to integrate new experimental data as they emerge and assist us to understand how the integrated structure and function of the lens contributes to the maintenance of its transparency.